[HN Gopher] Just talk to it - A way of agentic engineering
       ___________________________________________________________________
        
       Just talk to it - A way of agentic engineering
        
       Author : freediver
       Score  : 162 points
       Date   : 2025-10-15 06:21 UTC (16 hours ago)
        
 (HTM) web link (steipete.me)
 (TXT) w3m dump (steipete.me)
        
       | squirrel wrote:
       | I have to imagine that like pair programming, this multi-AI
       | approach would be significantly more tiring than one-window, one-
       | programmer coding. Do you have to force yourself to take breaks
       | to keep up your stamina?
        
         | throw-10-13 wrote:
         | The human context window is the limiting factor.
         | 
         | That and testing/reviewing the insane amounts of ai slop this
         | method generates.
        
           | csar wrote:
           | If you're getting AI slop you're doing it wrong. You should
           | be getting high quality code. Of course that's easier said
           | than done, but AI slop is a sign that things have gone off
           | the rails.
        
         | XenophileJKO wrote:
         | Well I don't use as many instances as they do, but using codex
         | for example will take some time researching the code. It mostly
         | just becomes a practice so that I don't have to wait for the
         | model, I just context switch to a different one. It probably
         | helps that I am ADHD, I don't pay much of a cost to ping pong
         | around.
         | 
         | So I might tell one to look back in the git history to when
         | something was removed and add it back into a class. So it will
         | figure out what commit added it, what removed it, and then add
         | the code back in.
         | 
         | While that terminal is doing that, on another I can kick off
         | another agent to make some fixes for something else that I need
         | to knock out in another project.
         | 
         | I just ping pong back to the first window to look at the code
         | and tell it to add a new unit test for the new possible state
         | inside the class it modified and I'm done.
         | 
         | I may also periodically while working have a question about a
         | best practice or something that I'll kick off in browser and
         | leave it running to read later.
         | 
         | This is not draining, and I keep a flow because I'm not sitting
         | and waiting on something, they are waiting on me to context
         | switch back.
        
       | philipp-gayret wrote:
       | > But Claude Code now has Plugins
       | 
       | > Do you hear that noise in the distance? It's me sigh-ing. (...)
       | Yes, maintaining good documents for specific tasks is a good
       | idea. I keep a big list of useful docs in a docs folder as
       | markdown.
       | 
       | I'm not that familiar with Claude Code Plugins, but it looks like
       | it allows integrations with Hooks, which is a lot more powerful
       | than just giving more context. Context is one thing, but Hooks
       | let you codify guardrails. For example where I work we have a
       | setup for Claude Code that guides it through common processes,
       | like how to work with Terraform, Git or manage dependencies and
       | the whitelisting or recommendation towards dependencies. You
       | can't guarantee this just by slapping on more context. With Hooks
       | you can both auto-approve or auto-deny _and_ give back guidance
       | when doing so, for me this is a killer feature of Claude Code
       | that lets it act more intelligently without having to rely on it
       | following context or polluting the context window.
       | 
       | Cursor recently added a feature much like Claude Code's hooks, I
       | hope to see it in Codex too.
        
       | hansmayer wrote:
       | So, just trying to understand this - he admits to code being slop
       | and in the same sentences states that agents (which created the
       | slop in the first place) also refactor it? Where is the logic in
       | that?
        
         | grim_io wrote:
         | He, who does not produce slop in the first iteration, cast the
         | first stone.
        
         | fhd2 wrote:
         | I feel in this context, refactoring has lost its meaning a bit.
         | Sure, it's often used analogous to changes that don't affect
         | semantics. But originally, the idea was that you make a quick
         | change to solve the problem / test the idea, and then spend
         | some time on properly integrating the changes in the existing
         | system.
         | 
         | LLMs struggle with simplicity in my experience, so they
         | struggle with the first step. They also lack the sort of
         | intelligence required to understand (let alone evolve) the
         | system's design, so they will struggle with the second step as
         | well.
         | 
         | So maybe what's meant here is not refactoring in the original
         | meaning, but rather "cleanup". You can do it in the original
         | way with LLMs, but that means you'll have to be incredibly
         | micro manage-y, in my experience. Any sort of vibe coding
         | doesn't lead to anything I'd call refactoring.
        
           | ImaCake wrote:
           | > LLMs struggle with simplicity in my experience
           | 
           | I think a lot of this is because people (and thus LLMs) use
           | verbosity as a signal for effort. It's a very bad signal,
           | especially for software, but its a very popular signal. Most
           | writing is much longer than it needs to be, everything from
           | SEO website recipes, consulting reports, and non-fiction
           | books. Both the author and the readers are often fooled into
           | thinking lots of words are good.
           | 
           | It's probably hard to train that out of an LLM, especially if
           | they see how that verbosity impressess the people making the
           | purchasing decisions.
        
             | Terr_ wrote:
             | > I think a lot of this is because people (and thus LLMs)
             | use verbosity as a signal for effort.
             | 
             | It's also one of the main use-cases for non-programmer use
             | of the models, so there are business-forces against toning
             | it down. Ex: "Make a funny birthday letter for my sister
             | Suzie who's turning 50."
        
         | sebstefan wrote:
         | "So, just trying to understand this - he admits to code being
         | buggy and in the same sentences states that he (the engineer
         | who created the bugs in the first place) also debugs it? Where
         | is the logic in that?"
        
           | hansmayer wrote:
           | Are you seriously comparing outputs of human intelligence to
           | a text generator ?
        
             | sebstefan wrote:
             | No I'm highlighting that the logic itself is stupid
             | 
             | If the point is that you can't solve with AI what you
             | messed up with AI, but with human intelligence spending a
             | bit more time on the problem does indeed tend to help, you
             | need to explain why his technique with the AI won't work
             | either.
             | 
             | Plus he's adding human input to it every time, so I see no
             | reason to default to "it wouldn't work".
        
               | hansmayer wrote:
               | Well you said it yourself, you are literally comparing
               | human intelligence with the so-called AI, or better said,
               | advanced text generator. The differentiator being, the
               | text generators have 0 intelligence, otherwise there
               | would not be a flood of AI gurus explaining the latest
               | trick to making them finally work.
        
         | cwyers wrote:
         | LLMs are good at pursuing objectives, but they aren't
         | necessarily good at juggling competing objectives at once. So
         | you can picture doing the following, for instance:
         | 
         | - "Here is a spec for an API endpoint. Implement this spec."
         | 
         | - "Using these tools, refactor the codebase. Make sure that you
         | are passing all tests from (dead code checker, cyclomatic
         | complexity checker, etc.)"
         | 
         | The clankers are very good at iteratively moving towards a
         | defined objective (it's how they were post-trained), so you can
         | get them to do basically anything you can define an objective
         | for, as long as you can chunk it up in a way that it fits in
         | their usable context window.
        
       | barrkel wrote:
       | It all sounds somewhat impressive (300k lines written and
       | maintained by AI) but it's hard to judge how well the experience
       | transfers without seeing the code and understanding the feature
       | set.
       | 
       | For example, I have some code which is a series of integrations
       | with APIs and some data entry and web UI controls. AI does a
       | great job, it's all pretty shallow. The more known the APIs, the
       | better able AI is to fly through that stuff.
       | 
       | I have other code which is well factored and a single class does
       | a single thing and AI can make changes just fine.
       | 
       | I have another chunk of code, a query language, with a tokenizer,
       | parser, syntax tree, some optimizations, and it eventually
       | constructs SQL. Making changes requires a lot of thought from
       | multiple angles and I could not safely give a vague prompt and
       | expect good results. Common patterns need to fall into optimized
       | paths, and new constructs need consideration about how they're
       | going to perform, and how their syntax is going to interact with
       | other syntax. You need awareness not just of the language but
       | also the schema and how the database optimizes based on the data
       | distribution. AI can tinker around the edges but I can't trust it
       | to make any interesting changes.
        
         | timr wrote:
         | On the contrary, this doesn't sound impressive at all. It
         | sounds like a cowboy coder working on relatively small
         | projects.
         | 
         | 300k LOC is not particularly large, and this person's writing
         | and thinking (and stated workflow) is so scattered that I'm
         | basically 100% certain that it's a mess. I'm using all of the
         | same models, the same tools, etc., and (importantly) _reading
         | all of the code_ , and I have 0% faith in any of these models
         | to operate autonomously. Also, my opinion on the quality of
         | GPT-5 vs Claude vs other models is wildly different.
         | 
         | There's a huge disconnect between my own experience and what
         | this person claims to be doing, and I strongly suspect that the
         | difference is that I'm paying attention and routinely disgusted
         | by what I see.
        
           | sarchertech wrote:
           | 300k especially isn't impressive if it should have been 10k.
        
             | timr wrote:
             | Yes, well put. And that's a common failure mode.
        
             | bdangubic wrote:
             | I would guess that roughly 0.000087% devs on the planet do
             | it in 10k (if it is possible) and 37.76% would do it in
             | 876k so 300k is probably right in some middle :)
        
           | CuriouslyC wrote:
           | To be fair, codebases are bimodal, and 300k is large for the
           | smaller part of the distribution. Large enterprise codebases
           | tend to be monorepos, have a ton of generated code and a lot
           | of duplicated functionality for different environments, so
           | the 10-100 million line claims need to be taken with a grain
           | of salt, a lot of the sub projects in them are well below
           | 300k even if you pull in defs.
        
           | myko wrote:
           | I'm fairly skeptical of the LLM craze but I deeply respect
           | Peter Steinberger's work over the years, he truly is a gifted
           | software developer in his own right. I'm sure his personal
           | expertise helps him guide these tools better than many could.
        
           | steipete wrote:
           | (OP) 1/3rd of the code is tests.
           | 
           | There's an Expo app, two Tauri apps, a cli, a chrome
           | extension. The admin part to help debug and test features is
           | EXTREMELY detailed and around 40k LOC alone.
           | 
           | To give some perspective to that number.
        
         | ljm wrote:
         | AI agents to me seem maximalist by default, and if it takes 250
         | lines to meet a requirement they would choose that over the
         | much simpler one-line change.
         | 
         | In an existing codebase this is easily solved by making your
         | prompt more specific, possibly so specific you are just
         | describing the actual changes to make. Even then I find myself
         | asking for refinements that simplify the approach, with
         | suggestions for what I know would work better. The only reason
         | I'm not writing the change myself is because the AI agent is
         | running a TDD-style red/green/refactor loop and can say stuff
         | like "this is an integration test, don't use mocks and prefer
         | to use relevant rspec matchers in favour of asserting on
         | internal object state" and it will fix every test in the diff.
         | 
         | In a brand new codebase I don't have a baseline any more and
         | it's just an AI adding more and more into a ball of mud. I'm
         | doing this with NixOS and the only thing keeping it sane is
         | that each generated file is quite small and simple (owing to
         | the language being declarative). Yet still, I have zero idea if
         | I can even deploy it yet as a result.
        
           | dingnuts wrote:
           | I stopped using AI assistance when I realized every time the
           | agent made a change, I had to go behind and simplify it by
           | about 80%. It's easier, faster, more fun, and produces a
           | better end product if I just go ahead and do it myself.
           | 
           | If I am feeling lazy I can have one of the chats give me
           | their shit solution to the micro problem at hand and extract
           | the line I need and integrate it properly. This is usually a
           | little faster than reading the manual, but it's wrong often
           | enough that I usually read the manual for everything the bot
           | does, to make sure. And so next time I can skip asking it.
           | 
           | Someone wake me up and tell me to try these tools again when
           | the flow isn't prompting and deleting and repeat.
           | 
           | inb4 someone tells me there's a learning curve for this human
           | language product that is supposed to make it so I'm obsolete
           | and my CEO can do my job because it makes coding so easy that
           | even an experienced coder has to climb a steep learning curve
           | but there's going to be a white collar blood bath also
           | 
           | fucking pick a narrative, AI shills
        
       | srameshc wrote:
       | Everytime I read something like this, I question myself, what I
       | am doing wrong ? And I tried all kinds of AI tools. But I am not
       | even close to claiming that AI writes 50% of my code. My work
       | which sometimes include feature enhancements and maintenance is
       | where I get even less. I have to be extremely careful and make
       | sure nothing unwanted or addition that I am unaware of has been
       | added. Maybe it's me and I am not good yet to get to 100% AI code
       | generation.
        
         | fhennig wrote:
         | I'm in the same boat, I still find the model to make mistakes
         | or solve things in a less than ideal way - maybe the future is
         | to just not care - but for now I want to maintain the level of
         | quality that the codebase currently has.
         | 
         | I think it's good to keep up with what early adopters are
         | doing, but I'm not too fussed about missing something. The
         | plugins is a good example: A few weeks ago there was a post on
         | HN where someone said they are using 18 or 25 or whatever
         | plugins and it's the future, now this person says they are
         | using none. I'm still waiting for the dust to settle, I'm not
         | in a rush.
        
           | CuriouslyC wrote:
           | The person using 25 plugins is giving bad advice. The agent
           | isn't going to need all those tools at once, and each tool
           | burns context and causes tool confusion. Enable MCPs for the
           | specific task you're going to have your agent do.
           | 
           | The trick is to create deterministic hurdles the LLM has to
           | jump over. Tests, linting, benchmarks, etc. You can even do
           | this with diff size to enforce simpler code, tell an agent to
           | develop a feature and keep the character count of the diff
           | below some threshold, and it'll iterate on pruning the
           | solution.
        
         | troupo wrote:
         | You're not doing anything wrong. You have to read past
         | hyperbole.
         | 
         | Here's how the article starts: "Agentic engineering has become
         | so good that it now writes pretty much 100% of my code. And yet
         | I see so many folks trying to solve issues and generating these
         | elaborated charades instead of getting sh*t done."
         | 
         | Here's how it continues:
         | 
         | - I run between 3-8 in parallel
         | 
         | - My agents do git atomic commits, I iterated a lot on the
         | agents file:
         | https://gist.github.com/steipete/d3b9db3fa8eb1d1a692b7656217...
         | 
         | - I currently have 4 OpenAI subs and 1 Anthropic sub, so my
         | overall costs are around 1k/month for basically unlimited
         | tokens.
         | 
         | - My current approach is usually that I start a discussion with
         | codex, I paste in some websites, some ideas, ask it to read
         | code, and we flesh out a new feature together.
         | 
         | - If you do a bigger refactor, codex often stops with a mid-
         | work reply. Queue up continue messages if you wanna go away and
         | just see it done
         | 
         | - When things get hard, prompting and adding some trigger words
         | like "take your time" "comprehensive" "read all code that could
         | be related" "create possible hypothesis" makes codex solve even
         | the trickiest problems.
         | 
         | - My Agent file is currently ~800 lines long and feels like a
         | collection of organizational scar tissue. I didn't write it,
         | codex did.
         | 
         | It's the same magical incantations and elaborated charades as
         | everyone does. The "the no-bs Way of Agentic Engineering" is
         | full of bs and has nothing concrete except a single link to a
         | bunch of incantations for agents. No idea what his actual
         | "website + tauri app + mobile app" is that he build 100% with
         | AI, but depending on actual functionality, after burning $1000
         | a month on tokens you may actually have a fully functioning app
         | in React + Typescript with little human supervision.
        
           | 1718627440 wrote:
           | > $1000 a month
           | 
           | Yeah at this point you could hire a software developer.
        
             | TheMrZZ wrote:
             | I don't know how much SWE get paid in your area, but I sure
             | hope it's not 1000$/month.
             | 
             | Though I'm aligned that I don't (yet) believe in this "AI
             | writes all my code for me" statements.
        
               | 1718627440 wrote:
               | It includes that with AI you still need someone to work.
               | First to query the AI and then to fix up something and to
               | bring it in a form you can release and use.
        
             | stocksinsmocks wrote:
             | $5.75/hr is well below outsourced rates. It's $1.40/hr if
             | the agent runs without stopping. If I hired a human
             | consultant for a project of any size, I could easily spend
             | $10,000 or more on just scoping and contract approval.
             | Humans don't win on cost.
        
               | 1718627440 wrote:
               | Right now they still need someone typing prompts and
               | verifying them. When they do what you intend it means
               | that is no longer more work to handhold them than doing
               | it yourself, but it is still work.
        
           | steipete wrote:
           | (OP) You know if I link to a half-finished project, people
           | would take it apart as many don't understand the nuance
           | between crap and simply not done yet. But if you follow me on
           | twitter it'll take you a few minutes to figure out. I'm two
           | months in, even with AI, shipping good stuff takes time.
        
         | tptacek wrote:
         | Same! Half would be a lot for me. I'm also not close to the
         | point where I'm comfortable merging LLM-authored PRs without
         | line-by-line reviews.
        
           | darkwater wrote:
           | Didn't you write a blog post a few months ago saying that you
           | had agents preparing PRs for you while AFK doing things IRL?
           | Your outlook back then seemed pretty optimistic, while this
           | comment now seems way less so. Did something change for you
           | or had I misunderstood your post back then?
        
             | tptacek wrote:
             | I still have agents (Sketch.dev mostly) produce PRs offline
             | for me! I'm very optimistic. This is the second most
             | important thing to have happened in my career (#1: the
             | Internet; #3: mobile; #4: not writing everything in C).
             | Nothing has changed. But yeah, I still line-by-line audit
             | everything the agent spits out, and I still take the wheel
             | myself about half the time. If everything stopped right
             | here and no further progress was made on any of this
             | technology and my workflow remained the same, this would
             | remain the second most important thing.
        
         | pessimizer wrote:
         | > I have to be extremely careful and make sure nothing unwanted
         | or addition that I am unaware of has been added.
         | 
         | I've started getting desperate to the point of saying 1)
         | "never. never, ever add or remove features without consulting
         | me first and getting approval." Then eventually, 2) appended to
         | the previous "The last rule is the most important rule, because
         | you keep doing it and I need you to stop doing it." Then
         | finally 3), "THE LAST RULE IS THE MOST IMPORTANT RULE, BECAUSE
         | YOU KEEP DOING IT AND I NEED YOU TO STOP DOING IT."
         | 
         | 3/4 of my AI bugs are the AI making changes to the
         | functionality of the code when I'm not looking, or repeatedly
         | reinserting bugs that had been previously removed. The most
         | valuable thing I'm getting it to do is to refactor the code it
         | already wrote into shorter well-named functions (during which
         | it still inevitably adds and removes behavior), because it
         | means that I can just debug by hand and stop demanding over and
         | over again that it not ignore what I said.
         | 
         | But, of course, it's not ignoring me, it's not thinking at all.
         | Trying to look for the magic words to keep it from ignoring me
         | and lying about it is just an illusion of control. The thing
         | that will knock it off it's dumb track is likely just a lucky
         | random seed during the 13th attempt. Then, like a sports fan, I
         | add the lucky underwear to my instructions.
         | 
         | edit: the "I'll get AI to write the AI prompt so it will be
         | perfect" stuff is so much voodoo. LLMs have no special insight
         | into what will make LLMs work correctly. I probably should have
         | stopped that last sentence after the word "insight." Feed them
         | a sample prompt that you say doesn't work, and it will explain
         | to you exactly why it's so bad, and could never work. Feed them
         | the same prompt and ask why it works so well, and it will tell
         | you how perfectly crafted it is and why. Then it will offer to
         | tell you how it could be improved.
        
           | Kim_Bruning wrote:
           | Hrrrm, do you write unit tests to check for the desired
           | behaviour? Or does it 'optimize' those away too? %-/
        
       | sarchertech wrote:
       | Another person building zero stakes tools for AI coding. 300k LOC
       | also isn't impressive if it should have been 10k.
        
       | N_Lens wrote:
       | I'm currently satisfied with Claude Code, but this article seems
       | to sing the praises of Codex. I am dubious Whether it's actually
       | superior or it's 'organic marketing' by OAI (Given that they
       | undoubtedly do this, and other shady practices).
       | 
       | I'll give codex a try later to compare.
        
         | esafak wrote:
         | Codex is about as capable as Sonnet, but slower. One advantage
         | is that it more readily pushes back against requests, like the
         | article noted.
        
           | lysecret wrote:
           | This is very funny to me I rarely found this pushback to be
           | useful and mostly very annoying. Claude code has the opposite
           | problem sometimes though. To some extend this ends up being a
           | pure preference of character. You want ur ai coder to be
           | disagreeable or agreeable. Maybe this is a good way to
           | differentiate.
        
         | dinkleberg wrote:
         | I've found codex to be a much more thorough code reviewer.
         | 
         | Recently I've been using Claude for code gen and codex for
         | review.
         | 
         | I keep trying to use Gemini as it is so fast, but it is far
         | inferior in every other way in my experience.
        
       | CuriouslyC wrote:
       | Use of the bell curve for this meme considered harmful.
       | 
       | If you're going to use AI like that, it's not a clear win over
       | writing the code yourself (unless you're a mid programmer). The
       | whole point of AI is to automate shit, but you've planted a flag
       | on the minimal level of automation you're comfortable with and
       | proclaimed a pareto frontier that doesn't exist.
        
       | mherrmann wrote:
       | I use Claude Code every day and find that it still requires a lot
       | of hand-holding. Maybe codex is better. But just in my last
       | session today, Claude wrote 100 lines of test code that could
       | have been 20, and 30 lines of production code that could have
       | been 5. I'm glad I do not have to maintain 300 kloc of 100% AI-
       | generated code. But at the end of the day, what counts is
       | velocity and quality, and it seems OP is happy. The tools
       | certainly are useful.
        
       | cruffle_duffle wrote:
       | Have any of these no-bs articles described how they handle schema
       | changes? Are they even using a "real" DB or is it all local,
       | single user sqllite? Because I can see a disaster looming letting
       | a vibe coder's agent loose on a database.
       | 
       | And does it require auth? How is that spec'd out and validated?
       | What about RBAC or anything? How would you even get the LLM to
       | constantly follow rules for that?
       | 
       | Don't get me wrong these tools are pretty cool but the old adage
       | "if it sounds too good to be true, it probably is" always
       | applies.
        
         | lmeyerov wrote:
         | Senior engineers know process, including for what you
         | described, and that maps to plan-driven AI engineering well:
         | 
         | 1. Note the discussion of plan-driven development in the claude
         | code sections (think: plan = granular task list, including
         | goals & validation criteria, that the agent loops over and
         | self-modifies). Plans are typically AI generated: I ask it to
         | do initial steps of researching current patterns for x+y+z and
         | include those in the steps and validations, and even have it
         | re-audit a plan. Codex internally works the same, and multiple
         | people are reporting it automates more of this plan flow.
         | 
         | 2. Working with database for tasks like migrations is normal
         | and even better. My two UIs are now the agent CLI (basically
         | streaming AI chat for task list monitoring & editing) and
         | GitHub PR viewer: if it wasn't smart enough to add and test
         | migrations and you didn't put that into the plan, you see it in
         | the PR review and tell it to fix that. Writing migrations is
         | easy, but testing them is annoying, and I've found AI helping
         | write mocks, integration tests, etc to be wonderful.
        
         | steipete wrote:
         | (OP) I use atlas for database migrations, it works quite well
         | with agents and has plenty guardrails around it.
        
       | pqdbr wrote:
       | One more article praising Codex CLI over Claude Code. Decided to
       | give it a try this morning.
       | 
       | A simple task that would have taken literally no more than 2
       | minutes in Claude Code is, as of now, 9m+ and still "inspecting
       | specific directory", with an ever increasing list of read files,
       | not a single line of code written.
       | 
       | I might be holding it wrong.
        
         | kendallchuang wrote:
         | What I understand is Codex takes more time to gather context to
         | make the relevant changes; with more context it may give a more
         | precise response than Claude Code.
        
           | pqdbr wrote:
           | With Claude Code, I can 'tune' the prompt by feeling how much
           | context the model needs to perform it's task. I can mention
           | more files or tell it to read more code as needed.
           | 
           | With one hour of experience of Codex CLI, every single prompt
           | - even the most simple ones - are 5+ minutes of investigation
           | before anything gets done. Unbearable and totally
           | unnecessary.
        
           | esafak wrote:
           | It has the same context. It does not take that long to ingest
           | a bunch of files. OpenAI is just not offering the same level
           | of performance, probably due to oversubscription.
        
       | sarchertech wrote:
       | I'm not making any psychiatric diagnoses based on GitHub repos or
       | YouTube videos.
       | 
       | But. Sometimes when I see someone talking about cranking out
       | hundreds of thousands of lines of vibe coded apps, I go watch
       | their YouTube videos, or checkout their dozens of unconnected,
       | half finished repos.
       | 
       | Every single time I get a serious manic vibe.
        
         | cruffle_duffle wrote:
         | The overlap between crypto hustlers and AI hustlers is pretty
         | interesting. Not strictly "hustle both" type overlap but it's a
         | similar type of energy. Bully the non-believers and hype the
         | hype regardless of reality.
         | 
         | I dunno. People say these tools trigger the gambling part of
         | your brain. I think there is a lot of merit to that. When these
         | tools work (which they absolutely do) it's incredible and your
         | brain gets a nice hit of dopamine but holy cow can these tools
         | fail. But if you just keep pulling that lever, keep adding "the
         | right" context and keep casting the right "spells" the AI will
         | perform its magic again and you'll get your next fix. Just keep
         | at it. Eventually you'll get it.
         | 
         | Surely somebody somewhere is doing brain imagery when using
         | these tools. I wouldn't be surprised to see the same parts of
         | the brain light up as when you play something like Candy Crush.
         | Dig deep into the sunk cost fallacy, pepper with an illusion of
         | control and that glorious "I'm on a roll" feeling (how many
         | agents did this dude have active at once?) and boom...
         | 
         | I mean read the post. The dude spends $1000/mo plugging tokens
         | into a grid of 8 parallel agents. They have a term for this in
         | the gaming industry. It's a whale.
        
           | Terr_ wrote:
           | Layer on the parasocial angle and it gets even worse: You're
           | gambling _and_ you have a  "friend."
        
           | handfuloflight wrote:
           | You're describing the classic developer dopamine loop, just
           | faster now.
           | 
           | Spinning up test after test, tweaking parameters, chasing
           | that "it works!" high, that's what debugging has always been.
           | 
           | You're doing the exact same thing with your code that you're
           | criticizing him for doing with AI. Same sunk cost fallacy
           | ("I've already spent 3 hours, might as well get it working"),
           | same illusion of control, same "I'm on a roll" feeling when
           | the tests finally pass.
           | 
           | The only difference is speed. He gets micro-hits every 10
           | seconds watching tokens stream. You get them every time you
           | re-run your test suite. Same gambling structure, same reward
           | circuit lighting up, you've just normalized yours because it
           | happened slowly enough to not look like a slot machine.
           | 
           | And you're the one reducing it to "gambling" unless you're
           | claiming human developers experience zero dopamine and write
           | code with omniscient correctness the first time. If they
           | don't, if there's iteration, failure, reward, then you're
           | describing the same neurochemistry. You've just decided it
           | only counts as "gambling" when it makes you uncomfortable.
        
             | hitarpetar wrote:
             | running and slots are both addictive, so they must be
             | equally bad for you right?
        
         | stocksinsmocks wrote:
         | Well, to be fair there were a lot of guys doing exactly this
         | sort of thing except they were writing their hobby projects by
         | hand. I don't take any technical blogs about someone's secret
         | sauce seriously at all. Programmer blogs are marketing pieces.
        
           | steipete wrote:
           | Marketing for what? I didn't even link to what I'm building
           | because I wanna ship it when it's ready.
        
         | darkwater wrote:
         | In this post they mentioned "blast radius" and said "I didn't
         | invent the term but I like it though". Maybe it's just because
         | I'm very well used to the term in our industry, but that
         | sentence felt so off for me. Cringe vibes.
        
       | bigblind wrote:
       | I'd love to be able to watch people work, who say that they're
       | sucessful with these tools. If there are any devs live streaming
       | software development on Twitch, or just making screen casts
       | (without too many cuts) of how they use these tools in day-to-day
       | work, I'd love to see it.
        
         | simonw wrote:
         | Armin Ronacher has done some of those:
         | https://www.youtube.com/@ArminRonacher
        
           | maqnius wrote:
           | I skimmed through one of the videos and it reminded me of how
           | I just had a week of mainly reviewing other's code and
           | supporting their work.
           | 
           | When I finally had the occasion to code myself, I felt so
           | much better and less stressed at the end of the day.
           | 
           | My point is: what I just saw is hopefully not my future.
           | 
           | I sometimes read the opinion, that those who like the
           | programming part of software engineering, don't like
           | ,,agentic engineering" and vica versa. But can we really
           | assume that Armin Ronacher doesn't like programming?
        
             | simonw wrote:
             | It's easy to find counter-examples to that idea that people
             | who like working with coding agents don't enjoy
             | programming. I'm one of those people - I'm enjoying myself
             | _so much_ getting agents to build stuff for me, and I 've
             | enjoyed the craft of programming for 25+ years. I'm doing
             | what I did before, just faster and with less time spent on
             | the frustrating, repetitive bits.
        
               | esafak wrote:
               | Same here. I like debating the architecture, API, schema,
               | algorithms, data structures, and user experience. Once
               | all that is done, I hand off the implementation.
        
               | bdangubic wrote:
               | sooooo much this. I am in the same 25+ (almost 30) and
               | more and more thinking that there is _something_ there
               | that us "veterans" dig this so much. perhaps it is the
               | discipline we have built over the years that is being
               | applied religiously with agents...
        
           | lysecret wrote:
           | +1 for him he got me into agentic coding earlier this year.
        
         | jrk wrote:
         | If you go just a few posts back in Peter's own blog he has a
         | video of himself doing exactly this:
         | 
         | https://steipete.me/posts/2025/live-coding-session-building-...
         | 
         | He has posted others over the past few months, but they don't
         | seem to be on his blog currently.
         | 
         | As @simonw mentions in a peer comment, Armin Ronacher also has
         | several great streams (and he's less caffeinated and frenetic
         | than Peter :)
        
         | FitchApps wrote:
         | My 2c - AI-first is awesome for rapid prototyping / POC but
         | beyond that the devs should own the project and use AI
         | sparingly. I'm not saying AI agents aren't capable, I'm saying
         | that your skills will shift from problem solving/coding to
         | managing AI and whatever code it produces
        
         | jasondjk wrote:
         | I recorded a bunch of videos like this for Ruby on Rails. This
         | one is generically relevant about operating Claude hands free
         | with --dangerously-skip-permissions and importantly sandboxing
         | it in a separate user account for security:
         | https://insidertrades.directory/built-with-rails/claude-code...
        
       | aredox wrote:
       | >With Claude Code I often have multi-second freezes and it's
       | process blows up to gigabytes of memory.
       | 
       | I am in a mood where I find it excessively funny that, all that
       | talk about AI, agents, billions of dollars, tera-watts/-hours
       | spent, and people still manage to publish posts with the
       | "its/it's" mistake.
       | 
       | (I am not a native English speaker, so I notice it at a higher
       | rate than people who learned English "by ear".)
       | 
       | Maybe you don't care or you find it annoying to have it pointed
       | out, but it says something about fundamentals. You know, "The way
       | you do one thing is the way you do all things".
        
         | WA wrote:
         | I get what you're saying. "they're" and "their" is also a
         | classic that many non-natives seem to get right, but native
         | speakers have trouble with.
         | 
         | But OP isn't native either. He's Austrian.
        
         | Izkata wrote:
         | As a native speaker, for a very long time I didn't understand
         | why "its" existed, and saw "it's" as parallel to "aredox's" -
         | apostophe-s being either ownership or contraction depending on
         | context (made even more confusing because "s" without an
         | apostrophe is pluralization with other words). Somehow it
         | didn't click until late teens or early 20s that "its" is
         | supposed to be a separate word along the lines of "his" and
         | "hers".
        
         | 8note wrote:
         | i dont think its/it's will still be distinct in the dictionary
         | in 15 years. Native english speakers dont really care about the
         | difference, and autocorrect on touch keyboards have
         | disconnected a lot of the input and output of people's typing.
        
         | steipete wrote:
         | tbh in the time where everyone uses AI to write articles, some
         | typos and mistakes like that are helpful to show that it's
         | human made.
        
       | codyb wrote:
       | I'm very confused.
       | 
       | In the picture right at the top of the article, the top of the
       | bell curve is using 8 agents in parallel, and yada yada yada.
       | 
       | And then they go on to talk about how they're using 9 agents in
       | parallel at a cost of 1000 dollars a month for a 300k line
       | (personal?) project?
       | 
       | I dunno, this just feels like as much effort as actually learning
       | how to write the code yourself and then just doing it, except, at
       | the end... all you have is skills for tuning models that
       | constantly change under you.
       | 
       | And it costs you 1000 dollars a month for this experience?
        
         | woeirua wrote:
         | 300k lines of AIslop that probably would've been 20k lines of
         | code from a human. And the human has no ability to maintain it,
         | or to reason about it.
        
           | CGMthrowaway wrote:
           | I'm picturing COBOL developers in the 80s saying the same
           | thing about modern developers today (without even bringing in
           | AI).
        
             | GoatInGrey wrote:
             | COBOL developers may have claimed that higher-level
             | language developers didn't understand what was happening
             | under the hood. However, they never suggested those
             | developers couldn't understand the high-level code itself
             | (what's going on here)--only what lay beneath it.
        
               | bitwize wrote:
               | But COBOL developers resisted modern tooling. A coworker
               | of mine tells the story of when he was working alongside
               | an old mainframe hand more than 25 years ago, and was
               | trying to explain to him how modern IDEs work. The
               | mainframe guy gave him a disdainful look and said "That
               | ain't how computing is done, kid."
               | 
               | Now what the guys above the programmers' paygrade knew
               | was that the aim of software development wasn't really
               | code, it was value delivered to customer. If 300k lines
               | if AI slop deliver that value quickly, they can be worth
               | much more than the 20k lines of beautiful human-written
               | code.
        
               | hitarpetar wrote:
               | I would wager that using a fully fledged IDE has limited
               | to no correlation with developer productivity across the
               | entire industry
        
               | asdff wrote:
               | COBOL guy has a point. Novel writers didn't get any
               | better when they switched from the typewriter to ms word.
        
             | eaglelamp wrote:
             | Higher level abstractions are built on rational
             | foundations, that is the distinction. I may not understand
             | byte code generated by a compiler, but I could research the
             | compiler and understand how it is generated. No matter how
             | much I study a language model I will never understand how
             | it chose to generate any particular output.
        
             | fragmede wrote:
             | Then you'd love "Real Programmers Don't Use PASCAL", by Ed
             | Post. It's about Fortran vs PASCAL, though it does mention
             | COBOL in passing. It's copyright 1983!
             | 
             | https://www.ee.torontomu.ca/~elf/hack/realmen.html
        
           | bdangubic wrote:
           | every one of the snarky comments like this on myriad of HN
           | threads like this:
           | 
           | 1. assumes most humans write good code (or even better than
           | LLMs)
           | 
           | 2. will stick around to maintain it
           | 
           | after 30 years in the industry and last 10 as consultant I
           | can tell you fairly definitively that #1 _cannot_ be further
           | from the truth and #2 is frequent cause of consultants
           | getting gigs, no one understand what "Joe" did with this :)
        
             | mattmanser wrote:
             | I think it's hard as he's done a huge article about coding
             | with agents, with no code examples.
             | 
             | You can go look at his GitHub but it's a bewildering array
             | of projects. I've had a bit of a poke around at a few of
             | the seemingly more recent ones. Bit odd though as in one
             | he's gone heavy on TS classes and another heavy on
             | functions. Might be he was just contributing to one as it
             | was under a different account.
             | 
             | And a lot of them seem to be tools that wrap a lot of cli
             | tools. There is a ton of scaffolding code, to handle a ton
             | of cli options. A LOT of logger stmts, one file I randomly
             | opened was a logger stmt every other line.
             | 
             | So it's hard to judge, I found it hard to wade through the
             | code as it's basically just a bunch of option handling for
             | tool calls. It didn't really _do_ much. But necessary,
             | probably?
             | 
             | Just very different code than I need to write.
             | 
             | And there are some weird tells that make it hard to
             | believe.
             | 
             | For example, he talks about refactoring for useEffect in
             | React but I KNOW GPT5 is really rubbish at it.
             | 
             | Some code it's given me recently was littered with
             | useEffect and useMemo when it wasn't needed. Then when
             | challenged it got rid of some, then changed other stuff to
             | useEffect when again, it wasnt needed.
             | 
             | And then got all confused and basically blew it's top.
             | 
             | Yet this person says he can just chuck a basic prompt at
             | his codex cli, running GPT5 and it magically refractors the
             | bad useEffects?
             | 
             | How are we getting such different results?
        
               | bdangubic wrote:
               | Personally, my experience with codex is same as yours, no
               | way I would ever use codex for TS projects and especially
               | not React. I don't know this mate personally but if we
               | were talking about this over beer I would probably tell
               | you (after 3rd one when I am more open to being direct)
               | that I think I trust this blog as much as I trust
               | President (this one or previous ones) to tell the truth
               | :)
               | 
               | My comment was more geared towards an insane amount of
               | comments on myriad of "AI" / "agent coding" posts where
               | soooooo many people will write "oh, such AI slop"
               | assuming that average SWE would write it better. I don't
               | know many things but working with these tools _heavily_
               | over the last year or so (and really heavily last 6
               | months) I 'll take their output over general average SWE
               | every day of the week and twice on Sunday (provided that
               | I am driving the code generation myself, not general AI
               | generated code...)
        
               | steipete wrote:
               | (OP) the current projec is closed source. If you look at
               | my cli tools, that's pure slop, all I care is that it
               | works, so reviewing that code for sure will show some
               | weird stuff. Does it matter? It's a tool to fetch logs
               | form a server. I run it locally. As long as is does that
               | reliably, idk about the code.
        
               | steipete wrote:
               | OP: If you give the llm examples like
               | https://react.dev/learn/you-might-not-need-an-effect, it
               | does a farily good job at refactoring useEffecs.
               | 
               | And yes refactoring sometimes re-introduces these, so
               | it's not a perfect solution.
        
         | ljm wrote:
         | This is like having a normal distribution where the average is
         | a 1x engineer, a standard deviation below is a 0x engineer, and
         | a standard deviation above is a 10x engineer. Which would make
         | more sense because someone running 9 agents with multiple git
         | checkouts and what-not is just managing a team of synthetic
         | vibe coders.
        
       | esafak wrote:
       | I wonder how many lines of code he generates and reviews a day.
       | With five subscriptions I do not think it is possible to read it
       | all. You can generate more code than you can read with just one
       | subscription.
        
       | outside1234 wrote:
       | Is this paid content from OpenAI?
        
         | simonw wrote:
         | No.
         | 
         | In the USA it's actually not legal for companies to pay for
         | promotional content like this without disclosure. Here's the
         | FTC's FAQ about that: https://www.ftc.gov/business-
         | guidance/resources/ftcs-endorse...
         | 
         | (It's pretty weird to me how much this comes up - there's this
         | cynical idea that nobody would possibly write at length about
         | how they're using these tools for their own work unless they
         | were a paid shill.)
        
       | ljm wrote:
       | Meta feedback: there are so many external links in this post (the
       | majority being to Twitter) that it really feels like the audience
       | is just...people who follow this guy on Twitter. There must be
       | about 25 separate links to one-liner tweets.
       | 
       | Surely one of those 9 parallel AI agents could add something like
       | footnotes with context?
        
       | FitchApps wrote:
       | Feels like with 3 agents coding non-stop you're no longer a coder
       | but rather a manager of sorts...is it even possible to code / fix
       | things by yourself in an environment such as this?
        
       | nf17 wrote:
       | Looks like many are questioning the credibility of the author as
       | a dev/engineer. Peter is the founder of PDFKit and well respected
       | name in iOS circles for his contribution to .framework and ideas
       | about building modular iOS apps. He may be overselling here, but
       | pretty sure he can manage AI generated code
        
       | bionhoward wrote:
       | Is using these terminal agents with customer noncompete and no
       | privacy questionable when cursor has the same models and privacy
       | mode?
        
       | Kim_Bruning wrote:
       | I get the idea that different AI have different characters, and
       | different people can either 'get along with them' or not.
       | 
       | To wit, I have absolutely no problems with claude code, but
       | anytime I try to do anything useful with chatgpt it turns into
       | (effectively) a shouting match; There's just no way that
       | particular AI and I can see eye-to-eye. (there's underlying
       | procedural reasons I think)
       | 
       | The author of this piece has the exact opposite experience.
       | Apparently they hate Claude with a passion, but love ChatGPT.
       | Weird!
        
         | lysecret wrote:
         | This is a fascinating aspect. I also find much more usage out
         | of Claude code and its willingness to go along with my ideas
         | and be "steerable" seems to be part of it with codex many times
         | it kept on overwriting changes I told it to make. It's a clear
         | kind of disagreeableness trait in action. Makes me think!
        
       ___________________________________________________________________
       (page generated 2025-10-15 23:01 UTC)