[HN Gopher] Cursor 1.7
___________________________________________________________________
Cursor 1.7
Author : mustaphah
Score : 137 points
Date : 2025-10-01 13:51 UTC (9 hours ago)
(HTM) web link (cursor.com)
(TXT) w3m dump (cursor.com)
| qsort wrote:
| I could be wrong about this, but it feels like Cursor is less and
| less compelling with better models and better CLI tools popping
| up. Are the plan limits generous enough that it's worth a spin?
|
| Again, I haven't used Cursor in a while, I'm mostly posting this
| hoping for Cunningham's Law to take effect :)
| anthonypasq wrote:
| Cursor is your best option if you want to switch models
| frequently, run multiple agents in parallel, and also have the
| best tab complete out there. And you're still getting extra vc-
| funded tokens. You get ~$40 worth of tokens at API costs for
| the $20 plan.
|
| idk seems worth it to me. If youre shelling out on one of the
| $200 plans maybe its not as worth it, but it just seems like
| the best all in one ai product out there.
| deaux wrote:
| Except for the autocomplete, it's not the best option even
| for the user you're describing.
| Sammi wrote:
| Does anyone have autocomplete that is half as good as
| Cursors? I just tried vanilla vs code with github copilot
| and it was terrible. Not worth paying for bad.
| anthonypasq wrote:
| windsurf is probably half as good
| anthonypasq wrote:
| nothing else does it all
| chermi wrote:
| As everyone with half a brain predicted, their pricing was
| never meant to last. Their "limit" (base plan) is now just $20
| in API credits, at slightly higher than provider token price.
| Sometimes they let you go a little over, but I'm not sure if
| that's still true.
| jermaustin1 wrote:
| I'm currently flying, and using Cursor. I have my model set to
| Sonnet-4, and it keeps bugging me that my usage is going to end
| on 10/21, 10/19, 10/13, 10/08, after just a couple hours of
| VERY slow LLM usage.
|
| I wouldn't even bother with it, but my MCP coding tool I built
| uses Claud Desktop and is for windows only, and my laptop is
| MacOS. So I'm using Cursor, and it is WAY WORSE than my most
| simple of MCP servers (that literally just does dotnet
| commands, filesystem commands, and github commands).
|
| I think having something that is so general like cursor causes
| the editor to try too many things that are outside what you
| actually want.
|
| I fought for 2 hours and 45 minutes while Sonnet-4 (which is
| what my MCP uses) kept inventing worse ways to implement OpenAI
| Responses using the OpenAI-dotnet library. Even switching to
| GPT-5 didn't help. Adding the documentation didn't help. I went
| to claude in my browser, pasted the documentation, and my class
| I wanted extended to use Responses, and it finished it in 5
| minutes.
|
| The Cursor "special-sauce" seems to be a hinderance now-days.
| But beggars can't be choosers, as they say.
| jtrn wrote:
| I find Cursor at the same level as Claude code, with some
| strengths and some weaknesses. Cursor is nice when I want to
| start multiple parallel agents, while browsing files,
| monitoring the progress, and switching models as needed. It's
| just a simple, zero config environment i can just start using
| intuitively.
|
| Claude code is more reliable and generally better at using MCP
| for tool cal, like docs from contex7. So if I had only one
| prompt and it HAD to make something work, Claude code would be
| my bet.
|
| Personally I like jumping between models and IDEs , if only to
| mix it up. And you get a reminder of different ways of doing
| stuff.
| visarga wrote:
| I tried Claude Code once and half an hour later it printed
| $10 cost. I thought I was using the pro subscription, not the
| API. This makes using CC dangerous, so I am avoiding it.
| esafak wrote:
| Don't avoid it, fix it!
| mohsen1 wrote:
| Cursor was good for a little while until VSCode opened up the
| APIs for AI editing. Now Copilot is really good and other
| extensions (specifically Kilo Code) are doing things so much
| better!
|
| I am seeing a lot of folks talking about maintaining a good
| "Agent Loop" for doing larger tasks. It seems like Kilo Code has
| figured it out completely for me. Using the Orchestrator mode I'm
| able to accomplish really big and complex tasks without having to
| design an agent loop or hand crafting context. It switches
| between modes and accomplishes the tasks. My AGENTS.md file is
| really minimal like "write test for changes and make small
| commits"
| jtrn wrote:
| Did something change with Kiro, or was I just using it wrong? I
| tried to have it make a simple MCP server based on docs, and it
| seriously spent 6 hours without making a basic MVP. It looked
| like the most impressive planner and executor while working,
| but it just made a mess.
| junebash wrote:
| Kilo != Kiro
| dghlsakjg wrote:
| Kilo Code != Kiro IDE
| WesleyJohnson wrote:
| I feel like I've hit a sweet spot for my use case, but am so
| behind the times. I've been a developer for 20 years and I'm
| not interested in vibe coding or letting an agent run wild on
| my full code base.
|
| Instead, I'll ask Cursor to refactor code that I know is
| inefficient. Abstract repetitive code into functions or
| includes. Recommend (but not make) changes to larger code
| blocks or modules to make them better. Occasionally, I'll have
| it author new functionality.
|
| What I find is, Cursor's autocomplete pairs really with with
| the agent's context. So, even if I only ask it for suggestions
| and tell it to not make the change, when I start implementing
| those changes myself (either some or all), the shared context
| kicks in and autocomplete starts providing suggestions in the
| direction of the recommendation.
|
| However, at any time I can change course and Cursor picks up
| very quickly on my new direction and the autocomplete shifts
| with me.
|
| It's so powerful when I'm leading it to where I know I want to
| go, but having enormous amounts of training data at the ready
| to guide me in best-practices or common patterns.
|
| I don't run any .md files though. I wonder what I'm missing out
| on.
| skydhash wrote:
| Abstraction for abstraction sake is usually bad. What you
| should aim for is aligning it to the domain so that feature
| change requests are proportional to the work that needs to be
| done. Small changes, small PRs.
| aeon_ai wrote:
| Why waste precious milliseconds typing complete sentences to your
| AI coding assistant? With autocomplete in the prompt box, we've
| solved the most pressing problem facing developers today: prompt
| fatigue.
|
| Gone are the days of exhausting yourself by typing full requests
| like "refactor this function to use async/await." Now, simply
| type "refac--" and let our AI predict that you want an AI to
| refactor your code.
|
| It's AI all the way down, baby.
| debesyla wrote:
| Swipe right if you vibe with AI suggestion, swipe left if not.
| cesarvarela wrote:
| With Meta's wristband, you can save some finger and arm
| movement as well.
| imiric wrote:
| No joke--out of all tech products announced in the last
| ~year, that wristband is what excites me the most.
| siva7 wrote:
| You write like that's a bad thing. What's with the negativity
| here..
| aeon_ai wrote:
| [flagged]
| kenreidwilson wrote:
| based
| vasco wrote:
| It's funny to imagine this AI based autocomplete prompting
| when the interface isn't a keyboard but a brain chip.
| Effectively mind control.
| yonaguska wrote:
| It's already been here for a long time actually. Think
| google search auto completion of prompts. You're looking
| for something that might have biases on either side, and
| you are only shown autocomplete entries for a specific
| bias.
| mrjay42 wrote:
| So you mean that with lactose intolerance, I could be more
| productive? :3
| enraged_camel wrote:
| >> What's with the negativity here
|
| The builders are quietly learning the tools, adopting new
| practices and building stuff. Everyone else is busy
| criticizing the tech for its shortcomings and imperfections.
| aeon_ai wrote:
| Look, I use AI regularly. I value AI.
|
| It's not a criticism of AI, broadly, it's commentary on a
| feature designed to make engineers (and increasingly non-
| engineers) even lazier about one of the main points of
| leverage in making AI useful.
| enraged_camel wrote:
| Autocomplete is one of Cursor's most popular features,
| and is cited as the _only_ reason some people continue to
| use it. And you 're mocking the Cursor team for adding it
| to the one place where devs still type a lot of text, and
| making a value judgment by calling it lazy.
| aeon_ai wrote:
| > adding it to the one place where devs still type a lot
| of text
|
| Because that's where the text the devs type still matters
| most.
|
| Do I care significantly about this feature's existence,
| and find it an affront to humanity? No.
|
| But, people who find themselves using auto-complete to
| make even their prompts for them will _absolutely_ be
| disintermediated, so I think it wise to ensure people
| understand that by making funny jokes about it.
| simianwords wrote:
| You come across as smug but there really is value in
| this. Let's get rid of autocorrect in ChatGPT while we
| are at it? Same logic right?
| noodletheworld wrote:
| It's obviously farcical.
|
| Anyone seriously using these tools knows that context
| engineering and detailed specific prompting is the way to
| be effective with agent coding.
|
| Just take it to the extreme and youll see; what if you
| auto complete from a single word? A single character?
|
| The system youre using is increasingly generating some
| _random output_ instead of what you were either a) trying
| to do, or b) told to do.
|
| Its funny because its like, "How can we make vibe coding
| _even worse_?"
|
| "...I know, lets just generate random code from random
| prompts"
|
| There have been multiple recent posts about how to direct
| agents using a combination of planning step, context
| summary/packing, etc to craft detailed prompts that
| agents can effectively action on large code bases.
|
| ...or yeah, just hit tab and go make a coffee. Yolo.
|
| This _could_ have been a killer feature about using a
| research step to enhance a user prompt and turn it into a
| super prompt; but it isnt.
| simianwords wrote:
| What's wrong with autocompleting the prompt? There exists
| entropy even in the English language and especially in
| the prompts we feed to the llms. If I write something
| like "fix the ab.." and it autocompletes to
| AbstractBeanFactory based on the context, isn't it
| useful?
| Capricorn2481 wrote:
| > The builders are quietly learning the tools, adopting new
| practices and building stuff
|
| I thought the "you're not a real programmer if you don't
| use AI" gatekeeping would take a little longer than this,
| but here we are. All from the most minor of jokes.
| semiquaver wrote:
| You're absolutely correct! This comment was more negative
| than it could be. Would you like me to rewrite it to
| demonstrate more positivity?
| compootr wrote:
| Yes! Please proceed by writing a haiku for a cookie recipe
| kiitos wrote:
| you're right, i guess it's only negative if you think it's
| important for people to understand the code they produce, if
| that's not a concern for you then no problemo
| TZubiri wrote:
| I hate writing prompt starters for AI, I wish I had a tool that
| automatically started sentences so that my AI could
| autocomplete it
| huvarda wrote:
| lowkey typing is so cumbersome though they should make an ai
| model that can read my thoughts and generate a prompt from
| them so i don't have to anymore
| ebiester wrote:
| You are thinking too small. AI should be able to determine
| what my thoughts should be and execute them so I don't have
| to spend my precious time actually thinking.
| fallinditch wrote:
| Precisely. And there should be an option to randomize.
| NitpickLawyer wrote:
| > It's AI all the way down, baby.
|
| This brings up an interesting point that's often missed, IMO.
| LLMs are one of the few things that work on many layers, such
| that once you have a layer that works, you can always add
| another abstraction layer on top. So yes, you could very well
| have a prompt that "builds prompts" that "builds prompts" that
| ... So something like "do x with best practices in mind" can
| turn into something pretty complex and "correct" down the line
| of a few prompt loops.
| imiric wrote:
| I can't tell anymore if comments like this are sarcastic or
| not.
| whywhywhywhy wrote:
| None of my experiences with cursor lately would ever give me
| confidence for letting it do a task that took long enough for it
| to be backgrounded.
|
| Caught Claude 4.5 via Cursor yesterday trying to set a password
| to "password" on an outward facing EC2 service.
| jjice wrote:
| Curious what your case was for using Claude to set passwords on
| EC2 instances. Terraform, CDK, something else?
| GuardianCaveman wrote:
| Nice to see the image files being read without having to paste
| them and team rules. Cursor has been extremely helpful the last
| few months but increasingly more expensive. I spent almost 300
| last month and had a lot of frustrating experiences so now I'm
| transitioning to Claude code in VS code.
| deaux wrote:
| $300!? You could literally switch to any of the dozen
| competitors and it'd be cheaper than that for at least the same
| quality, good god.
| cesarvarela wrote:
| For some reason, CLIs feel better as coding agent UIs. I loved
| Cursor at first, but now with Claude Code, it feels like Cursor's
| UI gets in the way.
| bfeynman wrote:
| The reason is abundantly clear. Cursor was just a GPT wrapper
| with a nice UI/UX (which was very nice when it came out) it has
| some other models like autocomplete as well, but its still a
| wrapper. OpenAI and Anthropic build and train models
| specifically to work via CLI driven processes, which is why
| they are so much better now. Cursor is basically dead as I'm
| sure they realized they get much better performance with the
| CLI/agentic approach.
| dmix wrote:
| > OpenAI and Anthropic build and train models specifically to
| work via CLI driven processes,
|
| Cursor agents open terminals just fine in VSCode and is a
| major part of how Cursor works.
|
| I personally code in VSCode text editor prior to Cursor (left
| VIM a while ago) and prefer to stay in the context of a
| desktop text editor. I find it's easier to see what's
| changing in real time, with a file list, file tabs, top level
| and inline undo buttons etc.
|
| I've even stopped tabbing to a separate terminal by about
| 50%, I learned to use VSCode terminals to run tests and git
| commands, which works well once you learn the shortcuts +
| integrate it into some VSCode test runner extensions. Plus
| Cursor added LLM/autocomplete to terminal commands which is
| great. I don't need a separate CLI tool or Bash/zsh script
| inside terminal to inject terminal commands I forgot the
| arguments for.
| jbkkd wrote:
| > just a GPT wrapper
|
| Cursor's tab auto complete isn't, and it's the greatest
| strength point of the product
| leerob wrote:
| (I work at Cursor)
|
| We also have a CLI, if you prefer coding in the terminal. We've
| seen this useful for folks using JetBrains or other IDEs:
| https://cursor.com/cli
| theappsecguy wrote:
| I'd love in-terminal autocomplete support with Vim or Helix.
| I can't stand VSCode but cursor autocomplete is 95% of my
| cursor usage.
| aurareturn wrote:
| I only use VSCode Copilot in Agent mode with either Claude Sonnet
| 4 or GPT5. Am I missing out on anything?
| mohsen1 wrote:
| 6 months ago you were missing out but today, not much really
| vel0city wrote:
| Anyone have good recommendations for plugins integrating things
| like LM Studio or Ollama into Visual Studio or Jetbrains IDEs?
| I'd like to do more local AI processing on code bases instead of
| always relying on outside providers, but a lot of these things
| like Copilot and Cursor seem so well integrated into the IDE.
| rickette wrote:
| JetBrains native AI assistant supports Ollama out of the box.
| No need for a 3rd party plugin anymore.
|
| See https://www.jetbrains.com/help/ai-assistant/use-custom-
| model...
| doomroot13 wrote:
| Copilot in VSCode supports local models through Ollama as well.
| Not sure about Copilot in Visual Studio. That's one of the most
| annoying things is VS is always behind VSCode in terms of
| Copilot features.
| hansonkd wrote:
| I wish cursor would let you see how much usage in terms of $$ you
| have done for your month. Its really hard to see in the dashboard
| the individual charges tokens, but then there is no cumulative. I
| haven't been able to find a way to see how much of my included
| usage is being used besides downloading the csv and manually
| summing. They just give you a very unhelpful "You will use your
| included credits by X date"
|
| I suppose this is by design so you don't know how much you have
| left and will need to buy more credits.
| enraged_camel wrote:
| You mean this page? https://cursor.com/dashboard?tab=usage
| hansonkd wrote:
| It doesn't show cumulative does it? For me it just shows my
| plan name and itemized token usage but no "You used x out of
| y of your included credits"
| enraged_camel wrote:
| It shows me $XX/$YYY at the very top, on the right side.
| /shrug
| hansonkd wrote:
| Thats on demand usage. Not your plan usage. You get Y
| credits every month before you start using on demand
| usage. That $XX/$YYY is how much of your on demand usage
| limit you used.
| leerob wrote:
| (I work at Cursor)
|
| We added usage visibility in the IDE with v1.4:
| https://cursor.com/changelog/1-4#usage-and-pricing-
| visibilit.... By default, it only shows when you are close to
| your limits. You can toggle it to always display in your
| settings, if you prefer.
| hansonkd wrote:
| great!
| oersted wrote:
| I'd love to hear from folks who mainly use Claude Code on why
| they prefer it and how they compare. It seems to be the most
| popular option here in HN, or at least the most frequently
| mentioned, and I never quite got why.
|
| I always preferred the deep IDE integration that Cursor offers. I
| do use AI extensively for coding, but as a tool in the toolbox,
| it's not always the best in every context, and I see myself often
| switching between vibe coding and regular coding, with various
| levels of hand-holding. And I do also like having access to other
| AI providers, I have used various Claude models quite a lot, but
| they are not the be-all-end-all. I often got better results with
| o3 and now GPT-5 Thinking, even if they are slower, it's good to
| be able to switch and test.
|
| I always felt that the UX of tools like Claude Code encourage you
| to blindly do everything through AI, it's not as seamless to dig-
| in and take more control when it makes sense to do so. That being
| said, they are very similar now, they all constantly copy each
| other. I suppose for many it's just inertia as well, simply about
| which one they tried first and what they are subscribed to, to an
| extent that is the case for me too.
| qsort wrote:
| I don't think we are in a phase where we can confidently state
| that there's a correct answer on how to do development,
| productivity self reports are notoriously unreliable.
|
| At least personally, the reason why I prefer CLI tools like
| Claude and Codex is precisely that they feel like yet another
| tool in my toolbox, more so than with AI integrated in the
| editor. As a matter of fact I dislike almost all AI
| integrations and Claude Code was when AI really "clicked" for
| me. I'd rather start a session on a fresh branch, work on
| something else while I wait for the task to be done, and then
| look at the diff with git difftool or IDE-integrated
| equivalent. I'd argue you have just as much control with this
| workflow!
|
| A final note on the models: I'm a fan of Claude models, but I
| have to begrudgingly admit that gpt-5-codex high is very good.
| I wouldn't have subscribed just for the gpt-5 family, but Codex
| is worth it.
| sexyman48 wrote:
| Maximalists who find value in "deep IDE integration" and go on
| about it also enjoy meetings.
| oersted wrote:
| That is a bit uncalled for, I like to be lean and technically
| precise as much as the next guy.
|
| I am not talking about "deep IDE integration" in a wishy-
| washy sense, what I care about as a professional engineer is
| that such an integration allows me to seamlessly intervene
| and control the AI when necessary, while still benefiting
| from its advantages when it does work well on its own.
|
| Blindly trusting the AI while it does things in the
| background has rarely worked well for me, so a UX optimized
| for that is less useful to me, as opposed to one designed to
| have the AI right where I can interlieve it with normal
| coding seamlessly and avoid context-switching.
| arjie wrote:
| It's primarily the simplicity with which I can work on multiple
| things. Claude code is also very good with using tools and
| stuff like that in the background so I just use a browser MCP
| and it does stuff by itself. I hook it up to staging bigquery
| and it uses test data. I don't need to see all these things. I
| want to look at a diff, polish it up in my IDE, and then git
| commit. The intermediate stuff is not that interesting to me.
|
| This suddenly reminded me that I have a Cursor subscription so
| I'm going to drop it.
|
| But of course if someone says that Cursor's flow suddenly 2x'd
| in speed or quality, I would switch to it. I do like having the
| agent tool be model hotpluggable so we're not stuck on
| someone's model because their agent is better, but in the end
| CC is good at both things and codex is similar enough that I'm
| fine with it. But I have little loyalty here.
| oersted wrote:
| That makes sense. Personally I have rarely gotten truly
| satisfactory results with such a hands-off approach, I cannot
| really stop babysitting it, so facilities to run it in the
| background or be able to do multiple things at once are
| rather irrelevant to me.
|
| But I can see how it might make sense for you. It does depend
| a lot on how mainstream what you are working on is, I have
| definitely seen it be more than capable enough to leave it do
| its thing for webdev with standard stacks or conventional
| backend coding. I tend to switch a lot between that and a bit
| more exotic stuff, so I need to be able to fluidly navigate
| the spectrum between fully manual coding and pure vibe
| coding.
| saltyoldman wrote:
| I think personally I really like Claude, but our company has
| standardized on Cursor. Both are very good. I do like the tab
| completion. The "accept/undo" flow of cursor is really annoying
| for me. I get why its there, but it just seems like a secondary
| on top of Git. I usually get everything in a completely
| committed state so I can already see all my changes through the
| standard git management features of "VSCode".
|
| I think Claude's latest VSCode plugin is really great, and it
| does make me question why Cursor decided to fork instead of
| make a plugin. I'd rather have it be a plugin so I don't have
| to wipe out my entire Python extension stack.
| oersted wrote:
| I like the "accept/undo" feature because it allows for much
| more granular control. You can accept some files or lines,
| and give feedback or intervene manually in other parts. I
| don't like building up technical debt by accepting everything
| by default.
| sexyman48 wrote:
| As in chess, stock trading, and combat aviation, people at
| first believed humans ought to curate computer-generated
| strategies. Then it become obvious the humans were
| unnecessary.
| hombre_fatal wrote:
| I've tried to use the agent sidebar of Cursor on a monthly
| basis for a year, but I just can't get into it.
|
| 1. I find it hard to review its changes inline in the editor
| compared to Claude Code's diffs. And I still don't really
| understand or like my editor being in a weird partial state
| when its changes are pending approval. With Claude, it doesn't
| touch my editor state. It pitches changes on the side, and I
| find this simpler.
|
| 2. I like to read code even when I'm waiting for Claude to
| write code, and I like to compare the source to Claude's diff,
| so I don't like how Cursor updates the file with proposals as
| it creates them. I like keeping it separate.
|
| 3. I was never good at figuring out complex IDE UX. Using
| Cursor's agent just now, I don't understand what UX
| interactions do despite repeating them multiple times much less
| how to derive a workflow. It feels like trying to figure out a
| bunch of icon buttons in Eclipse.
|
| For example, I asked the agent to write code and it did. Then I
| rejected its changes. But going back and clicking the code
| blocks in the convo or "..." -> "Show code" doesn't seem to
| show its proposal, it just opens the file? And I can't reapply
| the proposal? I can come up with a dozen of misunderstandings
| like this in 15min.
|
| Reminds me of when I spent a month learning Scala in uni but
| tried Clojure when I saw it on HN, and I built more that
| afternoon with Clojure than the whole month of Scala.
|
| That said, I use Cursor as my daily editor but I only pay
| $20/mo for the autocomplete.
| axwdev wrote:
| I use Cursor because I found their autocomplete to be the best
| option at the time. That seemed to be the consensus at one point
| too from bits of research I did.
|
| Do people think there are better autocomplete options available
| now? Is it a case of just using a particular model for
| autocomplete in whatever IDE you want to use?
| hahn-kev wrote:
| I agree, they bought out Supermaven which was amazing, but now
| Supermaven is dead and I want something in Rider.
| hn_throw2025 wrote:
| I don't think Supermaven is dead...
|
| Even though it is also part of Cursor, you could subscribe to
| the $10/month Pro plan and use it in Jetbrains IDEs like
| Rider.
|
| https://supermaven.com/pricing
| z3ratul163071 wrote:
| today i found myself wondering why Github Copilot is so
| retarded without any autocomplete whatsover in the agent input
| ddxv wrote:
| Same! Just tried Copilot heavily for a few days and the
| autocomplete is terribly slow and clunky.
|
| Overall I do like VSCode better but Cursors blazing fast and
| intelligent autocomplete is awesome, will probably stick with
| Cursor.
|
| Btw, I find the review / agent code stuff pretty bad on both.
| No idea how people get them working well.
| treefry wrote:
| Right. Yesterday I tried a simple task that just adds
| Required[] notation to all class fields. After making the
| change on one field, Cursor allows me to press tabs and update
| all other fields. VSCode doesn't understand what I was trying
| to do after the first operation, which is surprisingly bad (no
| improvement after months). Also I'm not in favor of the
| conversational experience of claude code or other CLIs for such
| trivial task. I'd be happy to know what else can provide a
| better user experience than Cursor.
|
| Disclaimer: I get enterprise level subscriptions to these
| services via my employer. I personally don't pay for them and
| never consider their cost, if that matters.
| causal wrote:
| I got into Cursor a little late, went really heavy on it, and see
| myself using it less and less as I go back to VSCode.
|
| 1) The most useful thing about Cursor was always state management
| of agent edits: Being able roll back to previous states after
| some edits with the click of a button, or reapply changes, and
| preview edits, etc. But weirdly, it seems like they never
| recognized this differentiator, and indeed it remains a bit
| buggy, and some crucial things (like mass-reapply after a
| rollback) never got implemented.
|
| 2) Adding autocomplete to the prompt box gives me suspicion they
| somehow still do not understand best practices in using AI to
| write code. It is more crucial than ever to be clear in your mind
| what you want to do in a codebase, so that you can recognize when
| AI is deviating from that path. Giving the LLM more and earlier
| opportunities to create deviation is a terrible idea.
|
| 3) Claude Code was fine in CLI and has a nearly-identical
| extension pane now too. For the same price, I seem to get just as
| much usage, in addition to a Claude subscription.
|
| I think Cursor will lose because models were never their
| advantage and they do not seem to really be thought leaders on
| LLM-driven software development.
| leerob wrote:
| (I work at Cursor)
|
| 1. Checkpoints/rollbacks are still a focus for us, albeit it's
| less used for those working with git. Could you share the bug
| you saw?
|
| 2. Autocomplete for prompts was something we were skeptical of
| as well, but found it really useful internally to save time
| completing filenames of open code files, or tabbing to
| automatically include a recently opened file into the context.
| Goal here is to save you keystrokes. It doesn't use an LLM to
| generate the autocomplete.
|
| 3. A lot of folks don't want to juggle three AI subscriptions
| for coding and have found the Cursor sub where they can use
| GPT, Claude, Gemini, Grok models to be a nice balance. YMMV of
| course!
| visarga wrote:
| > (I work at Cursor)
|
| I find the amount of credits included in the pro subscription
| per month totally insufficient. Maybe it lasts 1-2 weeks.
|
| Today I got a message telling me I exhausted my subscription
| when the web dashboard was showing 450/500. Is there a team
| level constraint on top of individual ones?
| causal wrote:
| Addressing 2) first: That's good, I totally misunderstood
| then, and guess I'll need to try it to understand what's new
| since I thought that kind of tabbing had been there a while.
|
| Back to 1): The type of bug I see most often is where
| conversation history seems incomplete, and I have trouble
| rolling back to or even finding a previous point that I am
| certain existed.
|
| Git shares some features but I think Git was not made for the
| type of conversational rapid-prototyping LLMs enable. I don't
| want to be making commits every edit in some kind of
| parallel-git-state. Cursor's rollback and branching
| conversations make it easy to backup if a given chat goes
| down the wrong path. Reapply is tedious since it has to be
| done one edit at a time - would be nice if you could roll-
| forward.
|
| I haven't put much thought into what else would be useful,
| but in general the most value I get from Cursor is
| simplifying the complex state of branching conversations.
| stagalooo wrote:
| FWIW, my workflow with git is to stage changes I want to
| keep after every prompt. Then I can discard changes in the
| working area after a bad prompt or stage individual changes
| before discarding from the working area. Works really nice
| for me.
| causal wrote:
| Yeah I've used staging/stashing similarly, but it feels
| like working around Cursor rather than with it
| __jl__ wrote:
| Since we have cursor people joining, let me bring up my
| constant problems around applying code changes. For
| background, I mostly work with "chat":
|
| 1. The apply button does not appear. This used to be mostly a
| problem with Gemini 2.5 Pro and GPT-5 but now sometimes
| happens with all models. Very annoying because I have to
| apply manually
|
| 2. Cursor doesn't recognize which file to apply changes to
| and just uses the currently open file. Also very annoying and
| impossible to change the file to which I want to apply
| changes after they were applied to one file.
| taylorfinley wrote:
| For both of these scenarios, it seems to happen when the
| context limit is getting full and the context is
| summarized. I've found it usually works to respond with the
| right file, i.e. "great, let's apply those changes in
| @path/to/file", but it may also be a good time to return to
| an earlier conversation point by editing one of your
| previous messages. You might edit the message that got you
| the response with changes not linked to a specific file,
| including the file path in that prompt will usually get you
| back on track.
| risho wrote:
| i really tried to use cursor and really wanted to like it but
| i constantly ran into this problem where the agent wasnt able
| to see what was happening in the terminal.
| kaoD wrote:
| I've had this happen too in VSCode, but for some reason
| I've never seen it since the GPT-5 Codex release?
|
| Are you perhaps on Windows+MinGW? That's the only weird
| thing in my setup (and it has caused problems in the past
| for me).
| xyos wrote:
| I did too and it was because powerlevel10k theme for zsh,
| if you customize your terminal as many people do, you will
| have a bad time
| visarga wrote:
| What I hate about Cursor is that - even when I have credits
| left - it still hangs for a full minute before starting to
| respond. Not always, but often enough. You don't know what
| you're buying, you might get fast response, you might get a
| tortoise.
| deelowe wrote:
| VScode has a bit of a history now of quickly deprecating
| competitors who innovate in this space. It already has good
| options for code completion, AI chat bots, and more features on
| the horizon. I'm not sure what cursors moat is. Seems to me
| like Microsoft could easily implement any new feature cursor
| comes up with.
| theturtle32 wrote:
| For me, the best kind of "moat" (tbh I hate that word, since
| it specifically implies needing to design (...scheme...) and
| engineer some kind of user lock-in, which is inherently user-
| hostile) would be _staying_ aggressively on the forefront of
| DX. More important than feature churn, making it polished and
| seamless and keeping a smile on my face as I work is the best
| kind of "moat."
|
| It requires constant attention and vigilance, but that's
| better for everyone than having some kind of "moat" that lets
| them start coasting or worse-- lets them start diverting
| focus to features that are relevant for their enterprise
| sales team but not for developers using the software.
|
| Companies really should have to stay competitive on features
| and developer happiness. A moat by definition is anti-
| competitive.
| clickety_clack wrote:
| I totally agree on point 1. Being able to make piece wise,
| limited updates with AI was a sweet spot, but they keep pushing
| towards "ai changes hundreds of lines across dozens of files"
| type edits. I bought into cursor heavily from the off, and I've
| seen it create auth bypasses, duplicate component libraries and
| break ORM models. I know what I want to do, I just want it to
| happen faster and in a way I can control and direct, and that's
| not the direction cursor seems to to be going.
|
| I've actually gone back to neovim, copying in snippets from
| ChatGPT. I don't think I've given up anything in speed.
| jrop wrote:
| Neovim + Git + Aider seems to get close to perfection.
| tripplyons wrote:
| I have tried similar workflows (Neovim + Opencode/Codex
| CLI), and for me, the biggest downside compared to Cursor
| is the lack of a tab completion model as good as Cursor's.
| Supermaven is the best one I've found so far for Neovim,
| but it gives worse suggestions and can only suggest changes
| on the same line you are on.
| causal wrote:
| I do find the agents useful sometimes, but Cursor is most
| useful when it gives me visibility and granular control over
| what the agents are doing. Trying to follow a verbose
| narrative through a narrow chat pane is not it.
| alphazard wrote:
| Cursor seems to give me access to a lot of models for a single
| fee. I would love to just pay for Claude and maybe ChatGPT or
| Grok, but it seems like that's more expensive than Cursor.
| Sammi wrote:
| I tried vanilla vs code again three weeks ago. The tab complete
| was so slow and gave such poor results that I had to crawl back
| to Cursor after not even a full week. Cursor is sooo fast and
| useful in comparison.
| tripplyons wrote:
| The main reason I use Cursor is for their tab complete model.
| I enjoy using Neovim more than Cursor, but I choose not to
| use it because I haven't been able to find anything that
| makes me as productive as Cursor's tab model.
| nailer wrote:
| > Claude Code was fine in CLI and has a nearly-identical
| extension pane now too.
|
| One of us is wrong here. Last I checked, the extension pane was
| a command line, that doesn't use macOS keybindings,
| reimplements common controls, uses monospaced text for prose,
| etc.
|
| I don't mind particularly about the last two but 'cmd A' on my
| Mac highlight all the text in the Claude Code user interface,
| rather than the text in the text box, is annoying.
| causal wrote:
| Sounds like you're still using the terminal. I'm talking
| about https://marketplace.visualstudio.com/items?itemName=ant
| hropi...
| nailer wrote:
| That's exactly the one I'm discussing. The extension pane
| runs in a terminal and has all the behaviors mentioned.
| Unless they rewrote the thing in Electron it doesn't use
| normal UI keyboard shortcuts or controls.
| ai-christianson wrote:
| > Adding autocomplete to the prompt box gives me suspicion they
| somehow still do not understand best practices in using AI to
| write code. It is more crucial than ever to be clear in your
| mind what you want to do in a codebase, so that you can
| recognize when AI is deviating from that path. Giving the LLM
| more and earlier opportunities to create deviation is a
| terrible idea.
|
| Agreed 100%
|
| Any time there's LLM auto complete on the prompt (chatgpt has
| done this too!) I find it horribly distracting and it often
| makes me completely lose track of what I had in mind,
| especially on more difficult tasks.
| nojs wrote:
| > The most useful thing about Cursor was always state
| management of agent edits
|
| Note that CC introduced this yesterday, it's very fast and
| good.
| sersi wrote:
| I really don't understand Cursor's 30 billion dollars valuation
| (half of Antropic). I use it, it's not a bad tool by any means
| but it's so buggy from version to version. Latest bug I had, it
| completely stopped keeping my zsh state in the terminal, I had to
| downgrade. And honestly, I'm not that sure what secret sauce is
| worth 30 billion dollars? The agent loop? Others can do that? The
| autocomplete?
| causal wrote:
| Yeah I have to imagine it's because of user base, there's no
| real moat in the technology
| bfeynman wrote:
| not only that but the way that openai and claude have their
| own foundational models/agents trained to work via CLI, which
| will basically always be better than just cursors gpt wrapper
| approach.
| esafak wrote:
| How are they trained to work via CLI? You prompt it and it
| returns response. Where does the CLI come into play?
| throwaway314155 wrote:
| Have you used Claude Code or OpenAI Codex yet?
| esafak wrote:
| Yes, daily.
| jsnell wrote:
| That's 1/6th of Anthropic, not half.
| jtokoph wrote:
| Off topic, but does anyone understand why Apple's reader mode is
| so bad? This post is an example of reader mode not displaying
| section titles. I see this pretty frequently, even in my own
| blog, and haven't been able to figure out hires to beat its
| flawed logic.
| mdale wrote:
| Was spending a lot with cursor switching between sonnet and opus
| 4.1s like 1500 to $2k a month. Was doing a lot of tabs in
| parallel of course. Output was like 5k lines on Good day. (Lines
| not the best measurement) But a yard stick against feature
| testing and rework.
|
| Now with gpt-5-codex and codex vs code ext .. getting through up
| to 20k line changes in a day again lots of parallel jobs; but
| codex allows for less rework.
|
| The job of the "engineer" has changed a lot. At 5k lines I was
| not reviewing every detail but it was possible to skim over what
| had changed. At 20k it's more looking at logs performance / arch
| & observation of features less code is reviewed.
|
| Maybe soon just looking at outcomes. Things are moving quickly.
| dmix wrote:
| Sounds like a different use case than Cursor. Editing that many
| files/lines probably scales better with a CLI tool. Cursor
| makes more sense for day-to-day maintenance and heavy hand-
| holding feature development coding.
|
| If I was building a new project from scratch I'd probably use a
| CLI tool to manage a longer TODO easier. But working on
| existing legacy code I find an IDE integration is more
| flexible.
| esafak wrote:
| And this unreviewed code is going into production?
| simonw wrote:
| OK I'd love to know more about how they implemented this:
| https://cursor.com/changelog/1-7#sandboxed-terminals
|
| "Commands now execute in a secure, sandboxed environment. If
| you're on allowlist mode, non-allowlisted commands will
| automatically run in a sandbox with read/write access to your
| workspace and no internet access."
| simonw wrote:
| ... I had Claude Code dig into it and looks like it's calling
| sandbox-exec.
| leerob wrote:
| Indeed, it's using `sandbox-exec`. I'll add this to the docs.
| saos wrote:
| I've been using this editor more and to be honest, I love it so
| much. Yet to try Claude code though.
| justhw wrote:
| Since finding out a Claude Code extension to run on VS
| Code/cursor, I use it less and less. With git and Claude Code,
| rolling back and forth is a breeze. Cursor is cooked, as the cool
| kids say now days. They need to adapt and find a moat.
| deaux wrote:
| Cursor will soon be irrelevant. The one thing that it excels at
| is autocomplete, and that's ironically the one feature they
| bought out and integrated (Supermaven) instead of developing
| themselves, which sums it up quite well. It's still making good
| money based on having been first to market , but it's market
| share has been in freefall for ages, only accelerating.
|
| The agentic side is nothing special and it's expensive for what
| you get. Even if you're the exact target audience - don't want
| CLI, want multiple frontier models to choose from for a fixed
| monthly price - Augment is both more competent and ends up
| cheaper.
|
| Then for everyone else who is fine with a single model, Claude
| Code and now Codex are obviously better choices. Or those who
| want cheaper and faster through open weights models, there's
| Opencode and Kilo.
|
| The mystery is that the other VC backed ones seemingly don't care
| or just don't put enough resources into cracking the autocomplete
| code, as many are still staying with Cursor purely for that - or
| were until CC became mainstream. Windsurf was making strides but
| now that's dead.
| romanovcode wrote:
| Do not underestimate enterprise customers who buy Cursor for
| all their employees. Cursor will become legacy tech soon, yes.
| But it will be slow death, not a crash.
| rfoo wrote:
| > and that's ironically the one feature they bought out and
| integrated (Supermaven) instead of developing themselves
|
| What? Cursor bought Supermaven last November and I have been
| using their much superior (compared to GH Copilot) completion
| since maybe early last year so it does not add up.
| Sammi wrote:
| Vs code tab complete is still so bad there's no point even
| having it.
| hackernewds wrote:
| Do you work at Supermaven, because that is 100% not the case
| mellosouls wrote:
| Like many others I was very pro cursor a year or so ago, but
| unfortunately since then 3 significant things have severely
| impacted its appeal:
|
| VS Code accepted the challenge and upped its game.
|
| Claude Code changed the game.
|
| Cursor's own heavy value decrease (always part of the strategy
| but poorly communicated and managed) hit Cursor users _hard_ when
| the cheap premium tokens honeymoon ended in recent months.
|
| Existing users are disappointed, potential new users no longer
| see it as the clear class leader, because it isn't.
| OldGreenYodaGPT wrote:
| with Codex and Claude Code there is no reason to use Cursor
| a_wild_dandan wrote:
| Is it possible to run Cursor entirely with local models? My Mac
| can comfortably run relatively massive models. I would experiment
| so much more with AI in my codebases knowing that I won't slam
| into a brick wall due to quotas, connection issues, etc.
| cadamsdotcom wrote:
| 1 year since canceling Cursor; I thank them for being a stepping
| stone on my journey of agentic coding.
|
| Legacy tech, but a great idea before models got good enough to
| use via CLI.
| timcobb wrote:
| Great job ya'll! Admittedly I haven't tried Claude Code but
| that's because I think Cursor is the bees knees! I do agree with
| the people posting that the 500 requests pricing approach is
| kinda rough, but I can see how you're trying to figure this out
| as a company that doesn't own a frontier model like Anthropic.
| Anyway, great job! _Love_ the new Agent View. Fun to see you guys
| hashing out this UI/UX release by release.
| robinhood wrote:
| I use Cursor only because of their extraordinary tab suggestion
| feature. It's still blowing the competition away. It's 1000000
| times better than any other tools I've tried and I've tried them
| all. Cursor should focus on that feature alone - anything else
| will end up in enshittification.
| AIorNot wrote:
| I used to work at NASA as an engineer, and the way it works (E.g
| space station operations or shuttle missions) was that hundreds
| of engineers are working on various complex systems on the ground
| while astronauts try to do a mission in space.
|
| What this means that dozens of procedures and activities are
| happening at any one time in orbit, and that a Flight Director on
| the ground and an Astronaut in space needs to be at least
| cognizant or aware of (at least enough to prevent disasters and
| complete the tasks) -this is the greatest challenge in on-orbit
| work.
|
| IE to widen this metaphor: to collect and gather complex
| operational data on differing parts of a system in a USEFUL way
| is the greatest challenge of complex work and software
| engineering is about controlling complexity above all.
|
| Now at NASA, we often wrote up procedures and activities with
| the- "Astronauts are smart they can grok it" mindset; but during
| debriefs the common refrain from those at the top of pyramid was
| that "I don't have the mental capacity to handle and monitor
| dozens of systems at the same time" -Humans are very bad at
| getting in flow when monitoring things.. maybe if some kind of
| flow state was achievable like a conductor over an orchestra in
| orchestrating agents..but I don't see that happening with
| multiple parts of the codebase getting altered at the same time
| by a dozen agents.
|
| Cursor and Agentic tools bring this complexity (and try to tame
| it through a chat window or text response) to our daily work on
| our desktop; now we might have dozens of AI Agents working on
| aspects of your codebase! Yes, its incredible progress but with
| this amazing technical ability comes great responsibility for the
| human overseer...this is the 'astronaut' in my earlier metaphor-
| an overburdened software engineer.
|
| Worryingly also culture wise- management teams now expect
| software devs to deliver much faster, this is dangerous since we
| can use these tools but are forced to leave more to autopilot in
| hopes of catching bugs in test etc - I see that trend is to push
| away the human oversight into blind agents but this is the wrong
| model I think for now -how can I trust and agent without
| understanding all that it did?
|
| To summarize, I like both Cursor and Claude Code, but I think we
| need better paradigms in terms of UX so that we can better handle
| conflicts, stupid models, reversions, better windows on what
| changed code-wise.. I also get the trend of creating trash-able
| instances in containers and killing them on failure, but we still
| need to understand how a code change impacts other parts of the
| codebase -
|
| anyway somebody on the cursor team will not even read this post
| -they will just summarize the whole HN thread with AI and
| implement some software tickets to add another checkbox to the
| chat window in response.. this is not the engineering we need in
| response to this new paradigm of working.. we need some deep
| 'human' design thinking here..
| DrNosferatu wrote:
| - Does anyone know good, thorough video tutorials for Cursor?
|
| I use Cursor, but I don't know if I'm using it to the fullest.
|
| (same for Claude Code - I never used it, and would actually like
| to compare between them)
___________________________________________________________________
(page generated 2025-10-01 23:01 UTC)