[HN Gopher] Kiro: A new agentic IDE
       ___________________________________________________________________
        
       Kiro: A new agentic IDE
        
       Author : QuinnyPig
       Score  : 991 points
       Date   : 2025-07-14 14:24 UTC (1 days ago)
        
 (HTM) web link (kiro.dev)
 (TXT) w3m dump (kiro.dev)
        
       | QuinnyPig wrote:
       | I got to play with this for the past week, and it's surprisingly
       | good from an angle of "does a lot of the context engineering work
       | for you." It enforces a rigor that I don't usually bring to vibe
       | coding...
        
         | NathanKP wrote:
         | Thanks so much for your feedback Corey! That's one of the big
         | goals of Kiro: to add a bit more of the rigor required to keep
         | your code projects sane as they grow over time. I think Kiro
         | hits the best of both worlds: the easy fun of "vibe coding" at
         | first but then when its time to do some software engineering,
         | Kiro is there to help dig deep into the technical requirements,
         | write the architectural design, and break the big project up
         | into reasonable tasks.
        
         | mh- wrote:
         | Can it sort out AWS bills yet?
         | 
         |  _(I initially started writing this as a joke upon recognizing
         | your name, but now I think I 'm serious..)_
        
           | QuinnyPig wrote:
           | I've yet to see a GenAI system that comes even slightly
           | close. They're dangerously inaccurate in this space.
        
             | mh- wrote:
             | That's been my experience as well. Makes sense, there's
             | little training data available and the (public) docs and
             | (first-party) tooling remain dreadful.
        
             | laurent_du wrote:
             | You probably need an ad hoc MCP for this kind of things.
        
               | QuinnyPig wrote:
               | You need far more than that. Beyond the basic resource
               | sizing / misconfiguration issues, it's highly
               | contextually dependent to an environment / institution. A
               | change that's great for one customer could be ruinous for
               | another.
        
       | techpineapple wrote:
       | Why does it feel like all tech companies are the same these days?
       | It wasn't always like this right?
        
         | NitpickLawyer wrote:
         | Because collecting signals from the people that use these
         | systems is extremely valuable. This kind of data is almost
         | impossible to gather unless you own such a product. And those
         | that do probably won't sell to the competition. So, it makes
         | sense that everyone is in the me too phase.
         | 
         | Goog is even heavily subsidising this. Anthropic is likely
         | doing it with their top tiers as well. Even the small ones @20$
         | most likely did in the beginning.
        
         | empath75 wrote:
         | All the tech companies have a lot of software developers
         | working there and they always have a ton of projects around
         | software development and deployment that they've released. It's
         | been new that they've been _monetizing them_, but that pretty
         | much has to be done for AI tooling because of inferencing
         | costs....
        
         | AstroBen wrote:
         | It's a new category of tool and they're all competing for it
        
       | NathanKP wrote:
       | Hello folks! I've been working on Kiro for nearly a year now.
       | Happy to chat about some of the things that make it unique in the
       | IDE space. We've added a few powerful things that I think make it
       | a bit different from other similar AI editors.
       | 
       | In specific, I'm really proud of "spec driven development", which
       | is based on the internal processes that software development
       | teams at Amazon use to build very large technical projects. Kiro
       | can take your basic "vibe coding" prompt, and expand it into deep
       | technical requirements, a design document (with diagrams), and a
       | task list to break down large projects into smaller, more
       | realistic chunks of work.
       | 
       | I've had a ton of fun not just working on Kiro, but also coding
       | with Kiro. I've also published a sample project I built while
       | working on Kiro. It's a fairly extensive codebase for an infinite
       | crafting game, almost 95% AI coded, thanks to the power of Kiro:
       | https://github.com/kirodotdev/spirit-of-kiro
        
         | charlysl wrote:
         | Is it something similar to Harper Reed's "My LLM codegen
         | workflow atm"?
         | 
         | https://harper.blog/2025/02/16/my-llm-codegen-workflow-atm/
        
           | NathanKP wrote:
           | Actually yes! I saw this post some months ago, and thought to
           | myself: "Wow this is really close to what we've been
           | building". Kiro uses three files though: requirements,
           | design, and then tasks. The requirements doc is a bunch of
           | statements that define all the edge cases you might not have
           | originally thought of. Design looks at what is currently in
           | the code, how the code implementation differs from the
           | requirements, and what technical changes need to happen to
           | resolve the difference. Then tasks breaks the very large end
           | to end development flow up into smaller pieces that an LLM
           | can realistically tackle. The agent then keeps track of it's
           | work in the tasks file.
           | 
           | Realistically, I don't think that Harper's statement of "I
           | get to play cookie clicker" is achievable, at least not for
           | nontrivial tasks. Current LLM's still need a skilled human
           | SDE in the loop. But Kiro does help that loop run a lot
           | smoother and on much larger tasks than a traditional AI agent
           | can tackle.
        
             | charlysl wrote:
             | Thank you, I will certainly check this out because this is
             | something I've been sort of doing, manually, but I am still
             | struggling to get the right workflow.
             | 
             | This recent OpenAI presentation might resonate too then:
             | 
             |  _Prompt Engineering is dead (everything is a spec)
             | 
             | In an era where AI transforms software development, the
             | most valuable skill isn't writing code - it's communicating
             | intent with precision. This talk reveals how
             | specifications, not prompts or code, are becoming the
             | fundamental unit of programming, and why spec-writing is
             | the new superpower.
             | 
             | Drawing from production experience, we demonstrate how
             | rigorous, versioned specifications serve as the source of
             | truth that compiles to documentation, evaluations, model
             | behaviors, and maybe even code.
             | 
             | Just as the US Constitution acts as a versioned spec with
             | judicial review as its grader, AI systems need executable
             | specifications that align both human teams and machine
             | intelligence. We'll look at OpenAI's Model Spec as a real-
             | world example._
             | 
             | https://youtu.be/8rABwKRsec4?si=waiZj9CnqsX9TXrM
        
               | sirsinsalot wrote:
               | You know what an executable spec is? Source code.
        
             | exclipy wrote:
             | That's a compelling three file format.
             | 
             | Have you considered a fourth file for Implemented such that
             | Spec = Implemented + Design?
             | 
             | It would serve both as a check that nothing is missing from
             | Design, and can also be an index for where to find things
             | in the code, what architecture / patterns exist that should
             | be reused where possible.
             | 
             | And what about coding standards / style guide? Where does
             | that go?
        
               | NathanKP wrote:
               | That is interesting. So far we are just using the task
               | list to keep track of the list of implemented tasks. In
               | the long run I expect there will be an even more rigorous
               | mapping between the actual requirements and the specific
               | lines of code that implement the requirements. So there
               | might be a fourth file one day!
               | 
               | Coding standards / style guide are both part of the
               | "steering" files: https://kiro.dev/docs/steering/index
        
         | htrp wrote:
         | Is this being powered by any specific model?
         | 
         | >overage charges for agentic interactions will be $0.04 per
         | interaction, and if enabled, will begin consuming overages once
         | your included amounts are used (1,000 interactions for Pro
         | tier, 3,000 for Pro+ tier). Limits are applied at the user
         | level. For example, if you are a Pro tier customer who uses
         | 1,200 requests, your bill would show an overage charge of $8
         | (200 x $0.04). Overages for agentic interactions must be
         | enabled prior to use.
         | 
         | What is defined as an interaction?
         | 
         | EDIT: RTFM
         | 
         | >Whenever you ask Kiro something, it consumes an agentic
         | interaction. This includes chat, a single spec execution,
         | and/or every time an agent hook executes. However, the work
         | Kiro does to complete your request--such as calling other
         | tools, or taking multiple attempts--does not count towards your
         | interactions.
        
           | NathanKP wrote:
           | There is a model picker that currently allows you to switch
           | between Claude Sonnet 4.0 and Claude Sonnet 3.7
           | 
           | And yes, Kiro is agentic, so it can (and often does) execute
           | a long running multi-turn workflow in response to your
           | interactions, however, the billing model is based on your
           | manual interaction that kicks off the workflow (via chat,
           | spec, or hook), even if that agent workflow takes many turns
           | for Kiro to complete
        
             | moffkalast wrote:
             | Ah yes the classic Cline setup, you can choose any model as
             | long as it's Claude. Anthropic has to be really making API
             | bank these days.
        
         | clbrmbr wrote:
         | Nicely done. I particularly like the emphasis on writing specs
         | which really is something new in the space and makes Kirk not
         | just "Cursor clone". This is something missing in Claude
         | Code... the user needs to remember to ask Claude to update the
         | specs.
         | 
         | How does Kirk deal with changes to the requirements? Are all
         | the specs updated?
        
           | NathanKP wrote:
           | Currently specifications are mostly static documents. While
           | they can be refreshed this is a more manual process, and if
           | you do "vibe coding" via Kiro it can make code changes
           | without updating the specs at all.
           | 
           | I find the best way to use specs is to progressively commit
           | them into the repo as an append only "history" showing the
           | gradual change of the project over time. You can use Kiro to
           | modify an existing spec and update it to match the new
           | intended state of the project, but this somehow feels a bit
           | less valuable compared to having a historical record of all
           | the design choices that led from where you started to where
           | you now are.
           | 
           | I think in the long run Kiro will be able to serve both types
           | of use: keeping a single authoritative library of specs for
           | each feature, and keeping a historical record of mutations
           | over time.
        
         | darkwater wrote:
         | Hello! What is the connection with AWS? Do you work for AWS? Is
         | this going to be some official AWS product, backed by Amazon Q
         | or Bedrock?
        
           | NathanKP wrote:
           | Kiro is created by an AWS team, and originates from AWS
           | expertise. We are using Kiro internally as one of our
           | recommended tools for development within AWS (and Amazon). So
           | Kiro is an official AWS product, however, we are also keeping
           | it slightly separated from the rest of core AWS.
           | 
           | For example, you can use Kiro without having any AWS account
           | at all. Kiro has social login through Google and GitHub.
           | Basically, Kiro is backed by AWS, but is it's own standalone
           | product, and we hope to see it grow and appeal to a broader
           | audience than just AWS customers.
        
             | cl0wnshoes wrote:
             | Seems like social login isn't working for me on OSX. Just
             | downloaded Kiro, clicked the Google option, allowed the
             | app, and then get redirected back to
             | http://localhost:3128/oauth/callback with an error "Error:
             | AuthSSOServer: missing state".
        
               | NathanKP wrote:
               | Thanks for the report! I'll keep an eye on it. So far we
               | aren't seeing any other reported issues, so it's possible
               | that a browser extension, or something else in your setup
               | is messing with the SSO flow.
               | 
               | Redirect back to localhost:3128 is normal, that's where
               | Kiro is watching for a callback, but the missing state is
               | not normal. Something may have stripped the info out of
               | the callback before it occurred, which is why I suspect
               | an extension in your browser.
               | 
               | Will keep an eye on this though!
        
               | cl0wnshoes wrote:
               | FWIW Github login worked, only extensions I run is a
               | password manager and Kagi.
        
               | NathanKP wrote:
               | Thanks for the additional info!
        
               | Imustaskforhelp wrote:
               | After you said that google login didn't work, since I had
               | also used github login, I wanted to tell that github
               | login had worked for me, but you beat me to it!
               | 
               | I think Auth can be a bit of mess, but yes Its still
               | absolutely great that I can just login with github and it
               | just works, I am trying out Kiro right as we speak!
        
               | homami wrote:
               | It is also not working for me, this opens
               | http://localhost:3128/oauth/callback?code=... but on Kiro
               | interface I see "There was an error signing you in.
               | Please try again"
        
               | DividableMiddle wrote:
               | Same error as the others. Looks like auth is successful
               | in popup window: "You can close this window".
               | 
               | Then in Kiro I see "There was an error signing you in.
               | Please try again.".
               | 
               | FWIW, I've tried GitHub & Google, in different browsers,
               | on different networks.
        
               | DividableMiddle wrote:
               | For me, it was Little Snitch blocking the request..
        
               | totality wrote:
               | Can you please report an issue on our GitHub Issue
               | tracker: https://github.com/kirodotdev/Kiro/issues?
               | 
               | Or can you join the Discord and message me directly
               | @swaminator
        
             | robbomacrae wrote:
             | This is a really interesting setup. If it's not too forward
             | to ask, how is the team structured in terms of incentives?
             | Is Kiro fully within the AMZN comp / RSUs structure, or
             | does it operate more like a spinout with potential for more
             | direct upside? I'm always curious how teams balance the
             | tradeoff between the support of a big org vs having more
             | control over your fate by going fully independent.
        
               | tuananh wrote:
               | this kinda speak about how anti-DX AWS is
        
         | qrush wrote:
         | Are there plans to let AWS customers hook this up to Bedrock /
         | use models through that?
        
           | NathanKP wrote:
           | At this time Kiro is a standalone product that does not
           | require an AWS account at all. Kiro is powered by Bedrock
           | behind the scenes, but it has a layer of abstraction between
           | Kiro and Bedrock, which includes system prompts and
           | additional functionality. I can definitely take this as a
           | feature request though!
        
             | powvans wrote:
             | If this integrated with AWS for billing, usage, and IAM
             | purposes it would be a no brainer to have my team trying
             | this out today.
        
               | NathanKP wrote:
               | You can do that!
               | 
               | There is an AWS IAM Identity Center option for login as
               | well: https://kiro.dev/docs/reference/auth-methods/#aws-
               | iam-identi...
               | 
               | We really need to add some more step by step docs for
               | setting this up, but it's very similar to the Amazon Q
               | Developer integration with AWS IAM Identity Center if you
               | are familiar with that:
               | https://docs.aws.amazon.com/amazonq/latest/qdeveloper-
               | ug/sec...
        
               | powvans wrote:
               | Nice, I'll have to put my (employer's) money where my
               | mouth is and try it out tomorrow. Thanks!
        
         | postalcoder wrote:
         | I don't know if this is feedback for Kiro per se or more
         | feedback for this category of applications as a whole, but I've
         | personally noticed that the biggest barrier holding me back
         | from giving an earnest look at new coding agents are the custom
         | rules I've set up w/ my existing agents. I have extensively
         | used Copilot, Continue, Cursor, Cline, Aider, Roo Code, and
         | Claude Code. I've just finished porting my rules over to Claude
         | Code and this is something I do not want to do again [even if
         | it's as simple as dragging and dropping files].
         | 
         | Companies would benefit a lot by creating better onboarding
         | flows that migrate users from other applications. It should
         | either bring in the rules 1:1 or have an llm agent transform
         | them into a format that works better for the agent.
        
           | namanyayg wrote:
           | in the early days of building something like that, would love
           | to talk for 10 minutes and get your advice if you have the
           | time? I couldn't find your email but mine is in my profile.
        
           | ffsm8 wrote:
           | Or a proper standard like MCP was for agentic tool use, this
           | time for context setup...
        
             | chrisweekly wrote:
             | Problems w auth / security in MCP skeeve me out. For that
             | reason, I really don't want to invest in workflows that
             | depend on MCP and have steered clear. But I'd be grateful
             | for well-informed comments / advice on that front.
             | 
             | As for a hypothetical new "context setup" protocol like you
             | posit, I suspect it'd benefit from the "cognitive tools"
             | ideas in this awesome paper / project:
             | <https://github.com/davidkimai/Context-Engineering>
             | 
             | ^ inspiring stuff
        
           | NathanKP wrote:
           | You will be happy to find out that Kiro is quite good at
           | this! One of my favorite features is "Steering Rules". Kiro
           | can help you write steering rules for your projects, and the
           | steering rules that it auto generates are actually super
           | great for large projects. You can see some examples of auto
           | generated steering files here in one of my open source
           | projects: https://github.com/kirodotdev/spirit-of-
           | kiro/tree/main/.kiro...
           | 
           | Also these steering rules are just markdown files, so you can
           | just drop your other rules files from other tools into the
           | `.kiro/steering` directory, and they work as is.
        
             | adastra22 wrote:
             | "I really don't want to do X"
             | 
             | "Kirk is actually quite good at this: you just have to do
             | X"
             | 
             | "..."
        
               | NathanKP wrote:
               | At the prompt: "I have extensively used Copilot,
               | Continue, Cursor, Cline, Aider, Roo Code, and Claude
               | Code. I do not want to move my files over again for Kiro
               | [even if it's as simple as dragging and dropping files].
               | Do it for me"
               | 
               | Kiro will do it for you automatically.
        
               | adastra22 wrote:
               | And then you have two separate specifications of your
               | intent, with the ongoing problems that causes. It's not
               | the same thing.
        
               | NathanKP wrote:
               | Yeah it would be nice if there was one way to specify the
               | rules and intent, but you know how these things go:
               | https://xkcd.com/927/
               | 
               | In all seriousness, I'm sure this will become more
               | standardized over time, in the same way that MCP has
               | standardized tool use.
               | 
               | I've long been interested in something that can gather
               | lightweight rules files from all your subdirectories as
               | well, like a grandparent rule file that inherits and
               | absorbs the rules of children modules that you have
               | imported. Something kind of like this:
               | https://github.com/ash-project/usage_rules
               | 
               | I think over time there will be more and more sources and
               | entities that desire to preemptively provide some
               | lightweight instructive steering content to guide their
               | own use. But in the meantime we just have to deal with
               | the standard proliferation until someone creates
               | something amazing enough to suck everyone else in.
        
               | helpfulContrib wrote:
               | Porting rules is one of the responsibilities of keeping
               | them.
        
           | theshrike79 wrote:
           | I just have a "neutral" guidance markdown setup written in a
           | repo.
           | 
           | Then I add it as a git submodule to my projects and tell
           | whatever agents to look at @llm-shared/ and update its own
           | rule file(s) accordingly
        
             | touristtam wrote:
             | I don't add them as submodule but just symlink and ignore
             | them globally so they never find their way into codebase; I
             | have colleagues that frown upon using LLMs, and. I am not
             | going to start a war over their preferences.
        
           | re5i5tor wrote:
           | Not Kiro related, but do your Claude Code version of rules
           | end up as CLAUDE.md files in various locations?
        
           | sys13 wrote:
           | Agents.md is at least used by both codex and GitHub copilot.
           | VSCode has its own thing for instruction files and Claude.md
           | is also its own thing :(
        
             | nsonha wrote:
             | and opencode
        
               | efitz wrote:
               | and cline (.clinerules)
        
               | nsonha wrote:
               | I mean opencode reads AGENTS.md
        
             | insane_dreamer wrote:
             | My Claude.md is a symlink to agents.md.
        
           | esafak wrote:
           | There should be a standard rule format in a standard place,
           | like ~/.config/llms/rules.md
        
             | brulard wrote:
             | this. We need a common file for all these tools. It's not
             | like they can not read the format of each other.
        
               | brulard wrote:
               | This comment gets downvoted a lot and I can not figure
               | why. Is the idea that agentic AI solutions could use
               | single common file for the directions misguided or did I
               | put the message together wrong?
        
             | kaptainscarlet wrote:
             | .vibecodingrc sounds better?
        
             | yodon wrote:
             | > There should be a standard rule format
             | 
             | We are a few months into widespread use of this class of
             | technology. Now is a terrible time to introduce standards.
             | Would be a small short term gain delivering huge long term
             | pain.
        
           | newman314 wrote:
           | It would sure be nice to have some standardized conventions
           | around this. AGENTS.md etc. It seems insane to have to have
           | multiple files/rules for essentially the same goals just for
           | different tools.
        
             | tln wrote:
             | Thats the convention I am using.
             | 
             | My CLAUDE.md and GEMINI.md both just say "See AGENTS.md".
        
               | mkw5053 wrote:
               | Same
        
               | Zopieux wrote:
               | Have you heard about symlinks yet?
               | 
               | The idea of having a bunch of A100 GPU cycles needed to
               | process the natural language equivalent of a file pointer
               | makes me deeply sad about the current state of software
               | development.
        
               | smus wrote:
               | Are you implying frontier models are running on a100s?
               | Certainly not
        
               | mdaniel wrote:
               | This take reminds me of the pain I experience when I
               | watch people type website addresses into the google
               | search box
        
             | seunosewa wrote:
             | How about:
             | 
             | Creating a MCP server that all the agents are configured to
             | retrieve the rules from?
        
               | 0x457 wrote:
               | Then you have to add a rule to every agent to tell it to
               | use this tool.
        
             | insane_dreamer wrote:
             | symlinks
        
           | apwell23 wrote:
           | > have an llm agent transform them into a format that works
           | better for the agent.
           | 
           | you can do this today though.
        
             | efitz wrote:
             | AFAICT there is no "format" to agent rule files; it's just
             | text describing how you'd like the LLM to behave. Typically
             | I've seen bullet lists.
             | 
             | Some agents have multiple prompts that are used for
             | different modes; I've typically seen this stored as JSON
             | that is agent specific and wouldn't necessarily apply to
             | different agents.
             | 
             | The only agent specific thing I've ever included in a
             | context file is referring to a specific tool. I probably
             | could have abstracted that by describing it as "the tool
             | that does X" or by just telling it to do the function that
             | the tool does.
        
         | spgingras wrote:
         | Can you comment on how the IDE performs on large codebases?
         | Does the spec based approach help with it? Any examples you can
         | give from experience at Amazon?
        
           | NathanKP wrote:
           | It works great in really large codebases!
           | 
           | I've published a sample project that is medium sized, about
           | 20k lines encompassing a game client, game server, and
           | background service: https://github.com/kirodotdev/spirit-of-
           | kiro This has been all developed by Kiro. The way Kiro is
           | able to work in these larger projects is thanks to steering
           | files like these:
           | 
           | - Structure, helps Kiro navigate the large project:
           | https://github.com/kirodotdev/spirit-of-
           | kiro/blob/main/.kiro...
           | 
           | - Tech, helps Kiro stay consistent with the tech it uses in a
           | large project: https://github.com/kirodotdev/spirit-of-
           | kiro/blob/main/.kiro...
           | 
           | And yes, the specs do help a lot. They help Kiro spend more
           | time gathering context before getting to work, which helps
           | the new features integrate into the existing codebase better,
           | with less duplication, and more accuracy.
        
         | svieira wrote:
         | Is this supposed to be a demo of how wide-ranging Kiro is or
         | how _accurate_ it is? Because the very first item in the
         | screenshots is in a superposition of conflicting states from
         | various parts of its description.
         | 
         | That said, thanks for being willing to demo what kinds of
         | things it can do!
        
         | theusus wrote:
         | Why build an editor and not a CLI. VS code is really slow for
         | me and I would have preferred a CLI.
        
           | NathanKP wrote:
           | Stay tuned! I think there is definitely room for a CLI
           | version as well. That said, IDE's have a significant
           | advantage over CLI because of the features available to them.
           | For example, the reason why IDE's feel "slow" is often
           | because they just come with more features: automatic linters
           | and code formatters, type checkers, LSP servers.
           | 
           | An agent running in the IDE can make use of all this context
           | to provide better results. So, for example, you will see Kiro
           | automatically notice and attempt to resolve problems from the
           | "Problems" tab in the IDE. Kiro will look at what files you
           | have open and attempt to use that info to jump to the right
           | context faster.
           | 
           | The way I describe it is that the ceiling for an IDE agent is
           | a lot higher than a CLI agent, just because the IDE agent has
           | more context info to work with. CLI agents are great too, but
           | I think the IDE can go a lot further because it has more
           | tools available, and more info about what you are doing,
           | where you are working, etc
        
             | didibus wrote:
             | That's all old news. Claude Code and even Amazon Q CLI can
             | leverage all this context through MCP as well, with
             | connecting to LSP servers, computing repo-maps or code
             | indexes, integrating with linters, etc.
             | 
             | In my opinion, CLIs have a higher ceiling, and then they
             | are easy to integrate into CI/CD, run them in parallel,
             | etc.
        
               | NathanKP wrote:
               | MCP is great, but it adds a lot of extra latency. The MCP
               | servers themselves will stuff your context full of tool
               | details, taking up valuable tokens that could be spent on
               | code context. Then at runtime the LLM has to decide to
               | call a tool, the tool call has to come back to your
               | machine, the data is gathered and sent back to the LLM,
               | then the LLM can act on that data. Multiply this by
               | however many rounds of tool use the LLM decides it needs
               | prior to taking action. If you are lucky the LLM will do
               | a single round of parallel tool use, but not always.
               | 
               | The advantage of something more purpose built for
               | gathering context from the IDE is that you can skip a lot
               | of roundtrips. Knowing the user's intent upfront, the IDE
               | can gather all the necessary context data preemptively,
               | filter it down to a token efficient representation of
               | just the relevant stuff, add it in the context
               | preemptively along with the user's prompt, and there is a
               | single trip to the LLM before the LLM gets to work.
               | 
               | But yeah I agree with your point about CLI capabilities
               | for running in parallel, integrating in other places.
               | There is totally room for both, I just think that when it
               | comes to authoring code in the flow, the IDE approach
               | feels a bit smoother to me.
        
               | didibus wrote:
               | I feel what you say is true only for auto-complete, which
               | is no longer the ideal workflow for agentic coding.
               | Otherwise the IDE doesn't know what it should include or
               | not in the context, and you need an AI model to determine
               | that.
               | 
               | What people do to avoid what you discussed, is multi-
               | agents. The main agent can build up context, plan, than
               | delegate execution to other agents, etc.
               | 
               | In my opinion, the benefit of the IDE is really just in
               | the possibility of an improved UI/UX over a TUI.
        
               | nwienert wrote:
               | It's so much easier for me to prompt by:
               | 
               | - cmd-t fuzzy finding files of cmd-p finding symbols to
               | open the various files that are relevant
               | 
               | - selecting a few lines in each file using fast IDE
               | shortcuts to move and add
               | 
               | - drag and drop an image or other json files into prompt
               | 
               | - not leave the editor im already working on
               | 
               | Not to mention:
               | 
               | - viewing the agents edits as a diff in the editor and
               | all the benefits of easily switching between tabs and one
               | click rejecting parts etc
               | 
               | - seeing the sidebar of the agents thoughts and progress
               | async alongside the code as I keep looking at things
               | 
               | - pausing the agent and reversing back steps visually
               | with the sidebar
               | 
               | - not having to reconfig or setup my entire dev
               | environment for some CLI - for example the biome v2 lsp
               | just works since it's already working in code which has
               | the best support for these things
               | 
               | And really the list of reasons an editor is far better
               | just never ends. Claude is ok, but I'm way way faster
               | with Cursor when I do need AI.
        
               | didibus wrote:
               | To each their own, and I absolutely agree with the prior
               | poster about both existing making a lot of sense. It
               | comes down to personal preference. I just wanted to point
               | out the CLI has no less support for feature and context,
               | just a different UX to them.
        
               | 9cb14c1ec0 wrote:
               | The next level of features I want from Claude Code is
               | LSPs built right into it, rather that something I have to
               | configure with some random MCP server I download from
               | some random place.
        
             | blibble wrote:
             | > For example, the reason why IDE's feel "slow" is often
             | because they just come with more features:
             | 
             | IDEs don't feel slow, they ARE slow
             | 
             | because written in HTML and Javascript
             | 
             | go and try Delphi from 2005, it's blazing fast (and more
             | functional...)
        
               | usef- wrote:
               | I'm surprised none of them have built on Zed yet
        
               | WD-42 wrote:
               | Rust is too hard when you can quickly fork vscode and
               | hack together enough JavaScript to hopefully get acquired
               | before the moat evaporates.
        
               | iamsaitam wrote:
               | Confidently wrong are we? I use VSCode daily with a
               | couple of extensions and it's fast, never stutters and I
               | never have to wait for anything, so I'm not sure where
               | you pulled that one from.
        
               | cess11 wrote:
               | It's not an IDE, and it's actually pretty sluggish.
        
           | didibus wrote:
           | They already have a CLI that is similar to Claude Code:
           | Amazon Q CLI, you can download it here:
           | https://github.com/aws/amazon-q-developer-cli
           | 
           | It actually has a pretty decent free tier, and maybe the
           | subscription is better value than Claude Code, but hard to
           | tell.
        
             | __bjoernd wrote:
             | It uses the same models as Claude Code. I've been using Q
             | CLI a lot and love it, but I'm amazed by what Claude Code
             | can do.
        
           | Imustaskforhelp wrote:
           | There are still people not even using an editor, but rather
           | using vibe-coding apps like lovable.
           | 
           | Also,I don't mean to be rude to cursor but the fact that they
           | are literally just a vscode wrapper still, to this day makes
           | me really crazy thinking that the value of an AI editor could
           | be so high..
           | 
           | I think it was the lack of competition really, Cursor (IMO)
           | always felt like the biggest player, I think there was
           | continue.dev before that, but that's all I know before
           | Cursor.
           | 
           | After Cursor became a hit, there are lot more things now like
           | (Void editor?) etc.
           | 
           | Also, if you Find Vscode editor slow, try zed. But like my
           | brother said to me when I was shilling zed, Vscode is just
           | for manipulating texts and using LSP. He personally didn't
           | feel like it was there any meaningful slowness to Vscode even
           | though he had tried zed. Zed has Ai stuff too iirc
           | 
           | Now Sure, they could've created CLI, but there are a lot of
           | really decent CLI like SST/opencode and even gemini cli.
           | Though I have heard good things about claude code too.
           | 
           | Honestly, I just think that any efforts in anything is cool.
           | I just like it when there are a lot of options and so things
           | stay a little competitive I guess.
        
             | nsonha wrote:
             | > just a vscode wrapper
             | 
             | Isn't that like all software. Before Claude 4 and Copilot
             | agent mode, Cursor/Cline did a lot of work under the hood
             | to achieve the same agentic capabilities, that stuff has
             | nothing to do with VSCode.
        
           | moffkalast wrote:
           | What kind of toaster are you running vscode on, it runs about
           | as fast as any basic text editor even in VMs for me.
        
         | ActorNightly wrote:
         | While I like the product, implementation could be better. Kiro
         | is sitting idle with Helper Plugin using a shitload of CPU for
         | no reason.
        
           | slacktivism123 wrote:
           | Having ten "Electron Helper (Plugin)" eat a GB of RAM each on
           | idle is the premier desktop experience nowadays. We can't
           | have native apps any more: we don't know how to build them.
        
             | ActorNightly wrote:
             | I use VSCode with Continue. It has a Code Helper Plugin,
             | which peaks during use, but when idle it doesn't use any
             | resource. Something is up with the Kiro version where some
             | background task is running.
        
               | Imustaskforhelp wrote:
               | See the NathanKP comment on the (grand parent post?), It
               | was the indexing which was causing the resource
               | utiliazation.
        
               | ActorNightly wrote:
               | For a large project, it seems to still be using high CPU
               | (maybe continuously indexing)
        
             | esafak wrote:
             | Fortunately the next generation seems to be CLI based!
             | Maybe we'll go back to native apps in the next generation.
        
             | rcleveng wrote:
             | It's not that people don't know how to build a native
             | application, it's rather a native application that runs
             | across Windows, Mac and Linux is still really hard. Trying
             | to add in a web version of the same application is
             | impossible.
             | 
             | ActiveX and Java Web Start, etc all tried to do this, and
             | all of them ended up deprecated and out of favor for native
             | web solutions.
             | 
             | Java IDEs did a lot of this for many years (Eclipse,
             | IntelliJ, NetBeans, JDeveloper, etc) and they worked
             | reasonably well on the desktop, but had no path to offering
             | a web hosted solution (like gitpod or codespaces)
             | 
             | There are not a lot of options here, compiling down a
             | native solution to wasm and running it in the browser would
             | work, I'm not sure if the performance would be
             | substantially better or more consistent across all OS'es
             | and web unfortunately.
             | 
             | So we are where we are :)
        
               | dgfitz wrote:
               | > It's not that people don't know how to build a native
               | application, it's rather a native application that runs
               | across Windows, Mac and Linux is still really hard.
               | Trying to add in a web version of the same application is
               | impossible.
               | 
               | Qt is pretty good at this actually. I don't have a Mac,
               | but building the same codebase for windows, linux, and a
               | wasm target was pretty neat the first time I did it.
        
               | ActorNightly wrote:
               | >it's rather a native application that runs across
               | Windows, Mac and Linux is still really hard.
               | 
               | Not really. Electron is basically web browser.
               | 
               | The issue is that a cornerstone of modern development is
               | basically "don't rewrite what already has been written",
               | however the problem is that you always get optimization
               | creep because of this - people just build shit on top of
               | other shit continuously and never go back and optimize.
        
             | WD-42 wrote:
             | Zed exists.
        
             | imtringued wrote:
             | I genuinely thought we have enough RAM since the 16GB era.
             | Nope, they figured out a way to consume it all plus a dozen
             | of GB in swap.
        
           | NathanKP wrote:
           | A few things:
           | 
           | 1) It's normal for Kiro (and almost every AI editor) to use a
           | lot more CPU when you first start it up, because it is
           | indexing your codebase in the background, for faster and more
           | accurate results when you prompt. That indexing should
           | complete at some point
           | 
           | 2) On initial setup of Kiro it will import and install your
           | plugins from VS Code. If you have a large number of plugins
           | this continues in the background, and can be quite CPU heavy
           | as it extracts and runs the installs for each plugin. This is
           | a one time performance hit though.
           | 
           | 3) If your computer is truly idle, most modern CPU's get
           | throttled back to save power. When the CPU is throttled, even
           | a tiny amount of CPU utilization can show up as a large
           | percentage of the CPU, but that's just because the CPU has
           | been throttled back to a very slow clock speed.
           | 
           | In my setup (minimal plugins, medium sized codebase, computer
           | set to never idle the processor clock) I rarely see Kiro
           | helper go above .4% CPU utilization, so if you are seeing
           | high CPU it is likely for one of the above reasons.
        
             | ActorNightly wrote:
             | Thanks for the reply. It was the indexing.
             | 
             | Is there any way to control this? I have my
             | files.watcherExclude setting, does it respect that?
        
               | NathanKP wrote:
               | I believe that the file indexing exclusion is based on
               | .gitignore, not files.watcherExclude, but let me check on
               | that and confirm.
        
               | ActorNightly wrote:
               | I tried with a small project, it worked fine, no high CPU
               | usage.
               | 
               | However with a large project, it seems that it indexed,
               | then dropped CPU, then I started opening up files and
               | working with them, then the CPU spiked again.
        
               | NathanKP wrote:
               | I'll look into this. Kiro is supposed to be doing
               | progressive reindexing. When you make a change it should
               | only have to reindex the files that changed. If you have
               | any logs or other data you are willing to share, to help
               | the team investigate you can use the "report a bug /
               | suggest an idea" link at the bottom, or open an issue at:
               | https://github.com/kirodotdev/Kiro/issues
        
               | ActorNightly wrote:
               | I ironically don't have a github account (use my own
               | personal gittea). However I don't think its the indexing.
               | I left Kiro open for a day, and CPU usage is still high.
        
         | sinatra wrote:
         | Have you documented how you built this project using Kiro? Your
         | learnings may help us get the best out of Kiro as we experiment
         | with it for our medium+ size projects.
        
           | NathanKP wrote:
           | I've got a longer personal blogpost coming soon!
           | 
           | But in the meantime I'm also the author of the "Learn by
           | Playing" guide in the Kiro docs. It goes step by step through
           | using Kiro on this codebase, in the `challenge` branch. You
           | can see how Kiro performs on a series of tasks starting with
           | light things like basic vibe coding to update an HTML page,
           | then slightly deeper things like fixing some bugs that I
           | deliberately left in the code, then even deeper to a full
           | fledged project to add email verification and password reset
           | across client, server, and infrastructure as code. There is
           | also an intro to using hooks, MCP, and steering files to
           | completely customize the behavior of Kiro.
           | 
           | Guide link here: https://kiro.dev/docs/guides/learn-by-
           | playing/
        
         | epiccoleman wrote:
         | > It's a fairly extensive codebase for an infinite crafting
         | game, almost 95% AI coded, thanks to the power of Kiro:
         | https://github.com/kirodotdev/spirit-of-kiro
         | 
         | This, along with the "CHALLENGE.md" and "ROADMAP.md" document,
         | is an incredibly cool way to show off your project and to give
         | people a playground to use to try it out. The game idea itself
         | is pretty interesting too.
         | 
         | It would be awesome if I ... didn't have to deal with AWS to
         | use it. I guess maybe that might be a good use case for agentic
         | coding: "Hey, Kiro - can you make this thing just use a local
         | database and my Anthropic API key?"
         | 
         | Complaining aside though, I think that's just such a cool
         | framework for a demo. Nice idea.
        
           | NathanKP wrote:
           | Thanks a lot! I plan to fork the project and make a generic
           | version that runs entirely locally using your GPU to do
           | everything. My early tests ran pretty well on NVIDIA 5070. So
           | that's next on my project list to open source in my free
           | time. The only thing more fun that building an AI agent, is
           | using it to build your own ideas!
        
             | underlines wrote:
             | 5070Ti user here: We are 150 people in a SME and most of
             | our projects NDA for gov & defense clients absolutely
             | forbid us to use any cloud based IDE tools like GitHub
             | Copilot etc. Would love for this project to provide a BYOK
             | and even Bring Your Own Inference Endpoint. You can still
             | create licensing terms for business clients.
        
               | hedgehog wrote:
               | What models do you use that you've found to be powerful
               | enough to be helpful?
        
               | Aherontas wrote:
               | I have the same question, do you use already an on prem
               | RAG system?
        
         | asib wrote:
         | FYI: I'm trying Kiro out now, and the IDE keeps popping open
         | the integrated terminal window of its own accord. Has done it
         | multiple times, including when I don't even have the IDE window
         | focussed on my desktop. Every 5-10 minutes it seems.
         | 
         | Neither VSCode nor Cursor do this, so even if it's an extension
         | triggering it somehow, the behaviour in Kiro is different to
         | those other two.
        
         | marviel wrote:
         | nice! Can't agree more on Vibe Speccing.
         | 
         | I wrote more about Spec Driven AI development here:
         | https://lukebechtel.com/blog/vibe-speccing
        
         | erichocean wrote:
         | How much are you using Kiro to improve itself? 100% of the
         | time? 10% of the time? Never?
        
           | NathanKP wrote:
           | It has grown over time as Kiro has developed. Many of the
           | most recent features in Kiro were developed using Kiro
           | specifications. We have a Twitch stream scheduled with some
           | engineers from the Kiro team where we plan to take live Q&A
           | about this in specific, how they are using Kiro to build
           | Kiro, etc. I don't have the schedule setup yet, but we've got
           | the channel setup here: https://www.twitch.tv/kirodotdev
        
         | personjerry wrote:
         | Why not deploy the game? I'd love to try it
        
           | NathanKP wrote:
           | I have a personal deployment of the game, but it costs money
           | to run the LLM so I'm not sharing that with all of Hacker
           | News haha. I've got an appsec ticket open to host an
           | "official AWS" version where AWS pays the LLM bill, but that
           | might take a while longer to get approved. For now the best
           | way to experiment is playing with it locally.
           | 
           | I'm also thinking of creating a fork of the project that is
           | designed to run entirely locally using your GPU. I believe
           | with current quantized models, and a decent GPU, you can have
           | an adequate enough fully local experience with this game,
           | even the dynamic image generation part.
        
         | ugh123 wrote:
         | Love the game! would be interesting to see an example of
         | prompts used to do this.
        
           | NathanKP wrote:
           | Unfortunately, midway through the project I lost the file
           | where I was keeping track of all the prompts I used as I
           | built. I do have some of them, plan to publish a wrap up
           | analysis of those at some point.
           | 
           | If you were referring to the prompts inside of the game, you
           | might find those fun and interesting. This one in particular
           | is the heart of the game:
           | https://github.com/kirodotdev/spirit-of-
           | kiro/blob/main/serve...
        
         | mkagenius wrote:
         | Hello Nathan,
         | 
         | I integrated[1] the recently released Apple Container (instead
         | of shell) to run codes generated by Kiro. It works great!
         | 
         | 1. CodeRunner: https://github.com/BandarLabs/coderunner
        
           | BoiledCabbage wrote:
           | Can you please stop shilling for this?
           | 
           | HN comments aren't an ad network...
        
         | thekevan wrote:
         | Will the pricing include consideration for if someone if an
         | Amazon Prime subscriber?
        
         | apwell23 wrote:
         | > almost 95% AI coded
         | 
         | I think its because you didn't have hard expectations for the
         | output. You were ok with anything that kind of looked ok.
        
           | NathanKP wrote:
           | False. In order to maintain high quality I often rejected the
           | first result and regenerated the code with a more precise
           | prompt, rather than taking the first result. I also regularly
           | used "refactor prompts" to ask Kiro to change the code to
           | match my high expectations.
           | 
           | Just because you use AI does not mean that you need to be
           | careless about quality, nor is AI an excuse to turn off your
           | brain and just hit accept on the first result.
           | 
           | There is still a skill and craft to coding with AI, it's just
           | that you will find yourself discarding, regenerating, and
           | rebuilding things much faster than you did before.
           | 
           | In this project I deliberately avoided manual typing as much
           | as possible, and instead found ways to prompt Kiro to get the
           | results I wanted, and that's why 95% of it has been written
           | by Kiro, rather than by hand. In the process, I got better at
           | prompting, faster at it, and reached a much higher success
           | rate at approving the initial pass. Early on I often
           | regenerated a segment of code with more precise instructions
           | three or four times, but this was also early in Kiro's
           | development, with a dumber model, and with myself having less
           | prompting skill.
        
             | apwell23 wrote:
             | > precise prompt
             | 
             | If there was such a thing you would just check in your
             | prompts into your repo and CI would build your final
             | application from prompts and deploy it.
             | 
             | So it follows that if you are accepting 95% of what random
             | output is being given to you. you are either doing
             | something really mundane and straightforward or you don't
             | care much about the shape of the output ( not to be
             | confused with quality) .
             | 
             | Like in this case you were also the Product Owner who had
             | the final say about what's acceptable.
        
               | a1j9o94 wrote:
               | The above is saying more precise not completely precise.
               | The overall point they're making is you still are
               | responsible for the code you commit.
               | 
               | If they are saying the code in this project was in line
               | with what they would have written, I lean towards
               | trusting their assessment.
        
               | apwell23 wrote:
               | I am not doubting 95% acceptance rate all. I've pure
               | vibecoded many toy projects myself.
               | 
               | > in line with what they would have written,
               | 
               | point i am making is that they didn't know what they
               | would've written. they had a rough overall idea but
               | details were being accepted on the fly. They were trying
               | out bunch of things and see what looks good based on a
               | rough idea of what output should be.
               | 
               | In a real world project you are not both product owner
               | and coder.
        
               | NathanKP wrote:
               | To be clear I did not have a 95% acceptance rate. I'm
               | saying that in the final published repo, 95% of the lines
               | of code were written by AI, not by me. I discarded and
               | refactored code along the way many times, but I did that
               | by also using the AI. My end goal was to keep my hands
               | off the code as much as possible and get better at
               | describing exactly what I wanted from the AI.
        
               | NathanKP wrote:
               | > if you are accepting 95% of what random output is being
               | given to you
               | 
               | I am not, and don't expect to be able to do that for many
               | years yet. The models aren't that good yet.
               | 
               | I would estimate that I accepted perhaps 25% of the
               | initial code output from the LLM. The other 75% of output
               | I wasn't satisfied with I just unapplied and retried with
               | a different prompt, or I refactored or mutated it using a
               | followup prompt.
               | 
               | In the final project 95% of the committed lines of code
               | in the published version were written by AI, however
               | there was probably 4x as much discarded AI generated code
               | along the way that was also written by AI. Often the
               | first take wasn't good enough so I modified it or
               | refactored it, also using AI. Over the course of using
               | the project I got better at providing more precise
               | prompts that generated good code the first time, however,
               | I rarely accepted the first draft of code back from Kiro
               | without making followup prompts.
               | 
               | A lot of people have a misguided thought that using AI
               | means you just accept the first draft that AI returns.
               | That's not the case. You absolutely should be reading the
               | code, and iterating on it using followup prompts.
        
         | dostick wrote:
         | Does it work for Swift development and can it compile to test
         | for compilation errors?
        
         | Szpadel wrote:
         | why it required forking vscode? what prevents this from being
         | just extension? from article I do not see any obvious
         | functionality that would prevent such implementation
        
           | touristtam wrote:
           | Maybe the fact that MSFT has been break extensions for fork
           | is enough?
        
         | orangebread wrote:
         | Hi Nathan, this is awesome. I also discovered similar workflows
         | and built SpecLinter:
         | https://github.com/orangebread/speclinter-mcp
         | 
         | Will be trying Kiro, excited to see how you approached
         | implementing a similar idea!
        
       | factorialboy wrote:
       | What's with the edited title "it's Cursor clone".
       | 
       | Unless it's literally a Cursor clone, I'd request to change it to
       | describe the product category.
       | 
       | Cursor by no means defines the whole category. Not even close.
        
         | KomoD wrote:
         | product category: "vscode with ai things slapped on top"
        
           | limpingninja wrote:
           | By vscode you mean atom clone with extra tools slapped on
           | top, right?
        
             | wg0 wrote:
             | And with atom you mean Notepad++ with extra tools slapped
             | on top?
        
               | actualwitch wrote:
               | To be fair, npp is not using electron. Atom is.
        
               | eddythompson80 wrote:
               | To be even more fair, the category used to be sublime
               | clones. Sublime was on a crazy run in the early 2010s and
               | there were various attempts at an "Open source Sublime".
        
         | dang wrote:
         | We've replaced the title. (Submitted title was "AWS launches
         | Kiro, its Cursor clone")
        
       | guluarte wrote:
       | loom mom, another vscode fork!
        
       | lonestarwarrior wrote:
       | I am a heavy Jetbrains user, I never liked the idea of Cursor. I
       | embraced Claude Code immediately when it came out.
        
         | jibe wrote:
         | Are you using the Claude Code plugin, or switching back and
         | forth between Claude Code and the Jetbrains IDE?
        
           | lonestarwarrior wrote:
           | With the plugin. CC runs in a terminal on the sidebar. The
           | plugin does not only provide diff view for CC edits, it also
           | gives CC access to diagnosis and all other IDE capabilities
           | through MCP.
        
         | williamzeng0 wrote:
         | VSCode is way worse for large codebases and also much worse for
         | Ruby, Golang, etc.
        
       | brene wrote:
       | wait, it's completely free during the preview period? That's a
       | better deal than Cursor, Windsurf, or Claude Code. Gotta check it
       | out
        
       | suralind wrote:
       | Here my problem with this: I don't want to be jumping an
       | editor/IDE every 6 months, learning new key bindings and even
       | more importantly, getting used to a completely new look.
       | 
       | In a space that moves as quickly as "AI" does, it is inevitable
       | that a better and cheaper solution will pop up at some point. We
       | kinda already see it with Cursor and Windsurf. I guess Claude
       | Code is all the rage now and I personally think CLI/TUI is the
       | way to go for anyone that has a similar view.
       | 
       | That said, I'm sure there's a very big user base (probably bigger
       | than terminal group) that will enjoy using this and other GUI
       | apps.
        
         | joelthelion wrote:
         | The nice thing about CLI/TUI is that you can keep using your
         | editor or IDE of choice and chat with the AI on the side.
        
         | ativzzz wrote:
         | Totally agreed, which is why I'm sticking with my editor
         | (neovim) regardless of whatever AI thing is hot and using tools
         | outside/analogous to it, currently claude code
        
         | znpy wrote:
         | > Here my problem with this: I don't want to be jumping an
         | editor/IDE every 6 months, learning new key bindings and even
         | more importantly, getting used to a completely new look.
         | 
         | You're basically advocating for GNU Emacs:
         | https://github.com/karthink/gptel
        
           | suralind wrote:
           | Thanks for the link. I'm not an emacs user and I'm more in
           | the search of something like opencode [1], but I think it's
           | not polished enough yet. I actually want to contribute to
           | open source, so maybe I should create my own thing, heh.
           | 
           | [1]: https://github.com/sst/opencode
        
           | aquariusDue wrote:
           | gptel is great, its one of the must have packages for Emacs
           | and I'm pretty sure that with time it will be one of the
           | reasons to use Emacs like org-mode has been for a long time.
           | 
           | For people wanting to get up and running with vanilla Emacs
           | (instead of a distribution) so that they can try out gptel
           | sometime this week, I recommend emacs-bedrock:
           | https://codeberg.org/ashton314/emacs-bedrock
           | 
           | And for a gptel backend Gemini is the fastest route
           | (excluding something local) from generating an API key to
           | using a LLM in Emacs (for free).
           | 
           | Bonus points because Emacs is useful for things other than
           | coding you can use gptel on your notes or any buffer really
           | to ask/talk about stuff.
        
         | TimMeade wrote:
         | Every 6 months? It's turning into every two weeks. Sticking
         | with claude code. Its working beautifully for us.
        
           | MuffinFlavored wrote:
           | I have a question. I do not like the concept of "agent mode"
           | for AI. I'm a control freak and I want to control every line
           | that gets committed because I am responsible for it and need
           | to understand/visualize/memorize every part of codebases I
           | work on.
           | 
           | Is Claude Code good for the "ask" flow? No, right?
           | 
           | The old flow before agent mode got added. Select some code,
           | ask questions about it or give an instruction on editing it
           | and then choose to accept the change.
           | 
           | As I understand (I could be wrong), with agent mode, it edits
           | the file for you, no way for you to accept before it does, so
           | you have to manually check the diff, roll back parts you
           | don't want, etc.
           | 
           | Am I right?
        
             | bryanlarsen wrote:
             | I like aider's solution of encapsulating each edit in a git
             | commit; I hope that gets widely adopted.
        
               | olivermuty wrote:
               | Add two lines to CLAUDE.md and claude code can do this as
               | well :)
        
               | NitpickLawyer wrote:
               | Unfortunately aider is showing its age. It is great for
               | what it does, but better LLMs + "agentic" have shown that
               | you can get more in the swe domain.
               | 
               | There was a paper recently where they had an LLM evolve
               | tool harnesses and got ~20% more than w/ aider on the
               | benchmark they used, so it's pretty clear that the models
               | + tools (+better harness) are better than just aider.
        
               | FergusArgyll wrote:
               | 1) You can plug in any model into aider 2) It can be
               | quite agentic
               | 
               | > evolve tool harnesses
               | 
               | Claude code & Gemini cli etc. don't do this either
        
               | NitpickLawyer wrote:
               | Don't get me wrong, I love aider and I've been using it
               | since the early days. I'm just commenting on the overall
               | "gains" and imo they are higher with the latest tools
               | (claude code, gemini, etc).
               | 
               | As for 1), I agree but you force the model to work within
               | aider's constraints. Claude4 for example excels at the
               | agentic flow and it's better at that than providing the
               | diffs that aider expects.
               | 
               | As for the last sentence, I disagree. They are evolving
               | the stack, and more importantly they are evolving both at
               | the same time, stack + LLM. That's the main reason they
               | all subsidise use atm, they are gathering data to improve
               | both. If I were to place a bet right now, I'd say that
               | provider_tool + provider_LLM > 3rd party tool + same
               | model in the short, medium and long term.
        
               | FergusArgyll wrote:
               | Oh, that's a good point, I misunderstood you to mean: The
               | LLM writes it's own harnesses etc.
        
               | manojlds wrote:
               | Each edit as in every little change?
        
               | bryanlarsen wrote:
               | Yes. Then you squash to make real commits.
        
             | qsort wrote:
             | Claude Code is definitely more agentic, but you can use it
             | in a variety of ways. In Plan Mode it won't touch the code,
             | and by default it asks you to accept every single diff.
             | With IDE integration you can definitely just highlight some
             | code and ask questions, I don't see why that workflow
             | wouldn't work.
        
             | cmrdporcupine wrote:
             | It could be better. I think the PMs and investors and
             | decision makers at these companies are running with a "we
             | want to replace / automate developers" philosophy, while
             | these tools are actually best at _augmenting_ developers.
             | And so they 're sorta builing with this "I'll do everything
             | and ask you for confirmation" (and basically encourage you
             | to give me blanket permission).
             | 
             | In reality these tools would be best if they took a more
             | socratic method, a more interactive pair programming
             | approach. So instead of giving you a blanket diff to accept
             | or refuse or "No, and here's some changes" -- it should be
             | more dialog oriented.
             | 
             | Of all of them so far though, I think Claude Code is
             | closest to this. IF you prompt it right you can have a much
             | more interactive workflow, and I find that most productive.
        
             | dangus wrote:
             | > As I understand (I could be wrong), with agent mode, it
             | edits the file for you, no way for you to accept before it
             | does, so you have to manually check the diff, roll back
             | parts you don't want, etc.
             | 
             | You're sort of technically correct but I wouldn't really
             | describe it this way exactly. You have to proactively
             | accept or reject all changes to your files in some way.
             | 
             | It is almost impossible to accidentally commit code you
             | don't want.
             | 
             | It's not really an edit in the same sense as an unstated
             | change. It doesn't even really do that until you accept the
             | result.
             | 
             | It's basically saving you a UI step compared to ask mode
             | with basically no downside.
        
             | TimMeade wrote:
             | We tend to allow this. But you can review the diff before
             | you allow it. It seems easier to say "roll that back" or
             | hit esc if you see it doing things you dont like and then
             | correcting it. I have to say the velocity is insane of
             | coding this way. We also commit a LOT and explicitly dont
             | allow claude to push code ever. That way we can roll back
             | if needed, but honestly it's pretty rare to need to. The
             | MAX plan is a must to work this way though.
        
             | memco wrote:
             | > As I understand (I could be wrong), with agent mode, it
             | edits the file for you, no way for you to accept before it
             | does, so you have to manually check the diff, roll back
             | parts you don't want, etc.
             | 
             | > Am I right?
             | 
             | With cursor you get reasonably flexible control at many
             | levels. You can have it only suggest changes that you have
             | to apply manually or you can have it make automatic changes
             | with various ways to review, change, reject or accept. I
             | usually have the changes made automatically but don't
             | accept the changes automatically. Cursor has a UI that lets
             | you review each edit individually, for the whole file or
             | all files. Depending on the situation I will use whichever
             | level is appropriate. The UI also allows you to revert
             | changes or you can ask the AI to undo or rework a change
             | that you just approved so there's plenty of ways to do
             | large changes without giving up control. There's also a
             | stop button you can use to interrupt mid-stream if the work
             | it's doing isn't what you want. It isn't flawless but I
             | haven't found myself in a corner where I couldn't get back
             | to a happy path.
        
           | NathanKP wrote:
           | I love Claude Code too, and it definitely has it's place. I
           | think that IDE's have a few advantages over CLI tools though.
           | In specific the IDE has a lot more contextual information
           | such as what files you have open, warnings from linters or
           | type checkers, information from LSP, etc.
           | 
           | I think it is entirely possible to build a fantastic CLI tool
           | for coding, and the CLI tools for coding already work well
           | enough, but there is just more context info available inside
           | of an IDE, therefore the ceiling is higher when working with
           | an agent that runs inside of the IDE. Context is king for LLM
           | results, and IDE's just have more context.
           | 
           | Over time I'm sure we'll see tools like Claude Code support
           | everything that an IDE can do, but for now if you want to
           | reach the same ceiling you still have to glue together a very
           | custom setup with MCP tool use, and that has the downside of
           | introducing additional tool use latency, compared to an IDE
           | that is able to source context directly from the IDE's
           | internal API, and provide that to the LLM nearly instantly.
        
             | TimMeade wrote:
             | I use claude code in vscode. Cmd-Esc opens a claude code
             | tab. Then /ide conects to the vscode and it's all like
             | cursor at that point.
        
               | epiccoleman wrote:
               | Same here - in fact, I just recently cancelled my Cursor
               | subscription because Claude Code + VSCode seems just as
               | good. I think Cursor is a decent product and some of the
               | UX it puts around LLM interaction is helpful - but I just
               | can't really justifying paying Cursor to middleman my
               | requests to LLM providers when Claude Pro is $20 / month.
        
         | bryanlarsen wrote:
         | They're all based vscode, so the switching costs are fairly
         | minimal? It'll get worse over time as they diverge, but at the
         | moment they're all fairly similar AFAICT. It's starting to
         | become noticeable that Cursor isn't picking up VSCode
         | enhancements and fixes, but it's still quite minor.
        
           | suralind wrote:
           | Not really, even at work I got to test couple different AI
           | solutions and the experience is always slightly different,
           | even if the editor is the same, for the most part. It's the
           | tiny things like using the prompt template, or opening the
           | panel. (I could, of course, make an attempt to customize the
           | keybindings, but why bother when it changes so quickly.)
        
             | scarface_74 wrote:
             | The entire idea that "I'm too cool to use an IDE" I find
             | kind of dumb. I was using a Turbo C IDE in college in 1994,
             | Visual Studio until 2019 and since then VSCode.
        
               | Oreb wrote:
               | I don't think "I'm too cool to use an IDE" was the point
               | being made. The point is that having to switch IDEs every
               | time the number one AI coding tool changes would be
               | annoying.
        
           | guluarte wrote:
           | only if you use vscode, I think TUIs are a better option
           | since a lot of us use other ides than vscode
        
             | theturtletalks wrote:
             | Seems like Amazon started making this when Cursor was hot
             | in the market, but now that CLI agents like Claude Code are
             | taking over, Kiro will have an uphill battle.
             | 
             | It's also not free or unlimited (though throttled) like
             | Cursor and Claude Code using max plan.
        
               | rob wrote:
               | I think IDE-based tools like Cursor, VS Code, etc, will
               | win out in the long term, especially as the younger
               | generation grows up.
               | 
               | In the short term though, I think CLI-based tools like
               | Claude Code are taking off because hardcore developers
               | see them as the last "vestige" they have in separating
               | themselves from the "noobs." They know there's still a
               | good portion of the public who don't know how to use the
               | terminal, install packages, or even know what Linux is.
        
               | guluarte wrote:
               | I think what is going to win is a tool independent to
               | your ide to run your agents, it could be a cli or a gui.
        
               | retinaros wrote:
               | You dreaming. The ui is gonna be like google for code. A
               | voice chat and an instruction/search bar that is it. The
               | model is the product
        
               | placardloop wrote:
               | Which is kind of ironic since the Amazon Q Developer CLI
               | (which is essentially Claude Code with a slightly
               | different wrapper) was released long before Claude Code
               | and seems to mostly be flying under the radar.
        
               | theturtletalks wrote:
               | Claude Code really was at the right place at the right
               | time. Cursor started putting new models under their MAX
               | plan that charges per use and I started getting worse
               | results with Cursor over time as they optimized costs. I
               | started looking into Cline/RooCode when Cursor did this
               | because I knew they were in the squeezing customers stage
               | now. I used those for a while with Sonnet thru
               | OpenRouter, but Anthropic had the genius plan of bundling
               | Claude Code with their Max plan. That made a lot of users
               | jump ship from Cursor and the difference is night and day
               | for me. Yes I pay 5 times more than I did with cursor,
               | but still less than using API credits and the results for
               | me have been superior.
        
               | nsonha wrote:
               | Claude Code is what it is because of Claude, TUI or not
               | isn't really the point. What makes IDEs lose to TUIs is
               | that the agentic models can really do more than coding
               | and is evolving toward a hands-off kind of workflow. A
               | clunky IDE is too much for that, but TUI is not the way
               | either. When has TUI ever been mainstream?
               | 
               | Agentic tools of the future will be rich notebook/chat
               | interface that's available in all form factors, which is
               | to say, most likely web/cross platform apps.
        
               | yencabulator wrote:
               | You can have an agent loop in your IDE, I don't see why
               | anything makes "IDEs lose to TUIs" there.
               | 
               | If anything, TUIs are the awkward in-between of "human in
               | the loop, but with poor tools" where one side is fully
               | automatic, agents suggesting fixes on issue tracker, and
               | the other is holding-AI's-hand where you review every
               | step one at a time.
               | 
               | I _hate_ trying to copy paste in /out of Claude Code's
               | unnecessarily-cute boxed text input.
               | 
               | Zed's implementation of the agent feedback loop isn't yet
               | as good as Claude Code, but there's nothing inherently
               | IDE-related in the parts that are lacking.
               | 
               | https://zed.dev/docs/ai/agent-panel
        
           | ImaCake wrote:
           | I just use VSCode with copilot and don't worry about these
           | re-skins. I don't get a lot of time to write code so I
           | certainly don't have time to learn a new IDE for a small
           | boost to my productivity when vscode gets me most of the way
           | already.
           | 
           | If these re-skinned vscode IDEs have any good ideas I'm sure
           | Microsoft will steal them anyway.
        
           | lxgr wrote:
           | Them all being based on VS Code makes it all the more
           | frustrating to have to switch IDEs to use them.
        
         | factorialboy wrote:
         | CLI -> Voice & Gesture UI
        
         | eulers_secret wrote:
         | YUP! This is why I've settled on Aider and it's "IDE
         | integration" (watches all files for comments that end in "AI!",
         | which then invokes the AI). I can then use it with whatever
         | editor I prefer. I view the vscode mono-culture as a bad thing.
         | I also like I can use any AI backend I like, which is really
         | how it should be: Vendor lock-in tools are bad, remember?
         | 
         | I guess you lose tab-completion suggestions, but I am not a fan
         | of those compared to 'normal' tab-complete (if backed by an
         | lang server). If I want AI, I'll write a short comment and
         | invoke the tool explicitly.
         | 
         | EDIT: Of course, it really depends an your usecase. I
         | maintain/upgrade C code libs and utils; I really cannot speak
         | to what works best for your env! Webdev is truly a different
         | world.
         | 
         | EDIT2: Can't leave this alone for some reason, the backend
         | thing is a big deal. Switching between Claude/Gemini/Deekseek
         | and even rando models like Qwen or Kimi is awesome, they can
         | fill in each other's holes or unblock a model which is 'stuck'.
        
         | seydor wrote:
         | people are trying to find a moat that will bind their userbase.
         | Browsers, editors, apps etc. There must be a format that locks
         | users in so they will try them all one after another
        
         | crinkly wrote:
         | This is why you will have to pry vim and my own brain out of my
         | cold dead hands.
         | 
         | It's not just the IDE but the ML model you are selling yourself
         | to. I see my colleagues atrophy before me. I see their tools
         | melt in their hands. I am rapidly becoming the only person
         | functionally capable of reason on my own. It's very very weird.
         | 
         | When the model money dries up what's going to happen?
        
           | ryandvm wrote:
           | I dunno. There's also a good chance that you just end up
           | being left behind like graybeards that only wanted to code in
           | C and assembler.
           | 
           | I too am old enough to have seen a lot of unnecessary tech
           | change cycles, and one thing I've noticed about this industry
           | is no matter how foolish a trend was, we almost never unwind
           | it.
        
             | crinkly wrote:
             | I get paid a fuck load of money to write C. Your point is?
             | 
             | As for trends, I've been around long enough to have seen
             | this cycle a couple of times...
        
               | ryandvm wrote:
               | > I get paid a fuck load of money to write C. Your point
               | is?
               | 
               | My point is there aren't many of you, are there?
               | 
               | All things considered, keeping up with the industry
               | trends is generally a more reliable career path.
        
               | crinkly wrote:
               | Correct but we are _never_ fungible. That's the trick for
               | a reliable career.
               | 
               | I've survived every single layoff season since 1995.
        
               | knowsuchagency wrote:
               | Ironically, Claude Code has me working in lower-level
               | languages with more low-level tools than ever before,
               | simply because of how powerful it is, particularly as a
               | terminal tool. I've always been more of a GUI person, but
               | now the editor I use most often is Helix.
               | 
               | If I've atrophied in certain aspects of my thinking, I
               | honestly think I've more than made up for it in learning
               | how to engineer the context and requirements for Claude
               | Code more effectively and to quickly dive in to fix
               | things without taking my hands off the keyboard and
               | leaving the terminal.
        
             | haiku2077 wrote:
             | > I dunno. There's also a good chance that you just end up
             | being left behind like graybeards that only wanted to code
             | in C and assembler.
             | 
             | All the people I know in the US with those skills make huge
             | amounts of money- at least, the ones who haven't already
             | retired rich.
        
               | rvz wrote:
               | Yes. The ones who maintain high risk system software that
               | allows all these machines to be able to train LLMs,
               | compile the systems software or maintaining systems that
               | ingest 2% of the worlds traffic are the ones who are
               | making a lot of money out of this.
               | 
               | Not the ones maintaining frontend web apps or "vibe
               | coding".
        
             | bowsamic wrote:
             | Remaining skilled while those around you atrophy is never a
             | bad decision
        
         | polynomial wrote:
         | > learning new key bindings
         | 
         | Why are they shipping them with different key bindings? Seems
         | like the opposite of what you do to encourage product adoption.
        
         | didibus wrote:
         | They have a CLI similar to Claude Code already:
         | https://github.com/aws/amazon-q-developer-cli
        
         | yakattak wrote:
         | All of these agentic IDEs could just be visual studio code
         | plugins. They're likely not because how do you secure VC
         | funding for a plugin?
        
           | umeshunni wrote:
           | More importantly - how do you monetize a plugin?
        
             | tacker2000 wrote:
             | There are lots of ecosystems where pro users pay for
             | plugins to get extra features. See the ecommerce domain,
             | jetbrains, even ms teams has plugins that are paid.
             | 
             | VSCode has some popular paid plugins like LSPs or some for
             | git.
             | 
             | I dont see why it wouldnt be possible to monetize a VSCode
             | plugin.
        
           | dcreater wrote:
           | But Continue and a bunch of others literally did that.
           | 
           | The better question is why is there this horrible monoculture
           | in SW startups around raising money through VCs? We need more
           | regular businesses who build something useful and charge a
           | fair price. Period.
        
         | apwell23 wrote:
         | this project was conceived when cursor was the king of
         | vibecoding. Everyone thought being an IDE would give you so
         | much more power.
        
         | bob1029 wrote:
         | I've been thinking about developing a VSIX for Visual Studio
         | 2022 that wraps my typical ChatGPT flow in the intellisense UX.
         | 
         | I don't mind that everyone is all-in with VSCode now, but I
         | already paid $500 for the big-boy version and I've got 20k
         | hours on it.
        
         | jillesvangurp wrote:
         | What I like about OpenAI's codex is that it's not an IDE but a
         | web based product that does things asynchronously from your
         | normal workflow. It creates branches and pull requests. And you
         | can iterate with it via git instead of working in the same
         | tool.
         | 
         | So, I can use the tools I use anyway and have AIs adapt to me
         | instead of me having to adapt to new AI powered tools. I'm
         | using a proper IDE (intellij). Me switching to cursor, kiro, or
         | whatever would be an enormously massive downgrade for me. These
         | tools don't come close to the utility and features of what I am
         | used to and depend on. And those new AI tools trying to catch
         | up with Intellij is not their focus or roadmap. I'm not going
         | to wait for that to happen. I need stuff that works now. Not
         | some years after they figure it out. And that includes AI
         | features.
         | 
         | There's a difference between vibe coding where you are sitting
         | on your hands and admiring all the crazy clever stuff the AI
         | does for you that you wouldn't be able to do yourself and
         | working on a system that you've spent years building from
         | scratch with AI to assist you. I do the latter. I'm constantly
         | intervening, dismissing poor results from AI, getting
         | frustrated with LLMs misunderstanding things, ignoring my
         | directions, not getting the full context, etc. But I'm also
         | getting a lot of value out of AIS with dealing with
         | tedious/repetitive stuff, figuring out weird bugs, pointing out
         | my mistakes, or generating perfectly usable solutions for TODOs
         | and FIXMEs I leave in my code. About 50-60% of the PRs codex
         | creates for me are pretty usable.
         | 
         | I use ChatGPT for the small stuff (it can look at intellij and
         | apply diffs) and codex for the bigger stuff "implement foo, add
         | some tests, and tell me when I can look at the PR". And maybe
         | I'll check out the branch and fix a few things myself. That's
         | something my IDE supports very well. It's not a big deal. It
         | doesn't need to be fixed.
         | 
         | I find that increasingly, model quality is not the main blocker
         | for this stuff but the developer/user experience is. Claude
         | might be better. But chat gpt has the far better UX. And I
         | don't even use o3 most of the time. I prefer the more rapid
         | responses other faster models give me. It's not a cost thing
         | but a speed thing. I only escalate to slower models when I
         | don't like the response I'm getting. Codex is nice but
         | slooooooow. But at least I can work on other stuff while it is
         | doing its thing. ChatGPT gives me instant gratification. Select
         | line, Option+shift+1, "Fix this", "....", "apply fix". That's
         | so nice and I do that a lot. And I didn't have to replace my
         | tools. In the same way, Claude code might be marginally better
         | at some stuff. But the Codex developer experience is superior.
         | 
         | So, Kiro sounds like a nice tool for people who don't need or
         | use IDEs. But it's not for me.
        
         | Andys wrote:
         | Try kilocode - https://kilocode.ai/ Its a VScode extension and
         | allows different LLMs to be used.
        
       | xnx wrote:
       | Title should be: "Introducing Kiro"
        
       | yahoozoo wrote:
       | Is this another VS Code fork or did they just completely rip the
       | VS code ui?
        
         | xena wrote:
         | It's another VS Code fork!
        
           | handfuloflight wrote:
           | Had they not forked VS Code the low value quips would reverse
           | to: "why didn't you just fork VS Code?"
        
         | TiredOfLife wrote:
         | Fork and an old one
        
       | cube00 wrote:
       | Hopefully better then the hell that is trying to use Amazon Q for
       | development.
        
       | angelmm wrote:
       | Many companies are considering IDEs the way to reach developers.
       | Atom started the trend of next generation IDEs and VSCode
       | consolidated most of the market. With the AI raising, people are
       | looking to get usage, gathering data, and positioning models. An
       | IDE provides you all of that.
       | 
       | AI seems to be a way to engage happy users to try new things.
       | Kiro joins a growing list of projects:
       | 
       | - Kiro (AWS)
       | 
       | - VSCode + Copilot (Microsoft)
       | 
       | - Windsurf (OpenAI tried to get it)
       | 
       | - Cursor
       | 
       | - Trae (Alibaba)
       | 
       | - Zed
       | 
       | - etc.
       | 
       | I put Zed in a separate category in the past. Now with assistants
       | / agents, it's playing on the same space.
       | 
       | The market is a bit saturated and tools like Claude Code gave
       | some flexibility and an alternative for users. I tried Cursor in
       | the past, and now I'm back to Helix / VSCode + Claude Code.
        
         | suralind wrote:
         | I love Zed as an editor/IDE without ANY AI/LLM features. I
         | think the AI support in Zed is actually pretty decent and I'm
         | still using it out of habit (actively trying to use more TUI
         | for AI).
         | 
         | But at the same time, it's my biggest worry that they will
         | continue on the AI and pollute the project with too much junk.
         | I gotta trust the smart minds behind it will find a way to
         | balance this trend.
        
           | angelmm wrote:
           | Totally. I think Zed has its own value proposition. That's
           | why I never put them close to other editors like Cursor at
           | the beginning.
           | 
           | Lately, I started putting it together due to all the AI
           | excitement. People try it because of the AI capabilities to
           | find an IDE that works for them.
           | 
           | I hope Zed continues providing new amazing features in all
           | the areas.
        
         | TiredOfLife wrote:
         | > Windsurf (OpenAI tried to get it)
         | 
         | And Google killed it.
        
         | bravesoul2 wrote:
         | It makes we attracted to Vim/Emacs. They'll be the same until I
         | die.
        
       | mupuff1234 wrote:
       | I'm surprised no one is gobbling up jetbrains.
        
         | TiredOfLife wrote:
         | They have been cleaning up and getting rid of projects, so
         | seems to be preparing for it.
        
           | williamzeng0 wrote:
           | do you mean jetbrains ai team?
        
       | ArcaneMoose wrote:
       | This is exactly how I've been building software with AI lately.
       | Getting AI to create a detailed plan with phases, then implement
       | and use a separate AI to review the code. It works quite well!
       | Curious to see how well it works when implemented directly in the
       | IDE
        
         | delfinom wrote:
         | At what point does the manager fire you and just let the AIs
         | have at it ;)
        
           | NathanKP wrote:
           | Realistically, none of the models can function fully
           | autonomously at this point. You still need a skilled human at
           | the helm. However, AI tools definitely change how the human
           | works. I find that I spend a lot less time thinking about
           | easy things, and a lot more time thinking about hard things.
           | 
           | Basically, the AI fast forwards through the easy stuff and I
           | just spend all day jumping directly from hard problem to hard
           | problem.
        
           | daxfohl wrote:
           | Nah, you never voluntarily reduce headcount. Headcount is
           | what keeps your salary coming. Any manager worth their salt
           | would use this newfound productivity to infringe on other
           | teams' domains: Hostile Takeover => More Headcount =>
           | Promotion. We'll see a lot of attempted empire building over
           | the next couple years while all this gets sorted out.
        
       | ranman wrote:
       | Caylent has been testing this for quite some time and I have to
       | say it's an interesting take. With claude code you can shift
       | between planning and coding modes and this offers a similar
       | approach. The speed is quite good and the results are solid. The
       | spec approach is solid but it takes a learning curve. Some of the
       | tooling and autojumps take a bit to get used to because they
       | differ from the other IDE approaches.
       | 
       | Overall I do believe this has accelerated our development and I'm
       | interested to see where it goes. I don't think it's a direct
       | comparison to claude code or cursor - its a different approach
       | with some overlap.
        
       | dangus wrote:
       | With my experience with Amazon Q in the AWS console (100%
       | useless, worse than a Google search), I can only assume that this
       | Kiro product will suck and not be a market leader.
       | 
       | As a customer I have no incentive to try it.
       | 
       | I think that reputation is 100% Amazon's fault. When all you do
       | is ship half-baked rushed products your customers will assume
       | your next big thing sucks because that's the reputation you built
       | for yourself.
        
         | shermantanktop wrote:
         | Given the rapidly-changing state of AI, "half-baked" is a
         | moving target. The Q console support was never great, but it's
         | materially worse than it was a year ago, relative to what could
         | be built today.
        
         | dangus wrote:
         | I would also like to add that forking VScode is not a value
         | add. Just publish a VSCode extension.
        
         | placardloop wrote:
         | AWS really shot themselves in the foot with naming everything
         | "Amazon Q <insert suffix here>". The Q that's in the console is
         | completely and entirely different from the "Q Developer" and
         | other AI products that AWS is launching.
         | 
         | The Q Developer CLI, Q Developer IDE plugins, and now Kiro are
         | pretty much just wrappers around Claude Sonnet 3.7/4, and work
         | just as well as them.
        
       | xena wrote:
       | This doesn't support development containers
       | (https://containers.dev), which means I can't insulate my machine
       | from AI tooling. Not keen on this unless it's somehow earth-
       | shattering.
        
         | Tokumei-no-hito wrote:
         | why doesn't it support them?
        
           | tristan957 wrote:
           | The remote containers extension on VSCode is proprietary.
           | Cursor had to write their remote extension suite.
        
       | 2Gkashmiri wrote:
       | Im.not a dev so i dont use these vs code forks...
       | 
       | How is one fork different from cursor or kiro or something else?
       | 
       | Arent these like what i assume skinning chromium or something
       | more ?
        
       | gsibble wrote:
       | Am I the only one who finds AI not very helpful?
       | 
       | Just this morning, Cursor was giving me a ton of incorrect tab
       | completions. When I use prompts, it tends to break more than it
       | fixes. It's still a lot faster to write by hand. Lots of
       | libraries that take *arguments in Python also cannot be groked by
       | AI.
        
         | shermantanktop wrote:
         | Of course you aren't the only one, and I'm sure you know that
         | you aren't the only one.
         | 
         | I doubt these tools will ever convince every last person on
         | every single use case, so the existence of those people isn't
         | exactly an indictment.
        
         | lvl155 wrote:
         | You have to put in some effort to put in the guardrails and
         | scaffolds to make it produce what you want. It's definitely not
         | out-of-the-box deal.
        
         | neutronicus wrote:
         | At work it's supremely unhelpful. Giant C++ codebase, big
         | enough to choke even traditional analysis tools like
         | IntelliSense, lots of proprietary libraries.
         | 
         | I have found it extremely useful for spinning up personal
         | projects though.
         | 
         | My wife bought us Claude subscriptions and she's been straight-
         | up vibe coding an educational game for our son with impressive
         | results (she is a UX designer so a lot more attuned to vibes
         | than gen-pop). I'm picking up some computational physics
         | research threads I dropped in grad school and Claude Code has
         | been incredible at everything _besides_ physics and HPC. Define
         | and parse an input file format, integrate I /O libraries, turn
         | my slapdash notes into LaTeX with nice TiKz diagrams, etc.
         | 
         | Hoping I can transfer over some insights to make it more
         | helpful at work.
        
       | Velorivox wrote:
       | I really like that the testimonials are linked directly to the
       | Github accounts of the contributors. I've seen a lot of websites
       | where it's questionable at best whether the people reviewing the
       | product even exist.
       | 
       | It's also interesting that the pricing is in terms of
       | "interactions" rather than tokens. I don't believe I've seen that
       | before.
        
       | aspittel wrote:
       | I've been testing Kiro for a few months, and yes, it's an agentic
       | IDE like many others. However, a lot of the features are
       | different - the spec driven development is a game changer. It
       | feels like you're truly software engineering versus vibing - you
       | break a problem into small, solvable steps using specs. So are
       | agent hooks - there are great use cases like updating Asana
       | statuses or syncing your design system with Figma.
        
       | jackmenotti wrote:
       | No autocomplete? Why? I mean is the current trend to leave all
       | the control from the experienced dev hands and just review the
       | final code? Not my cup of tea, I'll keep using Cursor and "vibe
       | code" with smart rewrites
        
         | NathanKP wrote:
         | Kiro does have autocomplete. It's just not advertised on the
         | product page as a star feature.
         | 
         | In my experience using Kiro you are still going to be hands on
         | with the code. Personally I choose to turn AI powered
         | autocomplete off because when I do touch the code manually it's
         | usually for the purposes of working on something tricky that AI
         | would likely not get right in autocomplete either.
         | 
         | However, the Kiro autocomplete is average in capability in my
         | experience, and you can absolutely use it to write code by hand
         | as well.
        
       | mmaunder wrote:
       | Big opportunity to be the first open source model agnostic Claude
       | Code with widespread adoption. You'll be the vim, the Linux, the
       | nginx, the MySQL of agentic coding. Who will it be? It's wide
       | open right now.
        
         | NathanKP wrote:
         | This is much more tricky than you'd think. Claude Code and
         | other similar tools only work as well as they do because the
         | prompts that power it have been tuned to match a specific
         | model.
         | 
         | When you make a tool that is "model agnostic" you also make a
         | tool that is unable to play to the individual strengths of each
         | model, or you set yourself up for a massive, multiplicative
         | effort of trying to tune your tool to every single popular
         | model out there, even though some of the models are drastically
         | less capable than others.
        
       | petesergeant wrote:
       | I think this is where the stickiness is with generation; very
       | little chance I'm switching from Claude Code unless something
       | exceptionally better comes along at this point. Assuming I'm not
       | abnormal, this is a huge win for Anthropic.
        
       | hmate9 wrote:
       | From the little I've played with it so far, its spec-driven
       | format seems to give better results when making large changes to
       | code.
        
       | premn wrote:
       | Kiro's spec based development is something that's new (for me
       | atleast) and it's pretty good.
        
       | ghimanshu6 wrote:
       | AWSome KIROOOOOO
        
       | pvartist wrote:
       | Impressive to see an AI IDE tackle the real world complexity of
       | software development. Love the separation of modes- Vibe for
       | ideation, Spec for clarity, and Agent Hooks for ongoing
       | maintenance. The spec-driven approach feels like a natural
       | evolution beyond the typical AI prototype tools. Excited to try
       | it out on a live project!
        
       | badaldavda wrote:
       | Awesome! Tried it and I should say, adds structure to my vibe
       | coding. Loving it.
        
       | croskcool wrote:
       | Why couldn't this be built inside Q?
        
       | nullandvoid wrote:
       | I'm already burnt from amazon Q which was forced onto us in an
       | alpha state in my workplace - was miles behind competitors for a
       | full year, before we finally won the battle to move back to co-
       | pilot.
       | 
       | Going to take a while before I trust any AWS AI related tooling
       | won't just be abandoned / mis-managed after my prior experience.
        
       | claudecodefan wrote:
       | Too late to the party. Feels like the market has moved onto
       | Claude Code and terminal agents. I use Claude Code extensively
       | and love the flexibility and fluidity. Also works well through
       | the terminal integration in IDE.
        
         | admn2 wrote:
         | Is there a way to preview changes in CC before "accepting" like
         | you can in Cursor?
        
       | WorldPeas wrote:
       | does this have any carveouts for CDK or other aws services? I've
       | found that sonnet sometimes struggles to know what params to use,
       | while amazon Q despite being on paper a worse model, can. It
       | seems this uses sonnet, but are there any adjustments?
        
       | lvl155 wrote:
       | Unless it offers me something substantially better than VSCode, I
       | am not gonna switch and it has a lot to do with unsupported
       | extensions. For now, I think UX preference has to be CLI with web
       | gui wrapper where you can pick models, agents, requirements, etc
       | and let that run anywhere, even headless. I don't like how these
       | guys (as in all the VSCode wrappers) are trying to sucker people
       | onto their platform to lock you in.
       | 
       | Edit: I know there's manual VSIX route.
        
         | ActorNightly wrote:
         | Kiro is Vscode (forked from the open source version). I
         | imported all the settings and extensions into it from VSCode,
         | worked fine.
        
         | Tokumei-no-hito wrote:
         | what are the unsupported extensions? i thought the support had
         | to do with marketplace access (search / download / update) but
         | if you already have the vsix it can be installed in any vscode
         | fork
        
           | SyrupThinker wrote:
           | Some of Microsoft's extensions are licensed such that they
           | may only be used with their own products (i.e. the official
           | VS Code they offer for download, etc.). This already affects
           | Cursor for example:
           | 
           | https://github.com/microsoft/vscode-dotnettools/issues/1909
        
       | kixiQu wrote:
       | Hey, a cute logo! I didn't know AWS allowed cute things.
        
       | storus wrote:
       | So we have another ugly VSCode clone with the same legal/support
       | issues as all the other clones, but without any vibe-coding
       | worthy assists like voice dictation/control or any other major
       | differentiator. Just another "me too" project from AWS to scratch
       | some product manager itch and commoditize the complement of some
       | competitor.
        
       | roficas wrote:
       | awesome tool!
        
       | trenchgun wrote:
       | Kiro in Finnish means "a curse".
        
         | mcraiha wrote:
         | More modern would be Kirous.
        
       | chandureddyvari wrote:
       | I use Roo code with orchestrator(Boomerang) mode which pretty
       | much has similar workflow. The orchestrator calls the architect
       | to design the specs, and after iterating and agreeing on the
       | approach, it is handed over to Code mode to execute the tasks.
       | Google Gemini 2.5 pro is pretty good at orchestration due to its
       | 1M context and I use claude sonnet 4 for code mode.
       | 
       | What else does Kiro do differently?
       | 
       | Edit: The hooks feature looks nifty. How is the memory management
       | handled? Any codebase indexing etc? Support to add external MCP
       | servers like context7 etc?
        
         | touristtam wrote:
         | Interesting. Do you have a write up on this setup I (we) could
         | follow?
        
       | aliljet wrote:
       | I'm a little confused about how pricing works here. What is an
       | 'agentic interaction' and how does that translate to dollars? And
       | how does this work with models that are differently priced???
        
       | t14000 wrote:
       | Why do I need to log in to a text editor?
        
       | fHr wrote:
       | Amazon ewwwww
        
       | johntarter wrote:
       | Is there any way to move the chat window to the primary side bar?
       | Having two side bars open takes up a lot of space. Not sure why
       | this pattern persists in these VScode forks.
        
         | duderific wrote:
         | Generally in VSCode and its clones you can drag the window
         | anywhere you like. I've been using my Copilot in the lower area
         | which spans multiple panels, to give myself a little more
         | viewing space.
        
       | alexts-aws wrote:
       | I tried Kiro just to test the tool and I was able to create a
       | small order application. I liked it that that it created the
       | documentation including planning and test scenarios. I will
       | continue using the tool to create more complex apps.
        
       | steve_adams_86 wrote:
       | I love the emphasis on specs here; this is something I do with
       | Claude Code (maintain a set of specs in text as we work).
       | 
       | I always keep the readme and some basic architecture docs (using
       | markdown/mermaid) updated as I go, and I often just work on those
       | rather than on code with Claude, because I find the value it
       | offers is less in code generation and more in helping me document
       | the rubber ducking process into useful schematics and
       | architecture.
       | 
       | What can Kiro offer that's meaningfully better than what I'm
       | already doing? I can take my system anywhere Claude Code and my
       | repos can go, using whatever editor I like. Does Kiro have some
       | special sauce for making this approach work better? Maybe some
       | DSL it uses for more succinct and actionable diagrams and plans?
       | 
       | As much as I like the idea, I find it so hard to abandon a
       | process I've been working on for months, using tools I'm already
       | productive with.
       | 
       | Also, will pricing essentially be bedrock pricing, or will there
       | be a value-add margin tacked on?
        
         | NathanKP wrote:
         | > Does Kiro have some special sauce for making this approach
         | work better?
         | 
         | I'd like to think so, but you'd have to compare the results to
         | what you are currently doing to see how you feel about it. I
         | personally love the format that it uses to define requirements,
         | and the details of the software design docs that it writes
         | (including mermaid diagrams)
         | 
         | > will pricing essentially be bedrock pricing, or will there be
         | a value-add margin tacked on?
         | 
         | The pricing is a flat rate, with a cap on number of
         | interactions per month. Each human driven "push" for Kiro to do
         | something is an interaction toward your limit, but Kiro may
         | work autonomously for many turns based on an interaction, and
         | will produce significant amounts of code from a single
         | interaction.
         | 
         | More details here: https://kiro.dev/pricing/
        
           | steve_adams_86 wrote:
           | Ah, thanks for the pricing link. I saw 'Kiro is free to use
           | during preview' or similar and assumed pricing is hidden.
           | 
           | At $39/month, is 3000 interactions a high limit? I use Claude
           | Code on the $30 plan (I think), and routinely hit limits. I'm
           | not ready to jump to the next tier, though. I think it's
           | $200/month, and the NGO I work for isn't prepared to throw
           | that kind of cash at developers (I'm second-rate here; the
           | science comes first)
        
             | SamDc73 wrote:
             | CC have $20 and $100 and a $200 tiers
        
               | steve_adams_86 wrote:
               | Right, thank you. I pay ~$30 CAD, but the other tier is
               | $200 USD. I should just sick to USD.
        
             | NathanKP wrote:
             | It's hard to directly compare, but 3000 interactions should
             | be very, very high. Think of each of these 3000
             | interactions as you supplying a prompt that potentially
             | runs for 3-5 minutes of Kiro iterating away on writing
             | code. With appropriately sized prompts (most likely aided
             | by spec mode), you could write a ridiculous amount of code.
             | 
             | For reference 3000 interactions * assumed 3 mins of AI work
             | per interaction / 60 mins per hour / 8 working hours per
             | day equals 18.75 working days of nonstop back to back AI
             | coding. Typical month has 20-23 working days. But
             | realistically you likely won't be using Kiro nonstop all
             | day back to back, so 3000 interactions per month should
             | more than cover your work month.
        
               | steve_adams_86 wrote:
               | Thanks, this is exactly what I wondered. In practical
               | terms I can't imagine hitting that limit.
               | 
               | It's a bit more than I pay in CAD, but I'd pay quite a
               | bit more just to stop hitting the limits I have with
               | Claude, even if the rest of the service was identical.
               | It's a pain. My usage is also very bursty so I spend
               | several days getting no usage, then repeatedly hit limits
               | while I brainstorm and spec things out.
               | 
               | I'm thinking out loud here in case it's useful feedback.
               | It seems like a great pricing schemes for my use case.
        
       | 44za12 wrote:
       | What models are supported, can we add custom models? I'm
       | struggling to add Kimi K2 to cursor and surf.
        
       | acd wrote:
       | Not amazed! Tell me one good reason I should use it?
       | 
       | Lets see EU US data privacy shield gone. Aws a bunch of open
       | source tools gobbled together with proprietary source. Trust in
       | made in US cloud platform tools is gone!
        
       | didibus wrote:
       | For anyone wondering, Amazon already offers an Agentic coding CLI
       | similar to Claude Code: https://github.com/aws/amazon-q-
       | developer-cli
       | 
       | It has a pretty decent free tier, and maybe the subscription is
       | better value than Claude Code, but hard to tell.
       | 
       | It supports MCP as well.
       | 
       | Amazon Q also has a VC Code and IntelliJ Idea plugin too, Kiro
       | goes beyond what you can do as a plugin in VS Code though,
       | similar to why Cursor had to fork VS Code.
        
         | artdigital wrote:
         | Q CLI is great. It's basically Claude models but pretty much
         | unlimited and only for $20
         | 
         | Not as polished as Claude Code but also a bit price difference
        
           | SyrupThinker wrote:
           | That sounds too good to be true, and it seems like they are
           | indeed introducing a usage system similar to their
           | competitors next month?
           | 
           | > Starting August 1, 2025, we're introducing a new pricing
           | plan for Amazon Q Developer designed to make things simpler
           | and more valuable for developers.
           | 
           | > Pro Tier: Expanded limits $19/mo. per user
           | 
           | > 1,000 agentic requests per month included (starting
           | 8/1/2025)
           | 
           | - https://aws.amazon.com/q/developer/pricing/
           | 
           | Previously agentic use was apparently "free", but with a set
           | deadline in June, so it seems like this was just for a
           | testing phase?
        
             | touristtam wrote:
             | 50 request per month? Am I reading that correctly? If
             | that's the case it is pityful.
        
         | smcleod wrote:
         | Q CLI has so many issues though, injects so much junk into you
         | shell profiles it can slow down your terminal invocations by
         | seconds, and it doesn't support standard streamableHttp / SSE
         | MCP servers.
        
           | didibus wrote:
           | That's for the shell auto-complete feature which I turn off.
        
             | smcleod wrote:
             | It's not that simple: https://github.com/aws/amazon-q-
             | developer-cli/issues/844
        
           | grogenaut wrote:
           | just turn those off, it's just 2 includes one at the top and
           | one at the bottom of your shell... file a ticket about making
           | it optional or not. I believe that the shell integration /
           | autocomplete is where they started the product so it's
           | probably one of those core features in the product team's
           | minds.
           | 
           | I generally like the integration but in some cases it's
           | getting in the way of other ai that is runnin q to quit and
           | all of a sudden its in q... I renamed it to amazonq and
           | removed it from my zshrc and added it as a command to
           | integrate, amazonqinit
        
             | smcleod wrote:
             | I'm the one that logged this:
             | https://github.com/aws/amazon-q-developer-cli/issues/844
             | Amazon really have dropped the ball with fixing it.
        
           | tmvphil wrote:
           | I turn that stuff off and just use `q chat` for everything,
           | which actually works very well in my experience.
        
       | SAI_Peregrinus wrote:
       | I'll stick with my gentic IDE & write my own bugs.
        
       | qq66 wrote:
       | How do I know that this is an AWS product? This should be on an
       | Amazon domain or the blog should be on an Amazon domain that
       | links to the site.
        
       | Imustaskforhelp wrote:
       | So I am pretty sure that there is some aws/amazon service which
       | can provide gpu's / model inference too.
       | 
       | I read it (I think) in one of the comment that There is a model
       | picker that currently allows you to switch between Claude Sonnet
       | 4.0 and Claude Sonnet 3.7
       | 
       | So is this just using Claude?
       | 
       | I really thought that the advantages of using Kiro might really
       | be that of the leverage that Amazon Gpu's infrastructure could
       | provide, maybe even some discounts to lure people to Kiro.
       | 
       | I am pretty sure that a lot of people will ask you the same
       | question, But I would really appreciate it if you could answer me
       | this question in preferably simple terms: "Why Kiro? Why not all
       | the other stuff that has come before it and the stuff that will
       | come after it"
       | 
       | Also I am really having some dejavu but while writing this
       | comment, has the title of this post changed, I swear I saw
       | something written in the header with Amazon and now I don't see
       | it. honestly, I am really being so off-topic but after seeing
       | this name change of the post, I really wish if that there was
       | some website that could track all the name changes of posts that
       | happen in HN, because I was completely baffled by this name
       | change or I am being totally paranoid.
        
         | pqdbr wrote:
         | The previous title stated Kiro as being "Amazon's Cursor
         | clone", which I agree was not adequate.
        
           | Imustaskforhelp wrote:
           | My suspicions were right that the name had something to do
           | with amazon because I went into this thread thinking about
           | Amazon's unique position in this market.
        
         | cowsandmilk wrote:
         | It does use AWS infrastructure, ie Bedrock which supports many
         | different models.
        
           | Imustaskforhelp wrote:
           | Ohh I forgot that anthropic uses AWS Bedrock (I think?,
           | right?) That checks out. This is really cool project!
        
             | akdev1l wrote:
             | From my understanding Anthropic is independent but they
             | offer Claude as an offering through Bedrock
        
       | retinaros wrote:
       | What is the difference between kiro and having a rule file in
       | claude code / cursor / cline saying << always start designing
       | before coding. Create a .md file for specs, ask the user for it
       | if it is not there? >>. You can just prompt the specs or whatever
       | feature is in this IDE.
       | 
       | Claude 4 can do it all already.
        
       | aaronvg wrote:
       | super interesting to see how this is marketed:
       | 
       | - Created by an AWS team but aws logo is barely visible at the
       | bottom.
       | 
       | - Actually cute logo and branding.
       | 
       | - Focuses on the lead devs front and center (which HN loves).
       | Makes it seem less like a corporation and more like 2 devs
       | working on their project / or an actual startup.
       | 
       | - The comment tone of "hey ive been working on this for a year"
       | also makes it seem as if there weren't 10 6-pagers written to
       | make it happen (maybe there weren't?).
       | 
       | - flashy landing page
       | 
       | Props to the team. Wish there were more projects like this to
       | branch out of AWS. E.g. Lightsail should've been launched like
       | this.
        
       | stillpointlab wrote:
       | I love all of this experimentation in how to effectively use AIs
       | to co-create output with human steering. This pattern, of the
       | human human focusing on the high-level and the AI focusing on the
       | low level feels like a big win.
       | 
       | In some sense, we are starting with a very high-level and
       | gradually refining the idea to a lower and lower levels of
       | detail. It is structured hierarchical thinking. Right now we are
       | at 3 levels: requirement -> spec -> code. Exposing each of these
       | layers as structured text documents (mostly Markdown right now it
       | seems) is powerful since each level can be independently
       | reviewed. You can review the spec before the code is written,
       | then review the code before it gets checked in.
       | 
       | My intuition is that this pattern will be highly effective for
       | coding. And if we prove that out at scale, we should start
       | asking: how does this pattern translate to other activities? How
       | will this affect law, medicine, insurance, etc. Software is the
       | tip of the iceberg and if this works then there are many possible
       | avenues to expand this approach, and many potential startups to
       | serve a growing market.
       | 
       | The key will be managing all of the documents, the levels of
       | abstraction and the review processes. This is a totally tractable
       | problem.
        
         | zmmmmm wrote:
         | > Exposing each of these layers as structured text documents
         | 
         | If we take it far enough, we could end up with a well
         | structured syntax with a defined vocabulary for specifying what
         | the computer should do that is rigorously followed in the
         | implemented code. You could think of it as some kind of a ...
         | language for .... programming the computer. Mind blowing.
        
           | stillpointlab wrote:
           | I get you are being sarcastic, but lets actually consider
           | your idea more broadly.
           | 
           | - Machine code
           | 
           | - Assembly code
           | 
           | - LLVM
           | 
           | - C code (high level)
           | 
           | - VM IR (byte code)
           | 
           | - VHLL (e.g. Python/Javascript/etc)
           | 
           | So, we already have hierarchical stacks of structured text.
           | The fact that we are extending this to higher tiers is in
           | some sense inevitable. Instead of snark, we could genuinely
           | explore this phenomenon.
           | 
           | LLMs are allowing us to extend this pattern to domains other
           | than specifying instructions to processors.
        
             | a5c11 wrote:
             | And we re-invent the wheel basically. You have to use very
             | specific prompts to make the computer do what you want, so
             | why not just, you know... program it? It's not that hard.
             | 
             | Natural language is trying to be a new programming
             | language, one of many, but it's the least precise one imho.
        
               | stillpointlab wrote:
               | > Natural language is trying to be a new programming
               | language, one of many, but it's the least precise one
               | imho.
               | 
               | I disagree that natural language is trying to be a
               | programming language. I disagree that being less precise
               | is a flaw.
               | 
               | Consider:
               | 
               | - https://www.ietf.org/rfc/rfc793.txt
               | 
               | - https://datatracker.ietf.org/doc/html/rfc2616
               | 
               | I think we can agree these are both documents written in
               | natural language. They underpin the very technology we
               | are using to have this discussion. It doesn't matter to
               | either of us what platform we are on, or what programming
               | language was used to implement them. That is not a flaw.
               | 
               | Biological evolution shows us how far you can get with
               | "good enough". Perfection and precision are highly
               | overrated.
               | 
               | Let's imagine a wild future, one where you copy-and-paste
               | the HTML spec (a natural language doc) into a coding
               | agent and it writes a complete implementation of an HTML
               | agent. Can you say with 100% certainty that this will not
               | happen within your own lifetime?
               | 
               | In such a world, I would prefer to be an expert in
               | writing specs rather than to be an expert in implementing
               | them in a particular programming language.
        
               | sirsinsalot wrote:
               | In this world where the LLM implementation has a bug in
               | it that impacts a human negatively (the app could
               | calculate a person's credit score for example)
               | 
               | Who is accountable?
        
               | stillpointlab wrote:
               | I couldn't even tell you who is liable _right now_ for
               | bugs that impact human 's negatively. Can you? If I was
               | an IC at an airplane manufacturer and a bug I wrote
               | caused an airplane crash - who is legally responsible? Is
               | it me? The QA team? The management team? Some 3rd party
               | auditor? Some insurance underwriter? I have a strong
               | suspicion it is very complicated as it is without
               | considering LLMs.
               | 
               | What I can tell you is that the last time I checked: laws
               | are written in natural language, they are argued
               | for/against and interpreted in natural language. I'm
               | pretty confident that there is applicable precedent and
               | the court system is well equipped to deal with autonomous
               | systems already.
        
               | sirsinsalot wrote:
               | I agree with this. There's so much snake oil at the
               | moment. Coding isn't the hard part of software
               | development and we already have unambiguous language for
               | describing computation. Human language is a bad choice
               | for it, and we already find that when writing specs for
               | other humans. Adding more humaness to the loop isn't a
               | good thing IMHO.
               | 
               | At best an LLM is a new UI model for data. The push to
               | get them writing code is bizarre.
        
       | nullbyte wrote:
       | Looks very nice, I like the hooks feature. That's a great idea
        
       | lacoolj wrote:
       | So I'm glad there are more agentic dev tools coming out, but can
       | we please stop making entirely new IDEs and start integrating as
       | plugins to well-established (and some already paid for) IDEs we
       | already use? Webstorm/other Jetbrains, VS Code, etc.
       | 
       | It is a huge hassle to match my existing settings, which I've
       | spent countless hours tweaking over the years, with a new editor
       | that can't import them. :(
        
         | imiric wrote:
         | The obvious solution is a meta-IDE that integrates all these
         | other IDEs and plugins.[1]
         | 
         | Or, you know, stop chasing the latest trends, and use whatever
         | you're most comfortable with.
         | 
         | [1]: https://xkcd.com/927/
        
         | williamzeng0 wrote:
         | Shameless plug but our co is building a AI plugin for JetBrains
         | that has next edit autocomplete + a strong coding agent (sweep
         | dev)
        
           | AstroBen wrote:
           | Isn't that competing directly with JetBrains themselves?
        
       | ManWith2Plans wrote:
       | I got early access to Kiro. Wrote about my experiences here if
       | you're interested: https://yehudacohen.substack.com/p/developing-
       | with-kiro-amaz...
       | 
       | It is my new daily driver.
        
       | sergiotapia wrote:
       | Would appreciate a video of someone adding a feature to an
       | existing project, just to get a feel for what the tool does. The
       | long blog post gets lost in the sauce, would love a short 5
       | minute video.
        
       | consumer451 wrote:
       | Important details from the FAQ, emphasis mine:
       | 
       | > For users who access Kiro with Pro or Pro+ tiers once they are
       | available, your content is not used to train any underlying
       | foundation models (FMs). AWS might collect and use client-side
       | telemetry and usage metrics for service improvement purposes. You
       | can opt out of this data collection by adjusting your settings in
       | the IDE. _For the Kiro Free tier and during preview, your
       | content, including code snippets, conversations, and file
       | contents open in the IDE, unless explicitly opted out, may be
       | used to enhance and improve the quality of FMs. Your content will
       | not be used if you use the opt-out mechanism described in the
       | documentation._ If you have an Amazon Q Developer Pro
       | subscription and access Kiro through your AWS account with the
       | Amazon Q Developer Pro subscription, then Kiro will not use your
       | content for service improvement. For more information, see
       | Service Improvement.
       | 
       | https://kiro.dev/faq/
        
         | srhngpr wrote:
         | To opt out of sharing your telemetry data in Kiro, use this
         | procedure:
         | 
         | 1. Open Settings in Kiro.
         | 
         | 2. Switch to the User sub-tab.
         | 
         | 3. Choose Application, and from the drop-down choose Telemetry
         | and Content.
         | 
         | 4. In the Telemetry and Content drop-down field, select
         | Disabled to disable all product telemetry and user data
         | collection.
         | 
         | source: https://kiro.dev/docs/reference/privacy-and-
         | security/#opt-ou...
        
           | m0llusk wrote:
           | Is there a way to confirm this works or do we just have to
           | trust that settings will be honored?
        
             | consumer451 wrote:
             | You could place some unique strings in your code, and test
             | it to see if they appear as completions in future
             | foundation models? Maybe?
             | 
             | I am nowhere near being a lawyer, but I believe the promise
             | would be more legally binding, and more likely to be
             | adhered to, if money was exchanged. Maybe?
             | 
             | The "Amazon Q Developer Pro" sub they mention appears to be
             | very inexpensive. https://aws.amazon.com/q/pricing/
        
             | Waterluvian wrote:
             | Just like using an AI model, you _can't_ actually know for
             | sure that it won't do anything malicious with what
             | interfaces you give it access to. You just have to trust
             | it.
        
               | dkga wrote:
               | Well, you can at least check if there is network traffic
               | to AWS or something similar.
        
               | yurishimo wrote:
               | But wouldn't that look the same as actually querying the
               | model? Or am I missing the joke?
        
               | Waterluvian wrote:
               | There's always ways to mitigate malicious behaviour once
               | it's already happening.
        
             | pmontra wrote:
             | As for everything else: trust, possibly enhanced by the
             | fear of consequences for the other party.
             | 
             | How do we know if random internet service sells our email /
             | password pair? They probably store the hashed password
             | because it's easier (libraries) than writing their own
             | code, but they get it as cleartext every time we type it
             | in.
        
               | Quekid5 wrote:
               | > How do we know if random internet service sells our
               | email / password pair? They probably store the hashed
               | password because it's easier (libraries) than writing
               | their own code, but they get it as cleartext every time
               | we type it in.
               | 
               | For that, we can just use a unique password per service.
               | That's not really a thing for code.
        
               | rusk wrote:
               | > How do we know if random internet service
               | 
               | Audits. Obviously not every service is going to be in a
               | jurisdiction that proactively audits data processors and
               | controllers. Another thing to consider before you hand
               | over your data.
        
         | lukev wrote:
         | This brings up a tangential question for me.
         | 
         | Clearly, companies view the context fed to these tools as
         | valuable. And it certainly has value in the abstract, as
         | information about how they're being used or could be improved.
         | 
         | But is it really useful as training data? Sure, some new
         | codebases might be fed in... but after that, the way context
         | works and the way people are "vibe coding", 95% of the novelty
         | being input is just the output of previous LLMs.
         | 
         | While the utility of synthetic data proves that context
         | collapse is not inevitable, it does seem to be a real
         | concern... and I can say definitively based on my own
         | experience that the _median_ quality of LLM-generated code is
         | much worse than the _median_ quality of human-generated code.
         | Especially since this would include all the code that was
         | rejected during the development process.
         | 
         | Without substantial post-processing to filter out the bad input
         | code, I question how valuable the context from coding agents is
         | for training data. Again, it's probably quite useful for other
         | things.
        
           | consumer451 wrote:
           | There is company, maybe even a YC company, which I saw
           | posting about wanting to pay people for private repos that
           | died on the vine, and were never released as products. I
           | believe they were asking for pre-2022 code to avoid LLM
           | taint. This was to be used as training data.
           | 
           | This is all a fuzzy memory, I could have multiple details
           | wrong.
        
           | janstice wrote:
           | I suspect the product telemetry would be more useful - things
           | like success of interaction vs requiring subsequent editing,
           | success from tool use, success from context & prompt tuning
           | parameters would be for valuable to the product than just
           | feeding more bits into the core model.
        
           | recursivecaveat wrote:
           | The human/computer interaction is probably more valuable than
           | any code they could slurp up. Its basically CCTV of people
           | using your product and live-correcting it, in a format you
           | can feed back into the thing to tell it to improve. Maybe one
           | day they will even learn to stop disabling tests to get them
           | to pass.
        
           | nicewood wrote:
           | I think it's less about the code output, but about the
           | process of humans iterating and adjusting the LLM-drafted
           | requirements and design. Claude Code et al. are good enough,
           | the bottleneck is IMO usually the context and prompt by now.
           | So further improving that by optimizing for and collecting
           | data about the human interaction seems like a good strategy
           | to me.
           | 
           | Essentially, the user labels (accept/edit) data (design
           | documents) for the agent (amazon)
        
         | metadat wrote:
         | This is the inevitable decline where we all eventually don't
         | care about the source code instructions anymore, just like the
         | transition from assembly to C. Sorry in advance, I'm a privacy
         | holdout too, but this isn't the interesting part of what's
         | happening. I tried Kiro and it is on par with Claude or
         | Crystal, nothing special at all.
         | 
         | Within the next couple of years there's going to be a 4-for-1
         | discount on software engineers. Welcome to The Matrix. You'd
         | best find Morpheus.
         | 
         | Check out the comments on
         | https://news.ycombinator.com/item?id=44567857 and tell me what
         | the alternative future is. Best wishes and good luck.
        
         | anonnon wrote:
         | > your content is not used to train any underlying foundation
         | models (FMs).
         | 
         | This implies your "content" may be used for anything else,
         | including training non-foundation LLMs. Frankly, even if their
         | disclaimer were broader, I'd still probably not trust them.
        
           | 0xEF wrote:
           | As you shouldn't! Only a rube trusts a rule for which there
           | is no real enforcement or punishment is a mere fine. If the
           | erosion of consumer privacy has not taught us that simply
           | stating "we won't use/sell your data" is the biggest lie of
           | the 21st century, then I don't know what will.
        
             | anonnon wrote:
             | The well-poisoning effect is especially strong in the AI
             | space based on how blatant the big players have been in
             | disregarding intellectual property law and how their
             | crawlers behave like DDOS bot farms.
        
       | ezekg wrote:
       | This post is downloading >100MB in gifs like it's not a thing...
        
       | _pdp_ wrote:
       | As a side note, Kiro is a diminutive of Kiril (Kiril) in Slavic-
       | speaking countries and in Greek. A quick web search also reveals
       | that it can mean "a curse".
        
         | prmph wrote:
         | How your comment contributes to the discussion I have no idea,
         | but thanks for this factoid nonetheless.
        
       | esafak wrote:
       | We need someone to compare the efficiency of these agent
       | wrappers. They may use the same models, but not as efficiently as
       | one another.
        
         | e2e4 wrote:
         | https://gosuevals.com/agents.html Is quite nice, there are also
         | YouTube videos that do a deeper dive
        
           | esafak wrote:
           | That table is uninformative and untrustworthy. Where is this
           | detailed breakdown they speak of? How can we replicate it?
           | Where is the cost? Who is behind it?
        
       | hexo wrote:
       | Thanks for accelerating global warming.
        
       | cleverwebble wrote:
       | I do like the control you have over organizing. The only thing I
       | was shocked was I couldn't revert a series of changes
       | (checkpointing) like you can can in Cursor. Sometimes the LLM
       | does it a different way I dont like, so I want to go back and
       | edit the prompt and try again.
        
       | qwertox wrote:
       | Is this an Amazon product? When I click on "Legal" at the bottom
       | of the page, I'm sent to AWS.
       | 
       | The docs state at https://kiro.dev/docs/reference/privacy-and-
       | security/#servic... that "Kiro is an AWS application that works
       | as a standalone agentic IDE."
       | 
       | But nowhere on the landing page or other pages it states that
       | this is an Amazon product.
       | 
       | What is going on?
       | 
       | Edit: I see that @nathanpeck is the "author" and he works for
       | Amazon, why are they trying to hide that fact?
        
         | QuinnyPig wrote:
         | My original title did mention that this was an AWS product, but
         | Hacker News made the editorial decision to reduce clarity.
        
         | PartiallyTyped wrote:
         | I don't think they are trying to hide that.
         | 
         | From the about page.
         | 
         | > Kiro is built and operated by a small, opinionated team
         | within AWS.
         | 
         | Disclaimer: I work at AWS, different org though.
        
         | seunosewa wrote:
         | Isn't AWS Amazon Web Services??
        
           | qwertox wrote:
           | Yes, why are you asking?
        
         | potamic wrote:
         | I didn't realize either until I saw this comment. The tone of
         | the blog post also felt like it was coming from an individual
         | rather than an organisation, which is not typical of Amazon. I
         | don't know if this was a recent acquisition, otherwise
         | diverting from your primary brand is strange. Unless they feel
         | an association with Amazon would only be negative.
        
         | KomoD wrote:
         | How are they hiding it?
         | 
         | Click about, says its made by a team within AWS.
         | 
         | Click on any of the legal links in footer, get sent to AWS
         | 
         | Look at the footer, has AWS logo
         | 
         | Look at the license, clearly says "Amazon.com, Inc. or its
         | affiliates"
         | 
         | On the download page "By downloading and using Kiro, you agree
         | to the AWS Customer Agreement"
        
       | prmph wrote:
       | People are lapping up vibe coding as a way a way to avoid deep
       | work, and spec-driven development is in opposition to that.
       | 
       | Looking at the brief for this, it likely involves painstaking
       | work to review and refine the specs produced. Not that there is
       | anything wrong with that; as I said before in a comment on
       | another story, coding assistants may reduce quite a bit of
       | drudgery, but to get the best out of them you still need to do
       | lots of work.
       | 
       | The more I use agentic coding tools, the more I come to the
       | realization that speccing is where you add value as an
       | experienced skilled engineer. And I think this bodes well for
       | software engineering, as a bifurcation emerges between the vibe
       | coders (who will probably merge with the mythical end-user
       | programmers) and serious engineers whose are skilled at using
       | LLMs via high quality specs to create software of higher quality
       | and maintainability.
       | 
       | So the vibe coders would probably not take to this tool that
       | much, but that's fine.
        
       | sandeepkd wrote:
       | Tried with one of my older projects to test it out. The problem
       | statement was to upgrade the Java spring boot version from 2.7 to
       | latest. I have done it in the past so exactly knew what had to be
       | done there. All the requirement docs, design specs, and tasks
       | look verbose and ok on high level. Interestingly I had some idea
       | where the language in those docs was coming from. 1. It created
       | about 40+ tasks (I have my own curated list of 5 tasks based on
       | past experience)
       | 
       | 2. At every task it tried to compile the code but failed for
       | dependency errors
       | 
       | 3. It still marked the task being complete and passed the onus of
       | failures on the downstream tasks
       | 
       | 4. Kept moving with the tasks where the original error were still
       | not fixed but the tasks were being marked as done
       | 
       | 5. After some point of time I got tired to a degree that I
       | stopped reading the exact commands being executed, the fatigue of
       | doing something that you are not involved in is for real 6. I
       | made a naive assumption that I can sandbox it by giving
       | permissions to the project folder only. It executed some CLI
       | commands for java that looked simple enough in the beginning.
       | 
       | 7. Turns out my environment variables got messed up and other
       | simple things related to git, gradle stopped working
       | 
       | Ended my experiment, reverted the code changes, fixed my
       | environment
       | 
       | Key takeaways:
       | 
       | 1. Its giving a sense of work being executed, the quality and
       | concreteness of work is hard to measure unless you have already
       | done that in past. Its creating classes, tests which are not
       | needed instead of focussing on the actual use case.
       | 
       | 2. Sandboxes are MUST, there is a real risk of corruption,
       | environment commands are not just simple file changes which could
       | be easily reverted.
        
         | hu3 wrote:
         | Interesting. How large is the project?
        
           | sandeepkd wrote:
           | It was relatively pretty small project, about 5ish
           | controllers and same number of service classes. The
           | experiment lasted for about 2.5 hours where I was active for
           | the first 45 minutes and then just pressing the buttons to
           | move next in passive mode.
        
       | softsales wrote:
       | It's not open source. Why bother?
       | 
       | OSS option will be there soon and will outsmart Kiro.
        
       | honorable_coder wrote:
       | Is model choice a core design consideration. Or will Kiro not let
       | developers chose the underlying model?
       | 
       | What if I want to set preferences for the underlying LLM for
       | different usage scenarios? For example, for a quick and snappy
       | understanding of a single file id want to use a fast model that
       | doesn't cost me an arm and a leg. Recent research on preference-
       | aligned LLM routing here: https://arxiv.org/abs/2506.16655
        
       | ghuntley wrote:
       | Source code analysis [and dump] of Kiro at
       | https://ghuntley.com/amazon-kiro-source-code/
       | 
       | - Uses ripgrep under the hood
       | 
       | - VSCode fork (thus suffers from the
       | https://ghuntley.com/fracture problem)
       | 
       | - There are 14 different ways defined to edit a file due to its
       | multi-modal design. Tuning this is going to be a constant source
       | of headaches for the team.
       | 
       | - Kiro utilises a https://ghuntley.com/specs based workflow.
        
         | chrisvalleybay wrote:
         | Not sure why you are being downvoted. I appreciate this!
        
       | zkxjzmswkwl wrote:
       | I don't see anything, anything at all, that would make a
       | significant percentage of Cursor users consider the switch.
       | 
       | They can try to market grab with low %, but will find themselves
       | in the boat as Cursor and eventually be forced to raise their
       | prices. Except their market grab will be significantly less
       | effective because they're _not_ a stand-out product. Cursor was.
        
       | conartist6 wrote:
       | Important: it's another fork of VSCode.
       | 
       | I thought AI was ushering in the age of innovation so why is the
       | only innovation anyone seems capable of copying something that
       | already exists...?
       | 
       | In all actuality, AI seems to be ushering out the age of
       | innovation since people now consider it foolish to spend their
       | time trying to innovate instead of clone
        
         | daxfohl wrote:
         | It does show that they're not limited to just greenfield
         | projects, which is a common perspective. That said, IDK if a
         | fork that is never planned to be merged back in really
         | constitutes a non-greenfield project. It's more like a
         | greenfield with a head start.
        
         | hu3 wrote:
         | I believe most projects use VSCode because it is hard to build
         | a cross platform code editor with plugin system.
         | 
         | And if you're going to copy, might as well be the most popular
         | editor to reduce user friction.
        
       | bhaktatejas922 wrote:
       | Notably missing fast apply like Morph
        
       | manbash wrote:
       | > 2. Technical design based on requirements > Kiro then generates
       | a design document by analyzing your codebase and approved spec
       | requirements. It creates data flow diagrams, TypeScript
       | interfaces, database schemas, and API endpoints--like the Review
       | interfaces for our review system. This eliminates the lengthy
       | back-and-forth on requirements clarity that typically slows
       | development.
       | 
       | This is nice for documentation but really having a design
       | document after-the-fact doesn't really help much. Designing is a
       | decision-making process _before_ the code is written.
        
         | p1necone wrote:
         | The Eisenhower quote comes to mind: "Plans are worthless, but
         | planning is everything."
        
           | Twirrim wrote:
           | If you don't start with approximately the right destination,
           | you're definitely never going to end up there, even if you
           | have to take some detours and compromise on some choices.
           | 
           | It gets really frustrating reviewing people's designs at
           | times, when it's crystal clear they're a) working backwards
           | and b) haven't really considered the customer experience at
           | all.
           | 
           | One of my favourite tell tale signs of a) is when the chosen
           | option 100% fits the specifications, doubly so if there's no
           | cons associated with the pros. Sometimes it's genuine, but
           | very rarely.
        
         | cgio wrote:
         | I read it as after requirements and before code. This is how I
         | would expect it to work too. It reads the existing codebase,
         | which also makes sense for non greenfield projects as in the
         | example.
        
         | the_arun wrote:
         | I slightly disagree. Plans are really useful for enhancements.
         | If we stick to original plans & patterns as we extend & add new
         | features, we can slow down the decay process.
        
         | danbeaulieu wrote:
         | Kiro takes the requirements and the existing code to create a
         | spec.
         | 
         | Otherwise the spec may cover requirements that are already met
         | in the existing code and needs to understand integration points
         | it needs to include in the spec.
         | 
         | Having used Kiro myself I think it does what you expect.
        
       | y2025 wrote:
       | I'm interested!
        
       | orliesaurus wrote:
       | Is it pronounced kee roh or kai roh
        
       | johndiv wrote:
       | Really impressed with what Amazon is doing with Kiro. The
       | emphasis on "spec-driven development" to get beyond "vibe coding"
       | and into production-ready software is a crucial step.
        
       | smcleod wrote:
       | My 2c-TLDR; after doing some battle testing over the few weeks
       | (so keep in mind some of this was on pre-release versions):
       | 
       | The good: It's great to see they've baked in the concept of setup
       | -> plan -> act into the tool with the use of specs If you're
       | someone who currently only has Copilot / Q dev, this is a good
       | step in the right direction - if you don't mind changing your
       | IDE. I love that it has a command / task queuing system. Hooks =
       | good.
       | 
       | Goes either way: Even though it uses Q under the bonnet, it does
       | seem somewhat better than Q although I think most of that is down
       | to the use of plan -> act workflows
       | 
       | The not good: There's no reason at all for it to be a VSCode fork
       | and running multiple IDEs for every vendor that wants me to use
       | their products is a PITA. It seems to massively over-complicate
       | solutions, for things that could be quite simple even if the
       | tasks are well defined it likes to create many files and go down
       | very extensive and complex implementation patterns. This has to
       | be something to do with the app itself as Sonnet 4 does not do
       | this with Cline/Roo Code so hopefully it can be fixed (but maybe
       | it suits the kind of folks that write big java apps!). It doesn't
       | seem to have any integrated web browser capabilities to allow the
       | model to run up and explore the app while inspecting the js
       | console browser side like Cline / Roo have. My installation has
       | mysteriously become 'corrupted' and needed reinstalling several
       | times. There's no global rules, you have to keep a note of them
       | somewhere and copy paste them into each project. GH Issue #25
       | 
       | The bad: It's slower than Cline / Roo Code, it just takes a lot
       | longer to get things done. It's very easy to hit the rate limits
       | and be blocked for an undefined amount of time before you can
       | continue working. There's lots of MCP bugs mainly relating to it
       | still not supporting the standard streamableHTTP or SSE modes and
       | breaks all MCPs without any warning or logs if you try to add
       | one. GH Issue #23 The version of VSCode it's built from is quite
       | out of date already, which rings alarm bells for how well such a
       | large, complex application will be maintained and rolled out at
       | speed over time.
        
       | somesun wrote:
       | anyone can make a comparation with cursor
       | 
       | too many ides , hard to choose
        
       | ryancnelson wrote:
       | I wonder if it's entirely coincidental that "KIRO" is a Seattle-
       | area (amazon land) television station.
        
       | laura_rich wrote:
       | Awesome!
        
       | zorrolovsky wrote:
       | Very impressed. As a programming impostor (never formally
       | trained, and not working as programmer) I find the program 1)
       | helped me to understand the basics of a full blown IDE dev cycle
       | end to end 2) helped me to refine an app on the making. Perhaps
       | the one thing that surprised me vs standard Claude is that it
       | didn't ask me about the tech stack to build my app. It went
       | nuclear with a complex react-based stack when my app's needs are
       | less demanding (a simple html+css+js could do it)
        
       | maoberlehner wrote:
       | I have to say, I'm a little bit proud of myself that their
       | approach comes close to what I consider a good method for
       | building software with LLMs:
       | https://markus.oberlehner.net/blog/ai-enhanced-development-b...
        
         | duckerduck wrote:
         | It seems that many in the field are converging to similar
         | ideas. With AI the emphasis seems to be more on defining
         | clearly _what_ to build rather than _how_. I made a similar
         | experiment [1] recently where I setup  "rules" between code and
         | spec and have the LLM check that they are the same, I think
         | similar to how Kiro uses hooks.
         | 
         | [1]: https://news.ycombinator.com/item?id=44432215
        
       | lastdong wrote:
       | This reminds me of the pocketFlow library, which takes a
       | specification document and uses it to create subtasks and
       | generate code, but can be used with local models.
        
       | larodi wrote:
       | Kiretsa, bate.
        
       | qpiox wrote:
       | They did not even spend time to put up a credible demo. The web
       | app they demo has missing images, images that do not correspond
       | to the text. Why would I or anyone else be convinced to spend
       | much more time learning a new IDE and switching to it, when they
       | did not spend enough time for a proper demo.
        
       | baalimago wrote:
       | 1000 interactions ($20/month) will run out in a 1-2 hours. Do the
       | math for 3000 interactions.
       | 
       | Kiro has the same problem as many LLM coding tools has: it's not
       | economically sustainable for the company producing the tool
       | (bubble will burst at some point), or it's not worth it for the
       | developer.
        
       | Fokamul wrote:
       | Mark my word guys, 2026 will be year of cybersecurity.
       | 
       | Vibe coders let's gooo.
        
       | brap wrote:
       | I think the interesting part here is not so much the IDE/coding
       | aspect, but LLM-assisted:
       | 
       | * requirements doc
       | 
       | * design doc
       | 
       | * plan doc
       | 
       | These alone make an interesting product. Give me a thing that
       | asks me the right, thought provoking questions (ideally let me
       | answer by just choosing from a list of relevant options) and
       | produces these docs in a structured and highly detailed way, and
       | I'm set.
       | 
       | I think the code is just a distraction. There are plenty of tools
       | for that.
        
         | daxfohl wrote:
         | True for greenfield projects, but once a project moves beyond
         | greenfield, the assistant will need to understand the existing
         | codebase in order to plan anything correctly. Once it has
         | functionality to understand a codebase, and understand the
         | requirements, plan, and architecture direction, then it's going
         | to have the most context to make edits, so may as well make it
         | an editor too.
        
       | bravesoul2 wrote:
       | How does it compare to Claude Code? Can't that do this sort of
       | thinking ahead and writing specifically? It may need some
       | prompting to do the specifically writing specifically though.
       | 
       | I feel like this might be nicer as an MCP and I bring my own AI
       | assistant to it.
        
       | GardenLetter27 wrote:
       | What is really the benefit of this if you are stuck paying Claude
       | API rates anyway?
       | 
       | We really need a new (and cheaper!) SOTA for agentic models.
        
       | k_kelly wrote:
       | Sep 1: generate requirements, generate design, generate task list
       | 
       | Step 2: run the tasks in claude code in parallel...
        
       | alberth wrote:
       | The ghost icon confused me at first, given ghostty use of a
       | similar icon.
       | 
       | https://ghostty.org/
        
       | riceflippa wrote:
       | they literally copied logo (even the color!) from phantom
        
       | reactordev wrote:
       | This looks really cool except for having to learn a new syntax
       | (is gherkin that bad?) however, something has been bothering me
       | with all of these Agent AI based workflows.
       | 
       | At what point do you actually do engineering? This was a great
       | demo for a project manager. Lead your "team" through feature
       | development. But without proper architecture, development really
       | does become spaghetti.
       | 
       | There's vibe coding - and then there's this, where I feel like
       | I'm a PM, not an engineer.
        
         | Insanity wrote:
         | Yeah, I hear you. Vibe coding is good for a POC style thing as
         | long as you can (somewhat) ignore architecture.
         | 
         | For any real-world application that is even slightly more
         | complex than these demos it will start to fail.
         | 
         | At least that has been my experience
        
         | daxfohl wrote:
         | It depends. A lot of projects / features really don't require a
         | ton of engineering thought. Add a new table that has some
         | foreign keys with existing tables, add a new page that lets you
         | modify that table, add a new set of REST CRUD handlers that do
         | some validation and store the data, add a new message queue
         | that does whatever needs to happen when the data gets changed.
         | 
         | If AI can handle things like that, then let AI do it: it's not
         | really engineering work anyway; it's copy-and-paste from a
         | previous design, just change the handler logic and the names of
         | things. If 90% of incoming features are like that, then that
         | gives you a lot more time to work on the 10% that are more
         | complex.
         | 
         | Eventually, you'll end up with spaghetti code no matter how
         | well you plan out the architecture, whether human or AI is
         | doing designs. But it'll move that direction even faster with
         | AI, and eventually AI won't be able to understand it well
         | enough to reliably design things anymore. That's where the real
         | engineering will come in. As the system evolves, how do we re-
         | architect things so that AI (and humans) can understand the
         | patterns again and make future changes more reliably?
         | 
         | Right now, it seems like services go through major
         | refactors/rewrites like that every five years or so. And those
         | rewrites tend to be slow and often unsuccessful: even though
         | the existing system is complex, engineers are used to it and
         | it's easier to add one more bandaid than to wait for the full
         | rewrite. Then such rewrites can get stuck in navel-gazing as
         | there's no "perfect" way to do them, and it's lower effort just
         | to go back to the system you already know.
         | 
         | As AI creates more churn though, the architecture will need to
         | be rethought much more frequently. Additionally there will be
         | more urgency to deliver the cleanup because AI will be
         | completely blocked by the existing spaghetti, which brings all
         | product dev to a halt, and you don't have time for navel-gazing
         | because there's no fallback option.
         | 
         | So I think the engineering work post-AI is really going to be
         | this kind of infrastructural planning and rearchitecting, such
         | that AI can deliver features on top of it without friction. And
         | in a way, as an engineer, that's what I want to be doing
         | anyway. We've always had this ideal of continuous refactoring
         | and continuous improvement, that always gets pushed to the
         | backburner when compared to feature development. "Sure this
         | refactor will help future velocity, but we need to make our
         | quarterly goals!" But now, AI will compress those timelines so
         | that maintaining clean architectures has a direct effect on the
         | deliverables of the current quarter.
         | 
         | I personally think this is great. If, in the future, PMs can
         | launch whole features without engineers writing a line of code,
         | that's awesome. It's our job to maintain a system where such an
         | ideal is possible. Which sounds like the job I wanted when I
         | originally signed up to be an engineer.
        
           | reactordev wrote:
           | >And in a way, as an engineer, that's what I want to be doing
           | anyway...
           | 
           | Yuk. That's pure project management.
           | 
           | > If, in the future, PMs can launch whole features without
           | engineers writing a line of code, that's awesome.
           | 
           | No it's not! Because then, there is no incentive to engineer
           | anything anymore. Just let the AI do it, Yey! Need new
           | features? Let the AI do it! Need to fix your infrastructure,
           | AI has your back! Has your product gotten so unwieldy that
           | you have context rot and AI can't do it anymore? Pivot, throw
           | it away, rebuild with AI, who needs engineers.
        
             | daxfohl wrote:
             | That's the thing though. I think we're pretty close to AI
             | being able to add fairly vanilla features that fit into the
             | existing architecture fairly autonomously. But I think
             | we're a long way away from AI being able to do major
             | refactors by itself, or even determine what needs
             | refactoring and when. Maybe someday it will, and it can
             | already be useful in implementing pieces of a refactor, but
             | it's nowhere near close on being able to design a major
             | platform shift at the moment. That's entirely a human
             | domain.
             | 
             | So while we're in the middle of those two pivot points, I
             | think most of our work will be on the architecture side.
             | Continuously clean up the platform so the LLM agents can
             | keep humming along on it.
             | 
             | Eventually we'll perhaps get to the point where AI can
             | automate 100% of this as well, and I have no clue what will
             | become of engineers then. But I don't see that happening in
             | the next ten years, and even when it does happen, I'm sure
             | the changes will create whole new industries, workflows,
             | and sets of problems for human engineers to solve. (SciFi
             | me expects a whole new field of extracting the most value
             | out of AI without letting it run amock. As fast as it goes,
             | and as intelligent as it will be, we won't be able to just
             | let it take over. We'll need to design guardrails for it so
             | that it does the things you want, and doesn't make
             | decisions that you don't want. This, by definition, has to
             | be a human driven process. So I think there'll be work for
             | human engineers to do for a long long time.)
        
       | elashri wrote:
       | It is strange that Amazon Q extension is incompatible with kiro
       | right now.
        
       | UrineSqueegee wrote:
       | do i have to run each task manually in the tasks.md? can i not
       | leave it unsupervised?
       | 
       | i also need to individually approve each command for some reason
       | and then if it fails due to a service high load i need to
       | manually restart all over again the same task.
        
         | harryf wrote:
         | > fails due to a service high load
         | 
         | It seems to be suffering the HN effect right now. Earlier it
         | was working nicely and pretty much doing everything in the
         | background
        
       | adonese wrote:
       | Sonnet 4 seems like the sweet spot for every ai provider now. I
       | wonder why oai couldn't match it
        
       | willsmith72 wrote:
       | first impressions:
       | 
       | 1. autopilot should be off by default. this is the norm for
       | claude code and cline (plan mode)
       | 
       | 2. my sidebar is on the right. that was imported correctly from
       | vs code, but the kiro window is still on the left. why can't it
       | be on the same side as my sidebar like a usual extension (e.g.
       | cline)?
       | 
       | 3. the textbox is super busy. for some reason the "Hold Shift to
       | drop image" is stuck there
        
       | stuaxo wrote:
       | Vscode again.
       | 
       | If MS didn't have their weird semi closed ecosystem for Vscode
       | this would be in Vscode proper.
        
       | lucasfdacunha wrote:
       | It seems that it doesn't work with WSL 2 yet. Any plans to
       | support it?
        
       | akdev1l wrote:
       | Tried to use this to create a minimal bootloader and kernel that
       | prints hello world in x86
       | 
       | There was never a point in which it successfully did anything.
       | 
       | 1. Tried to use macOS's toolchain (m2 laptop so this is not going
       | to work to build x86 binary)
       | 
       | 2. It tried to fix that and failed multiple times.
       | 
       | 3. Eventually I gave up on it trying to fix itself and told it to
       | just use a container with Fedora Linux on it to work around the
       | issue.
       | 
       | 4. It created Dockefile for Fedora 39 (current is 42)
       | 
       | 3. It still fails to recognize that we are on aarch64 and we need
       | x86 so the container it built was not correct anyway lol
       | 
       | I imagine "minimal bootloader + printing hello" is quite
       | represented in the training set as there's thousands of projects
       | like this on GitHub.
       | 
       | If it cannot deal with basic things like this, I legitimately
       | don't get all the comments here praising it
        
         | brandnewideas wrote:
         | You're using a slop tool and expect it to produce anything but
         | slop?
        
       | helsinki wrote:
       | Trash
        
       | andy_ppp wrote:
       | I know Cursor seems to work best using Anthropic's models, is
       | this similar or does it use a model from Amazon?
        
       | brandnewideas wrote:
       | Slop.
        
       | bcheung wrote:
       | Is there a way to use your Claude Max plan? I checked my token
       | usage (ccusage) if I wasn't on a plan, and last month it would
       | have been over $2000. This constraint prevents me from
       | realistically considering alternatives to Claude Code.
        
       ___________________________________________________________________
       (page generated 2025-07-15 23:01 UTC)