{"slug": "cursor", "name": "Cursor", "category": "ai-coding", "category_name": "AI coding tools", "description": "AI-powered code editor forked from VS Code with built-in agents and autocomplete.", "recommenders": 123, "commenters": 301, "warners": 42, "score": 106.238, "rising": -2.09, "first": "2025-11-01", "latest": "2026-10-31", "why": "Liked for the fast, cheap in-house Composer and Auto models, easy switching between models from different providers and its Cursor Tab autocomplete.", "why_is_quote": false, "has_verdict": true, "sentiment": {"recommend": 125, "neutral": 138, "compare": 11, "warn": 44}, "spark": [7, 10, 11, 7, 8, 13, 7, 25, 7, 15, 10, 5], "listed": true, "loved": ["Composer and Auto", "Model choice"], "caveat": "Pricing", "short_quote": "I love Cursor. As a Product Manager who's not really had coding experience, it's been very useful.", "icon": true, "domain": "cursor.com", "github_repo": null, "official_url": "https://cursor.com", "pricing": "freemium", "aliases": ["Cursor"], "verdict": [{"text": "Liked for the fast, cheap in-house Composer and Auto models", "cites": [{"id": 794776993, "item_id": 49673562, "url": "https://news.ycombinator.com/item?id=49673562", "by": "time0ut", "date": "2026-09-12", "stance": "recommend", "quote": "I prefer Cursor at this point just because of Composer.", "excerpt": "If I had to pick just one, these days it\u2019s Composer. It is just a cheap, fast, surgical workhorse. My workflow uses other models as well for various phases: Opus for planning, Sonnet for review, etc. I prefer Cursor at this point just because of Composer. Claude Code is passable but the lack of a good, fast, cheap workhorse sucks. Sonnet and Haiku aren\u2019t it. I also do like Codex and Sol, Terra, and Luna. They are dec", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Ask HN: What default model do you use and why?"}, {"id": 792880016, "item_id": 49555001, "url": "https://news.ycombinator.com/item?id=49555001", "by": "lacoolj", "date": "2026-09-03", "stance": "recommend", "quote": "I use Cursor daily and almost everything I do, highly complex or high volume, can be handled with Auto mode or Composer 2.5", "excerpt": "Jesus what are you doing that requires Sol usage so often? Terra not enough? I know Luna isn't reliable, so that's fair. Genuinely curious though, because I use Cursor daily and almost everything I do, highly complex or high volume, can be handled with Auto mode or Composer 2.5 (or Grok 4.6 High). So I have to assume you're doing something far more complex than what I am", "context": "", "use_case": "daily coding", "switched_from": "", "story": "OpenAI begins rolling out GPT-6 Astra"}, {"id": 777084560, "item_id": 48567785, "url": "https://news.ycombinator.com/item?id=48567785", "by": "jemmyw", "date": "2026-06-17", "stance": "recommend", "quote": "now I use it for my personal projects. The plan is good value for accessing different sota models", "excerpt": "I didn't like cursor when it first came about but now I use it for my personal projects. The plan is good value for accessing different sota models occasionally for planning. Composer is actually really good, and fast. I'm not sure if it's because my personal projects are small enough I know them inside out and my work project is huge, but I prefer terminal code agents for day work over ide integration.", "context": "", "use_case": "personal projects, planning", "switched_from": "", "story": "SpaceX to buy Cursor AI coding agent operator Anysphere for $60B"}]}, {"text": ", easy switching between models from different providers", "cites": [{"id": 791794672, "item_id": 49487167, "url": "https://news.ycombinator.com/item?id=49487167", "by": "rippeltippel", "date": "2026-08-29", "stance": "recommend", "quote": "The thing that keeps me using it is precisely the ability to switch between models", "excerpt": "I may be a rare Cursor user around here, but I am saddened by this news. The thing that keeps me using it is precisely the ability to switch between models: I usually do brainstorm/planning with Sol or Terra, then let Composer (free) deal with the implementation. For certain tasks I use Claude, which tends to be more expensive but sometimes saves me time. Using both OpenAI and Anthropic models, Cursor is cheaper than", "context": "", "use_case": "AI coding with multiple models", "switched_from": "", "story": "Our decision on Cursor following its acquisition by SpaceX"}, {"id": 777035345, "item_id": 48564709, "url": "https://news.ycombinator.com/item?id=48564709", "by": "ghshephard", "date": "2026-06-16", "stance": "recommend", "quote": "the nice thing about Cursor - you can flick between models.", "excerpt": "You absolutely don't. I use all three products. My preference is Claude Code for my personal project. The one at work is kind of sandboxed off - but does have the benefit of an MCP for every enterprise service we have (Kibana, Victoria Metrics, Grafana, Jira, etc...) - which is nice. Over time - I expect Composer will be cheaper than Opus 4.8 - but the nice thing about Cursor - you can flick between models. And (this", "context": "", "use_case": "work coding with enterprise MCPs", "switched_from": "", "story": "SpaceX to buy Cursor AI coding agent operator Anysphere for $60B"}, {"id": 800050416, "item_id": 50003151, "url": "https://news.ycombinator.com/item?id=50003151", "by": "disgruntledphd2", "date": "2026-10-08", "stance": "recommend", "quote": "I kinda like cursor, mostly because it provides a nice review UI and I can use whatever model I want.", "excerpt": "> Cursor is easily the worst experience I've had with an AI harness I kinda like cursor, mostly because it provides a nice review UI and I can use whatever model I want. Getting away from all the Claude-speak has been a revelation, and fortunately Anthropic helped me here by hyping up GLM 5.3. Like, if there's an open weight Fable competitor, then why wouldn't I use it?", "context": "", "use_case": "AI coding with code review UI", "switched_from": "", "story": "Docker Agent"}]}, {"text": " and its Cursor Tab autocomplete.", "cites": [{"id": 777039120, "item_id": 48564945, "url": "https://news.ycombinator.com/item?id=48564945", "by": "mjrbrennan", "date": "2026-06-16", "stance": "recommend", "quote": "the Cursor Tab autocompletion is still the best AI-based editor autocomplete I have used.", "excerpt": "Yes, I use it as my daily driver at Discourse, the Cursor Tab autocompletion is still the best AI-based editor autocomplete I have used. I switched to nvim earlier in the year because there was no real great AI integrations that didn't feel cumbersome, Cursor in vim mode is a much nicer experience, I like adding lines of code to agent context and so on. All of the extensions from VSCode, LSP integration, and so on ar", "context": "works at Discourse", "use_case": "daily driver editor", "switched_from": "", "story": "SpaceX Is Buying Cursor"}, {"id": 786197200, "item_id": 49137325, "url": "https://news.ycombinator.com/item?id=49137325", "by": "RussianCow", "date": "2026-08-01", "stance": "recommend", "quote": "none of them feel nearly as polished as Cursor", "excerpt": "They're not as good. I've tried all the options available a couple months ago, and none of them feel nearly as polished as Cursor. For one thing, Cursor Tab is just far better than any other \"next edit\" prediction I've used. I also happen to like their agent UI the most, but they don't support ACP, so you can't use it with Claude Code, which was a deal-breaker for me. These days I've switched to Zed, which is good en", "context": "", "use_case": "IDE with next-edit prediction", "switched_from": "", "story": "Cursor removed cost information from the usage page and CSV export"}, {"id": 796342273, "item_id": 49771392, "url": "https://news.ycombinator.com/item?id=49771392", "by": "muzani", "date": "2026-09-20", "stance": "recommend", "quote": "The autocomplete itself is extremely good.", "excerpt": "I've moved to Codex lately, Astra does better with less bugs. When GPT does poorly, I use Cursor. The autocomplete itself is extremely good. And then there's Kimi code and similar which can't keep up with the existing demand, much less the demand if all other tools go down. Then Opencode, which would probably be a year or so behind SOTA but it's good enough.", "context": "", "use_case": "autocomplete", "switched_from": "", "story": "Ask HN: What happens when Claude Code goes away?"}]}, {"text": " The most common complaint is confusing and rising pricing", "cites": [{"id": 777069248, "item_id": 48566828, "url": "https://news.ycombinator.com/item?id=48566828", "by": "jackzhuo", "date": "2026-06-17", "stance": "warn", "quote": "I had stopped using Cursor since July 2025, because of its mess pricing policy.", "excerpt": "I had stopped using Cursor since July 2025, because of its mess pricing policy. Now I use codex & claude code & antigravity, and can not return to using Cursor.", "context": "", "use_case": "AI coding", "switched_from": "", "story": "SpaceX to buy Cursor AI coding agent operator Anysphere for $60B"}, {"id": 784253904, "item_id": 49015869, "url": "https://news.ycombinator.com/item?id=49015869", "by": "subhobroto", "date": "2026-07-22", "stance": "warn", "quote": "That assumption is now a financial mishap waiting to happen as of today", "excerpt": "Cursor's \"Auto\", to me, used to mean \"cheap flat rate, don't worry which model ran\". That assumption is now a financial mishap waiting to happen as of today: 2026-07-22. Cursor just shipped \"Cursor Router\" [1]. Auto in the model picker is now three modes, no longer one: - Intelligence - frontier quality - Balance - \"daily driver\" frontier quality - Cost - the previous Auto routing, with fixed per-token prices (per Co", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Tell HN: Cursor Auto is no longer \"Auto\"! Let's welcome Auto Cost"}, {"id": 791844704, "item_id": 49490294, "url": "https://news.ycombinator.com/item?id=49490294", "by": "zxspectrum1982", "date": "2026-08-29", "stance": "recommend", "quote": "I use Cursor at work and love it. It's a great IDE, the best IMHO.", "excerpt": "I use Cursor at work and love it. It's a great IDE, the best IMHO. But it becomes really expensive. Since the introduction of the Cursor Token Rate, my company tells us to use Claude and Codex directly with Anthropic (or Vertex AI) and OpenAI, respectively. https://cursor.com/docs/models-and-pricing#cursor-token-rate I'm now using Grok 4.6 most of the time. Sonnet some times. But that's it. Cursor-native models 99% o", "context": "employee whose company pushes direct vendor tools", "use_case": "work IDE", "switched_from": "", "story": "Our decision on Cursor following its acquisition by SpaceX"}, {"id": 777024305, "item_id": 48564019, "url": "https://news.ycombinator.com/item?id=48564019", "by": "CSMastermind", "date": "2026-06-16", "stance": "warn", "quote": "Cursor was costing me $10k / month.", "excerpt": "> I was switching between Opus and GPT 5.x and was spending anywhere between $500-1000/month. I switched to Codex because Cursor was costing me $10k / month. If the price goes up by 4x I'm not sure the value will be there for a lot of people.", "context": "", "use_case": "coding agent", "switched_from": "", "story": "SpaceX Is Buying Cursor"}]}, {"text": ", with some users also wary of the xAI/SpaceX ownership.", "cites": [{"id": 805095120, "item_id": 50318445, "url": "https://news.ycombinator.com/item?id=50318445", "by": "arendtio", "date": "2026-10-31", "stance": "recommend", "quote": "In general, I am pretty happy with Cursor", "excerpt": "I used Cursor first, tried Claude Code, but went back to Cursor. In general, I am pretty happy with Cursor, but given Elon's talent for ruining things, I am currently preparing for an exit. It is not because I don't like Cursor or have found something better, just because I see things like no OpenAI models going forward, a push for Grok, and the stuff that xAI did in the past. Before Cursor, I used vim + tmux.", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Backdoor in Claude Code for VS Code extension on the Cursor Marketplace"}, {"id": 788399393, "item_id": 49274962, "url": "https://news.ycombinator.com/item?id=49274962", "by": "calldacopsidgaf", "date": "2026-08-12", "stance": "warn", "quote": "if you're looking to get off of Cursor since X.ai bought them", "excerpt": "Literal trash for nazis. By the way if you're looking to get off of Cursor since X.ai bought them, I switched to Zed a few weeks ago and out-of-the-box it does everything Cursor can without charging you their dumbass premium. The transition is pretty much seamless", "context": "", "use_case": "code editing", "switched_from": "", "story": "Grok 4.6"}, {"id": 804849440, "item_id": 50303090, "url": "https://news.ycombinator.com/item?id=50303090", "by": "darkwi11ow", "date": "2026-10-30", "stance": "recommend", "quote": "Cursor was the market leader in LLM-assisted IDE experience before SpaceX acquisition", "excerpt": "There is no alternative really. Cursor was the market leader in LLM-assisted IDE experience before SpaceX acquisition, though Elon nerfed the product a lot in recent months. And there is still no good alternative to it. Google tries to compete via Antigravity, but that also uses OpenVSX. I myself use Cursor and use Claude there installed via OpenVSX, and was not affected only thanks to my laziness (I saw upgrade butt", "context": "", "use_case": "AI-assisted IDE", "switched_from": "", "story": "Backdoor in Claude Code for VS Code extension on the Cursor Marketplace"}]}], "praise": [{"label": "Composer and Auto", "summary": "Cursor's own Composer model and Auto mode are described as fast, cheap and good enough for most tasks.", "quotes": [{"id": 794776993, "item_id": 49673562, "url": "https://news.ycombinator.com/item?id=49673562", "by": "time0ut", "date": "2026-09-12", "stance": "recommend", "quote": "I prefer Cursor at this point just because of Composer.", "excerpt": "If I had to pick just one, these days it\u2019s Composer. It is just a cheap, fast, surgical workhorse. My workflow uses other models as well for various phases: Opus for planning, Sonnet for review, etc. I prefer Cursor at this point just because of Composer. Claude Code is passable but the lack of a good, fast, cheap workhorse sucks. Sonnet and Haiku aren\u2019t it. I also do like Codex and Sol, Terra, and Luna. They are dec", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Ask HN: What default model do you use and why?"}, {"id": 792880016, "item_id": 49555001, "url": "https://news.ycombinator.com/item?id=49555001", "by": "lacoolj", "date": "2026-09-03", "stance": "recommend", "quote": "I use Cursor daily and almost everything I do, highly complex or high volume, can be handled with Auto mode or Composer 2.5", "excerpt": "Jesus what are you doing that requires Sol usage so often? Terra not enough? I know Luna isn't reliable, so that's fair. Genuinely curious though, because I use Cursor daily and almost everything I do, highly complex or high volume, can be handled with Auto mode or Composer 2.5 (or Grok 4.6 High). So I have to assume you're doing something far more complex than what I am", "context": "", "use_case": "daily coding", "switched_from": "", "story": "OpenAI begins rolling out GPT-6 Astra"}, {"id": 791913568, "item_id": 49494598, "url": "https://news.ycombinator.com/item?id=49494598", "by": "thefourthchime", "date": "2026-08-30", "stance": "recommend", "quote": "The best bet is Cursor Ultra ($200)", "excerpt": "It's a little confusing because Grok and Cursor kinda live in different worlds. Grok has SuperGrok and SuperGrok Heavy ($300 a month!) The best bet is Cursor Ultra ($200), which is the equivalent a month plan that you get from OpenAI and Anthropic. I get a LOT more capacity out of it because I almost always use the \"Auto\" mode, which auto picks between Opus 5, GPT 5.6, Grok 4.6, and Composer 2.5. I like Auto mode so ", "context": "uses Cursor for work account", "use_case": "vibe coding", "switched_from": "", "story": "Our decision on Cursor following its acquisition by SpaceX"}]}, {"label": "Model choice", "summary": "Users value switching between OpenAI, Anthropic and other models in one tool.", "quotes": [{"id": 791794672, "item_id": 49487167, "url": "https://news.ycombinator.com/item?id=49487167", "by": "rippeltippel", "date": "2026-08-29", "stance": "recommend", "quote": "The thing that keeps me using it is precisely the ability to switch between models", "excerpt": "I may be a rare Cursor user around here, but I am saddened by this news. The thing that keeps me using it is precisely the ability to switch between models: I usually do brainstorm/planning with Sol or Terra, then let Composer (free) deal with the implementation. For certain tasks I use Claude, which tends to be more expensive but sometimes saves me time. Using both OpenAI and Anthropic models, Cursor is cheaper than", "context": "", "use_case": "AI coding with multiple models", "switched_from": "", "story": "Our decision on Cursor following its acquisition by SpaceX"}, {"id": 777035345, "item_id": 48564709, "url": "https://news.ycombinator.com/item?id=48564709", "by": "ghshephard", "date": "2026-06-16", "stance": "recommend", "quote": "the nice thing about Cursor - you can flick between models.", "excerpt": "You absolutely don't. I use all three products. My preference is Claude Code for my personal project. The one at work is kind of sandboxed off - but does have the benefit of an MCP for every enterprise service we have (Kibana, Victoria Metrics, Grafana, Jira, etc...) - which is nice. Over time - I expect Composer will be cheaper than Opus 4.8 - but the nice thing about Cursor - you can flick between models. And (this", "context": "", "use_case": "work coding with enterprise MCPs", "switched_from": "", "story": "SpaceX to buy Cursor AI coding agent operator Anysphere for $60B"}, {"id": 804854656, "item_id": 50303416, "url": "https://news.ycombinator.com/item?id=50303416", "by": "darkwi11ow", "date": "2026-10-30", "stance": "recommend", "quote": "Cursor comes very convenient to have all three in a single interface", "excerpt": "Well for me, as developer on a modern stack, there is always some risk involved. If not from agentic tools, then the package registries are compromised left and right, so it all comes down to mitigating the risk. I use Claude, Codex and Cursor/SpaceX agents, and Cursor comes very convenient to have all three in a single interface. Also I still code manually especially when prototyping, so having an IDE helps with it ", "context": "developer on a modern stack", "use_case": "unified AI coding IDE", "switched_from": "", "story": "Backdoor in Claude Code for VS Code extension on the Cursor Marketplace"}]}, {"label": "Tab autocomplete", "summary": "Cursor Tab is called the best AI editor autocomplete, and some users miss it after switching away.", "quotes": [{"id": 777039120, "item_id": 48564945, "url": "https://news.ycombinator.com/item?id=48564945", "by": "mjrbrennan", "date": "2026-06-16", "stance": "recommend", "quote": "the Cursor Tab autocompletion is still the best AI-based editor autocomplete I have used.", "excerpt": "Yes, I use it as my daily driver at Discourse, the Cursor Tab autocompletion is still the best AI-based editor autocomplete I have used. I switched to nvim earlier in the year because there was no real great AI integrations that didn't feel cumbersome, Cursor in vim mode is a much nicer experience, I like adding lines of code to agent context and so on. All of the extensions from VSCode, LSP integration, and so on ar", "context": "works at Discourse", "use_case": "daily driver editor", "switched_from": "", "story": "SpaceX Is Buying Cursor"}, {"id": 786197200, "item_id": 49137325, "url": "https://news.ycombinator.com/item?id=49137325", "by": "RussianCow", "date": "2026-08-01", "stance": "recommend", "quote": "none of them feel nearly as polished as Cursor", "excerpt": "They're not as good. I've tried all the options available a couple months ago, and none of them feel nearly as polished as Cursor. For one thing, Cursor Tab is just far better than any other \"next edit\" prediction I've used. I also happen to like their agent UI the most, but they don't support ACP, so you can't use it with Claude Code, which was a deal-breaker for me. These days I've switched to Zed, which is good en", "context": "", "use_case": "IDE with next-edit prediction", "switched_from": "", "story": "Cursor removed cost information from the usage page and CSV export"}, {"id": 779247664, "item_id": 48702979, "url": "https://news.ycombinator.com/item?id=48702979", "by": "mjrbrennan", "date": "2026-06-27", "stance": "recommend", "quote": "the only thing I miss is cursor tab. The vscode implementation just isn\u2019t as good", "excerpt": "Update to this comment \u2014 I switched to VSCode and the only thing I miss is cursor tab. The vscode implementation just isn\u2019t as good :(", "context": "", "use_case": "AI autocomplete", "switched_from": "", "story": "SpaceX Is Buying Cursor"}]}, {"label": "Value for money", "summary": "Some find it cheaper or more token-efficient than Claude Code, especially on the Ultra plan.", "quotes": [{"id": 788454272, "item_id": 49278392, "url": "https://news.ycombinator.com/item?id=49278392", "by": "maxdo", "date": "2026-08-12", "stance": "recommend", "quote": "Cursor ultra is great . For 200 you got essentially unlimited capacity vs Claude.", "excerpt": "Cursor ultra is great . For 200 you got essentially unlimited capacity vs Claude. I used auto in cursor it\u2019s much faster va Claude code and as good.", "context": "", "use_case": "AI coding", "switched_from": "", "story": "SpaceXAI's Grok 4.6 Scores 61 on the Artificial Analysis Intelligence Index"}, {"id": 781675904, "item_id": 48854744, "url": "https://news.ycombinator.com/item?id=48854744", "by": "noisy_boy", "date": "2026-07-09", "stance": "recommend", "quote": "I have been using Cursor daily (along with Claude)", "excerpt": "I did the side by side between Claude code (effort medium) and Cursor (auto). Asked Claude to prepare a plan and asked Cursor to review it and it found tons of gaps in the plan. Cost-wise, it came out better too. I have been using Cursor daily (along with Claude) and the former has been 20-30% cheaper despite me spending more time on it.", "context": "", "use_case": "reviewing plans and coding", "switched_from": "", "story": "GPT-5.6"}, {"id": 793441680, "item_id": 49590105, "url": "https://news.ycombinator.com/item?id=49590105", "by": "Dmitry-kov", "date": "2026-09-06", "stance": "recommend", "quote": "in cursor i wasted less tokens while i do some tasks", "excerpt": "I use claude code and cursor. Interesting that I use opus 5 in cirsor and claude code, but in cursor i wasted less tokens while i do some tasks. During auto-tests runs, Claude code re-watch tasks and context before start my auto-test. In cursor this problem not reproduce. I use cursor most of the time.", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Portal by Spotify cut my Claude Code token usage by 90%"}]}, {"label": "Review and editor UX", "summary": "In-editor review, quick edits and the agent UI keep users in the flow.", "quotes": [{"id": 791802800, "item_id": 49487675, "url": "https://news.ycombinator.com/item?id=49487675", "by": "jackjeff", "date": "2026-08-29", "stance": "recommend", "quote": "cursor has just a better UX for AI integration", "excerpt": "Is there some kind of alternative to Cursor in these terms - fast because the code is already indexed no need to start every prompt rediscovering the world with rg - in editor/vscode review much better than relying on git diff at the very end. You can click on next button to jump there. Quick edit in place. Or a quick prompt (seconds) to fix something small - in editor completion / quick edits, when you do things by ", "context": "", "use_case": "AI-assisted coding in editor", "switched_from": "", "story": "Our decision on Cursor following its acquisition by SpaceX"}, {"id": 800050416, "item_id": 50003151, "url": "https://news.ycombinator.com/item?id=50003151", "by": "disgruntledphd2", "date": "2026-10-08", "stance": "recommend", "quote": "I kinda like cursor, mostly because it provides a nice review UI and I can use whatever model I want.", "excerpt": "> Cursor is easily the worst experience I've had with an AI harness I kinda like cursor, mostly because it provides a nice review UI and I can use whatever model I want. Getting away from all the Claude-speak has been a revelation, and fortunately Anthropic helped me here by hyping up GLM 5.3. Like, if there's an open weight Fable competitor, then why wouldn't I use it?", "context": "", "use_case": "AI coding with code review UI", "switched_from": "", "story": "Docker Agent"}, {"id": 791844704, "item_id": 49490294, "url": "https://news.ycombinator.com/item?id=49490294", "by": "zxspectrum1982", "date": "2026-08-29", "stance": "recommend", "quote": "I use Cursor at work and love it. It's a great IDE, the best IMHO.", "excerpt": "I use Cursor at work and love it. It's a great IDE, the best IMHO. But it becomes really expensive. Since the introduction of the Cursor Token Rate, my company tells us to use Claude and Codex directly with Anthropic (or Vertex AI) and OpenAI, respectively. https://cursor.com/docs/models-and-pricing#cursor-token-rate I'm now using Grok 4.6 most of the time. Sonnet some times. But that's it. Cursor-native models 99% o", "context": "employee whose company pushes direct vendor tools", "use_case": "work IDE", "switched_from": "", "story": "Our decision on Cursor following its acquisition by SpaceX"}]}], "caveats": [{"label": "Pricing", "summary": "Users complain of messy pricing changes, router billing surprises and high monthly costs.", "quotes": [{"id": 777069248, "item_id": 48566828, "url": "https://news.ycombinator.com/item?id=48566828", "by": "jackzhuo", "date": "2026-06-17", "stance": "warn", "quote": "I had stopped using Cursor since July 2025, because of its mess pricing policy.", "excerpt": "I had stopped using Cursor since July 2025, because of its mess pricing policy. Now I use codex & claude code & antigravity, and can not return to using Cursor.", "context": "", "use_case": "AI coding", "switched_from": "", "story": "SpaceX to buy Cursor AI coding agent operator Anysphere for $60B"}, {"id": 784253904, "item_id": 49015869, "url": "https://news.ycombinator.com/item?id=49015869", "by": "subhobroto", "date": "2026-07-22", "stance": "warn", "quote": "That assumption is now a financial mishap waiting to happen as of today", "excerpt": "Cursor's \"Auto\", to me, used to mean \"cheap flat rate, don't worry which model ran\". That assumption is now a financial mishap waiting to happen as of today: 2026-07-22. Cursor just shipped \"Cursor Router\" [1]. Auto in the model picker is now three modes, no longer one: - Intelligence - frontier quality - Balance - \"daily driver\" frontier quality - Cost - the previous Auto routing, with fixed per-token prices (per Co", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Tell HN: Cursor Auto is no longer \"Auto\"! Let's welcome Auto Cost"}, {"id": 777024305, "item_id": 48564019, "url": "https://news.ycombinator.com/item?id=48564019", "by": "CSMastermind", "date": "2026-06-16", "stance": "warn", "quote": "Cursor was costing me $10k / month.", "excerpt": "> I was switching between Opus and GPT 5.x and was spending anywhere between $500-1000/month. I switched to Codex because Cursor was costing me $10k / month. If the price goes up by 4x I'm not sure the value will be there for a lot of people.", "context": "", "use_case": "coding agent", "switched_from": "", "story": "SpaceX Is Buying Cursor"}]}, {"label": "Token usage", "summary": "One user says Cursor burns far more tokens than alternatives.", "quotes": [{"id": 781428819, "item_id": 48839301, "url": "https://news.ycombinator.com/item?id=48839301", "by": "froggy", "date": "2026-07-08", "stance": "warn", "quote": "Orgs need to start getting more visibility into why Cursor burns so many tokens.", "excerpt": "If you want to do some non-eugenics, fascist-free AI coding, try Zed with GitHub Copilot. I\u2019ve been using it this week with better results than I ever had with Cursor. There\u2019s even a low token \u201cMAI-Code-1-Flash\u201d model which has been giving me better results than any Composer model I used to use and the tokens used seem to be way less. I asked it today to fix a non-simple bug and MAI fixed it in one shot with less tha", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Grok 4.5"}]}, {"label": "Ownership concerns", "summary": "Some users are preparing to leave or have left since xAI/SpaceX bought Cursor.", "quotes": [{"id": 805095120, "item_id": 50318445, "url": "https://news.ycombinator.com/item?id=50318445", "by": "arendtio", "date": "2026-10-31", "stance": "recommend", "quote": "In general, I am pretty happy with Cursor", "excerpt": "I used Cursor first, tried Claude Code, but went back to Cursor. In general, I am pretty happy with Cursor, but given Elon's talent for ruining things, I am currently preparing for an exit. It is not because I don't like Cursor or have found something better, just because I see things like no OpenAI models going forward, a push for Grok, and the stuff that xAI did in the past. Before Cursor, I used vim + tmux.", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Backdoor in Claude Code for VS Code extension on the Cursor Marketplace"}, {"id": 788399393, "item_id": 49274962, "url": "https://news.ycombinator.com/item?id=49274962", "by": "calldacopsidgaf", "date": "2026-08-12", "stance": "warn", "quote": "if you're looking to get off of Cursor since X.ai bought them", "excerpt": "Literal trash for nazis. By the way if you're looking to get off of Cursor since X.ai bought them, I switched to Zed a few weeks ago and out-of-the-box it does everything Cursor can without charging you their dumbass premium. The transition is pretty much seamless", "context": "", "use_case": "code editing", "switched_from": "", "story": "Grok 4.6"}, {"id": 804849440, "item_id": 50303090, "url": "https://news.ycombinator.com/item?id=50303090", "by": "darkwi11ow", "date": "2026-10-30", "stance": "recommend", "quote": "Cursor was the market leader in LLM-assisted IDE experience before SpaceX acquisition", "excerpt": "There is no alternative really. Cursor was the market leader in LLM-assisted IDE experience before SpaceX acquisition, though Elon nerfed the product a lot in recent months. And there is still no good alternative to it. Google tries to compete via Antigravity, but that also uses OpenVSX. I myself use Cursor and use Claude there installed via OpenVSX, and was not affected only thanks to my laziness (I saw upgrade butt", "context": "", "use_case": "AI-assisted IDE", "switched_from": "", "story": "Backdoor in Claude Code for VS Code extension on the Cursor Marketplace"}]}, {"label": "Clunky UX", "summary": "Some users find it clunky, dislike its shortcut hijacking, or dislike the agent-first V3 update.", "quotes": [{"id": 791814531, "item_id": 49488408, "url": "https://news.ycombinator.com/item?id=49488408", "by": "aws_ls", "date": "2026-08-29", "stance": "warn", "quote": "stopped using it due to clunkiness", "excerpt": "I code using Codex or sometimes ClaudeCode. I use Zed to review the code. CLI is great for most things. Some times, when I am reviewing a PR, I just tell Codex to do a diff between source and target branches in PR, and generate a HTML report. Then I read that, and also review relevant pieces of code in Zed. I tried using Cursor, many of my colleagues use it, but stopped using it due to clunkiness. And of late, even i", "context": "", "use_case": "", "switched_from": "", "story": "Our decision on Cursor following its acquisition by SpaceX"}, {"id": 786187328, "item_id": 49136708, "url": "https://news.ycombinator.com/item?id=49136708", "by": "murlax", "date": "2026-08-01", "stance": "warn", "quote": "When Cursor hijacked literally every CMD key combo, I got fed up", "excerpt": "This is basically what I did. In 2023 I moved from VS Code to Cursor. And in 2025 when Opus 4.7 (or was it 4.6?) did that big leap in December, I switched to Claude Code and VSCode for any edits. I come from Sublime Text so those shortcuts are hardwired in me (which was also the defaults in VSCode). When Cursor hijacked literally every CMD key combo, I got fed up and switched back to VSCode. Maybe I should just go ba", "context": "", "use_case": "code editor", "switched_from": "", "story": "Cursor removed cost information from the usage page and CSV export"}, {"id": 777052064, "item_id": 48565754, "url": "https://news.ycombinator.com/item?id=48565754", "by": "esalman", "date": "2026-06-16", "stance": "warn", "quote": "I used Cursor for a couple of days and then went back to VS Code, largely due to Cursor pushing agentic first approach with V3 update.", "excerpt": "I work at a 20k-employee company with footprint in tech. A couple of weeks ago a decision was made to not renew Cursor license. This week it was made public and has been greeted with groans. Some employees have been publicly saying how ineffective and unproductive they are going to become due to this decision- which actually strikes me as really naive. Personally I like to use a stable IDE. I used Cursor for a couple", "context": "works at a 20k-employee company", "use_case": "IDE", "switched_from": "", "story": "SpaceX to buy Cursor AI coding agent operator Anysphere for $60B"}]}, {"label": "Claude Code integration", "summary": "No ACP support, and using Claude Code via plugin is a UX downgrade.", "quotes": [{"id": 786197200, "item_id": 49137325, "url": "https://news.ycombinator.com/item?id=49137325", "by": "RussianCow", "date": "2026-08-01", "stance": "recommend", "quote": "none of them feel nearly as polished as Cursor", "excerpt": "They're not as good. I've tried all the options available a couple months ago, and none of them feel nearly as polished as Cursor. For one thing, Cursor Tab is just far better than any other \"next edit\" prediction I've used. I also happen to like their agent UI the most, but they don't support ACP, so you can't use it with Claude Code, which was a deal-breaker for me. These days I've switched to Zed, which is good en", "context": "", "use_case": "IDE with next-edit prediction", "switched_from": "", "story": "Cursor removed cost information from the usage page and CSV export"}, {"id": 777043600, "item_id": 48565225, "url": "https://news.ycombinator.com/item?id=48565225", "by": "dmix", "date": "2026-06-16", "stance": "recommend", "quote": "I use Cursor with the Claude code plugin because Cursors autocomplete is really good", "excerpt": "I use Cursor with the Claude code plugin because Cursors autocomplete is really good and I like the way Cursor is set up. But it\u2019s definitely a UX downgrade using a plugin instead of the builtin Cursor agent stuff which I do miss. Claude with Max are just a safer bet economically these days than a cursor plan. I except that model and pricing gap to narrow over time though", "context": "", "use_case": "autocomplete and editor", "switched_from": "", "story": "SpaceX Is Buying Cursor"}]}, {"label": "Unclear value", "summary": "Some users who now work with CLI agents question what Cursor still adds.", "quotes": [{"id": 786170784, "item_id": 49135674, "url": "https://news.ycombinator.com/item?id=49135674", "by": "aroman", "date": "2026-08-01", "stance": "warn", "quote": "Can someone help me understand what value cursor offers in 2026?", "excerpt": "I was an early and passionate adopter and paying customer of Cursor (since 2023!), but it\u2019s probably been 6 months since I opened it. These days I \u201cwrite\u201d code with claude code and codex, and read/review it on GitHub. If I need to read it locally, I use a plain text editor. Can someone help me understand what value cursor offers in 2026?", "context": "early paying Cursor customer since 2023", "use_case": "code editing", "switched_from": "", "story": "Cursor removed cost information from the usage page and CSV export"}, {"id": 786175091, "item_id": 49135943, "url": "https://news.ycombinator.com/item?id=49135943", "by": "leonvoss", "date": "2026-08-01", "stance": "warn", "quote": "I don't think it offers any.", "excerpt": "I don't think it offers any. I got tired of switching between Codex and Claude plus I wanted to start using glm and kimi so I switch to pi. Then I got tired of VSCode eating up battery and RAM so I moved to Neovim which has barely any efficiency downside anymore since most code is not written by hand and if you know how to use it well it was only maybe 10% less efficient than VSCode to begin with. I am not sure why a", "context": "", "use_case": "", "switched_from": "", "story": "Cursor removed cost information from the usage page and CSV export"}]}], "who": [{"by": "darkwi11ow", "context": "developer on a modern stack", "url": "https://news.ycombinator.com/item?id=50303416", "date": "2026-10-30"}, {"by": "boogiefromzk", "context": "built an agentic delegation scheme", "url": "https://news.ycombinator.com/item?id=50251451", "date": "2026-10-26"}, {"by": "vibepreflight", "context": "organization where no one writes code manually", "url": "https://news.ycombinator.com/item?id=50132397", "date": "2026-10-17"}, {"by": "ricalamino", "context": "senior frontend engineer seeking work", "url": "https://news.ycombinator.com/item?id=49977565", "date": "2026-10-06"}, {"by": "boltzmann-brain", "context": "Senior software engineer", "url": "https://news.ycombinator.com/item?id=49929994", "date": "2026-10-02"}, {"by": "ymarkov", "context": "cofounder and CTO hiring", "url": "https://news.ycombinator.com/item?id=49925202", "date": "2026-10-01"}, {"by": "nmekala35", "context": "software engineer", "url": "https://news.ycombinator.com/item?id=49836271", "date": "2026-09-24"}, {"by": "andsoitis", "context": "Cursor user", "url": "https://news.ycombinator.com/item?id=49789807", "date": "2026-09-21"}, {"by": "mohamedkoubaa", "context": "works in simulation software", "url": "https://news.ycombinator.com/item?id=49651276", "date": "2026-09-10"}, {"by": "wiggin77", "context": "hiring for Mattermost", "url": "https://news.ycombinator.com/item?id=49530116", "date": "2026-09-02"}, {"by": "thefourthchime", "context": "uses Cursor for work account", "url": "https://news.ycombinator.com/item?id=49494598", "date": "2026-08-30"}, {"by": "zxspectrum1982", "context": "employee whose company pushes direct vendor tools", "url": "https://news.ycombinator.com/item?id=49490294", "date": "2026-08-29"}], "tags": ["for multi-model workflows", "for side projects", "for small teams", "for daily heavy coding"], "use_cases": ["ai coding", "coding", "daily coding", "ai-assisted coding", "ai-assisted development", "ai coding at work"], "compared": [{"slug": "claude-code", "name": "Claude Code", "co": 147, "switched_from": 3, "switched_to": 22}, {"slug": "codex", "name": "Codex", "co": 74, "switched_from": 2, "switched_to": 10}, {"slug": "claude", "name": "Claude", "co": 60, "switched_from": 0, "switched_to": 1}, {"slug": "claude-opus", "name": "Claude Opus", "co": 37, "switched_from": 1, "switched_to": 1}, {"slug": "zed", "name": "Zed", "co": 23, "switched_from": 0, "switched_to": 6}, {"slug": "visual-studio-code", "name": "Visual Studio Code", "co": 27, "switched_from": 0, "switched_to": 3}, {"slug": "github-copilot", "name": "GitHub Copilot", "co": 22, "switched_from": 1, "switched_to": 1}, {"slug": "composer", "name": "Composer", "co": 22, "switched_from": 0, "switched_to": 0}], "makers": [{"id": 761904752, "item_id": 47619047, "url": "https://news.ycombinator.com/item?id=47619047", "by": "jonasnelle", "date": "2026-04-02", "stance": "neutral", "quote": "We recommend using our official AppImage from https://cursor.com/download", "excerpt": "Hey, sorry about that! Some AUR packages share cursor in a way that isn't forward+backwards compatible across releases. We recommend using our official AppImage from https://cursor.com/download Alternatively, please use a different AUR package that doesn't have these issues https://aur.archlinux.org/packages/cursor-nightly-bin", "context": "Cursor team member", "use_case": "AI code editor", "switched_from": "", "story": "Cursor 3"}, {"id": 753834898, "item_id": 47114681, "url": "https://news.ycombinator.com/item?id=47114681", "by": "stared", "date": "2026-02-22", "stance": "neutral", "quote": "I used GPT 5.2 Codex in Cursor for decompiling an old game", "excerpt": "To be honest, it is also our surprise. I mean, I used GPT 5.2 Codex in Cursor for decompiling an old game and it worked (way better than Claude Code with Opus 4.5). We tested for Opus 4.6, but waiting for public API to test on GPT 5.3 Codex. At the same time, various task can be different, and now all things that work the best end-to-end are the same as ones that are good for a typical, interactive workflow. We used ", "context": "", "use_case": "running Codex for decompiling", "switched_from": "", "story": "We hid backdoors in ~40MB binaries and asked AI + Ghidra to find them"}], "threads": [{"url": "https://news.ycombinator.com/item?id=48554215", "title": "SpaceX Is Buying Cursor", "mentions": 21}, {"url": "https://news.ycombinator.com/item?id=48553224", "title": "SpaceX to buy Cursor AI coding agent operator Anysphere for $60B", "mentions": 19}, {"url": "https://news.ycombinator.com/item?id=47618084", "title": "Cursor 3", "mentions": 16}, {"url": "https://news.ycombinator.com/item?id=49486172", "title": "Our decision on Cursor following its acquisition by SpaceX", "mentions": 11}, {"url": "https://news.ycombinator.com/item?id=47388646", "title": "Ask HN: How is AI-assisted coding going for you professionally?", "mentions": 9}, {"url": "https://news.ycombinator.com/item?id=47501690", "title": "Ask HN: $50 monthly budget, which coding models would you recommend now?", "mentions": 5}], "sentiment_by_month": {"2025-11": {"warn": 1, "recommend": 7, "neutral": 9}, "2025-12": {"recommend": 10, "neutral": 5, "warn": 7}, "2026-01": {"neutral": 12, "recommend": 11, "compare": 2, "warn": 2}, "2026-02": {"recommend": 7, "neutral": 15, "warn": 2, "compare": 1}, "2026-03": {"warn": 5, "neutral": 15, "recommend": 8, "compare": 2}, "2026-04": {"recommend": 13, "warn": 7, "compare": 1, "neutral": 8}, "2026-05": {"recommend": 7, "warn": 3, "neutral": 3, "compare": 1}, "2026-06": {"neutral": 23, "recommend": 25, "warn": 10, "compare": 1}, "2026-07": {"neutral": 12, "recommend": 7, "warn": 1}, "2026-08": {"warn": 6, "recommend": 15, "neutral": 17, "compare": 2}, "2026-09": {"recommend": 10, "compare": 1, "neutral": 10}, "2026-10": {"neutral": 9, "recommend": 5}}, "quotes": [{"id": 805095120, "item_id": 50318445, "url": "https://news.ycombinator.com/item?id=50318445", "by": "arendtio", "date": "2026-10-31", "stance": "recommend", "quote": "In general, I am pretty happy with Cursor", "excerpt": "I used Cursor first, tried Claude Code, but went back to Cursor. In general, I am pretty happy with Cursor, but given Elon's talent for ruining things, I am currently preparing for an exit. It is not because I don't like Cursor or have found something better, just because I see things like no OpenAI models going forward, a push for Grok, and the stuff that xAI did in the past. Before Cursor, I used vim + tmux.", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Backdoor in Claude Code for VS Code extension on the Cursor Marketplace"}, {"id": 804930177, "item_id": 50308136, "url": "https://news.ycombinator.com/item?id=50308136", "by": "satellites", "date": "2026-10-30", "stance": "neutral", "quote": "Cursor was the first AI coding tool I used that had a \"wow\" factor", "excerpt": "Cursor was the first AI coding tool I used that had a \"wow\" factor and got me to switch over from typing out most of my code to having AI write most of it. But then when I used Claude Code for the first time, I never went back to Cursor. I can see the value in a world where you still want to be a bit more hands-on with your code, but that didn't feel worth paying for anymore. Now if I want to be hands-on I actually p", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Backdoor in Claude Code for VS Code extension on the Cursor Marketplace"}, {"id": 804854656, "item_id": 50303416, "url": "https://news.ycombinator.com/item?id=50303416", "by": "darkwi11ow", "date": "2026-10-30", "stance": "recommend", "quote": "Cursor comes very convenient to have all three in a single interface", "excerpt": "Well for me, as developer on a modern stack, there is always some risk involved. If not from agentic tools, then the package registries are compromised left and right, so it all comes down to mitigating the risk. I use Claude, Codex and Cursor/SpaceX agents, and Cursor comes very convenient to have all three in a single interface. Also I still code manually especially when prototyping, so having an IDE helps with it ", "context": "developer on a modern stack", "use_case": "unified AI coding IDE", "switched_from": "", "story": "Backdoor in Claude Code for VS Code extension on the Cursor Marketplace"}, {"id": 804849440, "item_id": 50303090, "url": "https://news.ycombinator.com/item?id=50303090", "by": "darkwi11ow", "date": "2026-10-30", "stance": "recommend", "quote": "Cursor was the market leader in LLM-assisted IDE experience before SpaceX acquisition", "excerpt": "There is no alternative really. Cursor was the market leader in LLM-assisted IDE experience before SpaceX acquisition, though Elon nerfed the product a lot in recent months. And there is still no good alternative to it. Google tries to compete via Antigravity, but that also uses OpenVSX. I myself use Cursor and use Claude there installed via OpenVSX, and was not affected only thanks to my laziness (I saw upgrade butt", "context": "", "use_case": "AI-assisted IDE", "switched_from": "", "story": "Backdoor in Claude Code for VS Code extension on the Cursor Marketplace"}, {"id": 804513888, "item_id": 50282118, "url": "https://news.ycombinator.com/item?id=50282118", "by": "teach", "date": "2026-10-28", "stance": "recommend", "quote": "Not surprising that Cursor is better at charging money for something that isn't an ad.", "excerpt": "Yeah I was using Argon in Cursor on launch day and it's become my daily driver for anything requiring moderate smarts or lots of prose. Not surprising that Cursor is better at charging money for something that isn't an ad.", "context": "", "use_case": "accessing models", "switched_from": "", "story": "Gemini 4 Carbon"}, {"id": 804444467, "item_id": 50277779, "url": "https://news.ycombinator.com/item?id=50277779", "by": "nater5000", "date": "2026-10-28", "stance": "neutral", "quote": "we use Cursor at work, so it was just a matter of picking a different model for me", "excerpt": "For what it's worth: Argon is a pretty good model, and this is coming from someone who just sticks with Opus 5.5 mostly across the board. For the current introductory price, it provides an exceptional value. Looks like they're trying to release Carbon (which is apparently a significant improvement) at the same price as Argon, which would be a crazy value. It's worth trying if you have easy access to it (we use Cursor", "context": "", "use_case": "AI coding at work", "switched_from": "", "story": "Gemini 4 Carbon"}, {"id": 804037527, "item_id": 50252345, "url": "https://news.ycombinator.com/item?id=50252345", "by": "xp84", "date": "2026-10-26", "stance": "neutral", "quote": "Open on my desktop right now: Slack, Outlook, Zoom, Windows Terminal, Edge, Claude, Obsidian, whatever the Windows image viewer is called, Cursor, and VS Code", "excerpt": "> I use lots Oh really? I, sadly, use nearly none. Open on my desktop right now: Slack, Outlook, Zoom, Windows Terminal, Edge, Claude, Obsidian, whatever the Windows image viewer is called, Cursor, and VS Code. Only the last 2 have menu bars. And I can\u2019t be certain that I didn\u2019t dig through the preferences of one or both of them when I first installed them to tell them to knock off the bullshit and give me back the m", "context": "", "use_case": "code editing", "switched_from": "", "story": "Oldest GUI application that still runs on Windows 11"}, {"id": 804023220, "item_id": 50251451, "url": "https://news.ycombinator.com/item?id=50251451", "by": "boogiefromzk", "date": "2026-10-26", "stance": "neutral", "quote": "I also made sure Opus controls Grok in Cursor", "excerpt": "Last months I was searching for a way to make smart AI model submit and verify the work to cheap model so that it will cost less, and after many try and failures I was able to get stable result where I use Fable and its limits spent slower than overall account limit because most context intensive work is done by Sonnet. At the same time the response quaility is still Fable. I also made sure Opus controls Grok in Curs", "context": "built an agentic delegation scheme", "use_case": "AI coding", "switched_from": "", "story": "Cost-effective agentic delegation scheme for Claude Code, Cursor and Codex"}, {"id": 802118352, "item_id": 50132397, "url": "https://news.ycombinator.com/item?id=50132397", "by": "vibepreflight", "date": "2026-10-17", "stance": "neutral", "quote": "We use cursor and stay mainly in the Agent window crafting prompts and validating functionality.", "excerpt": "None in our organization are writing code anymore. We use cursor and stay mainly in the Agent window crafting prompts and validating functionality. Even code review has been handed over to code review agents. The amount of code being written nowadays by agents too overwhelming. It is impossible for developers to review all code manually at this point.", "context": "organization where no one writes code manually", "use_case": "AI-driven code writing", "switched_from": "", "story": "Ask HN: How much are developers trusting LLMs to write prod code?"}, {"id": 801199075, "item_id": 50074942, "url": "https://news.ycombinator.com/item?id=50074942", "by": "josefchen", "date": "2026-10-13", "stance": "neutral", "quote": "I use quite a few coding agents (Claude Code, Codex, Cursor, ...)", "excerpt": "Hey HN - I use quite a few coding agents (Claude Code, Codex, Cursor, ...) and often several of them concurrently, so it can be hard to keep track of which agent is waiting for me. So I built Muster. Press \u2325Tab and it'll show you agents that are waiting for you first, agents that are still going second, and agents that finished recently last. Release \u2325 on one, it'll bring up Claude's app, Codex's threads page, Cursor", "context": "", "use_case": "coding agent", "switched_from": "", "story": "Show HN: Muster, a Mac Menu Bar Switcher for Claude Code, Codex and Cursor"}, {"id": 800050416, "item_id": 50003151, "url": "https://news.ycombinator.com/item?id=50003151", "by": "disgruntledphd2", "date": "2026-10-08", "stance": "recommend", "quote": "I kinda like cursor, mostly because it provides a nice review UI and I can use whatever model I want.", "excerpt": "> Cursor is easily the worst experience I've had with an AI harness I kinda like cursor, mostly because it provides a nice review UI and I can use whatever model I want. Getting away from all the Claude-speak has been a revelation, and fortunately Anthropic helped me here by hyping up GLM 5.3. Like, if there's an open weight Fable competitor, then why wouldn't I use it?", "context": "", "use_case": "AI coding with code review UI", "switched_from": "", "story": "Docker Agent"}, {"id": 799641041, "item_id": 49977565, "url": "https://news.ycombinator.com/item?id=49977565", "by": "ricalamino", "date": "2026-10-06", "stance": "recommend", "quote": "Claude Code and Cursor daily", "excerpt": "Open to work: Senior / Staff Frontend Engineer (React, TypeScript, Next.js) \u2014 also Senior Full-Stack (frontend-heavy, Node.js). AI-native. Location: S\u00e3o Paulo, Brazil (UTC-3; full overlap with US Eastern/Central, workable overlap with EU) Remote: Yes, remote only. Eligible to work from Brazil for companies anywhere: worldwide, LATAM, US, EU. Contractor/B2B or EOR, no visa or sponsorship needed. Willing to relocate: N", "context": "senior frontend engineer seeking work", "use_case": "daily AI-assisted development", "switched_from": "", "story": "Ask HN: Who wants to be hired? (October 2026)"}, {"id": 799140418, "item_id": 49946276, "url": "https://news.ycombinator.com/item?id=49946276", "by": "wiggin77", "date": "2026-10-03", "stance": "neutral", "quote": "We use coding agents daily (Claude Code, Cursor, and others)", "excerpt": "Mattermost | Remote (US and Canada) | FT | Multiple roles Mattermost (https://mattermost.com) is an open-core collaboration and workflow automation platform for air-gapped, on-prem and private clouds. Our customers are in defense, intelligence, security and critical infrastructure, including the USAF and NASA. Y Combinator led our Series B, their largest open-source investment at the time. Both openings are full stac", "context": "", "use_case": "coding agents", "switched_from": "", "story": "Ask HN: Who is hiring? (October 2026)"}, {"id": 798879907, "item_id": 49929994, "url": "https://news.ycombinator.com/item?id=49929994", "by": "boltzmann-brain", "date": "2026-10-02", "stance": "neutral", "quote": "I use GPT, Codex, Claude, Cursor and other current tools extensively.", "excerpt": "Location: Austria, EU Remote: Yes, US/EU/UK/Global Technologies: Rust, Python, Go, Haskell, C++, TypeScript, JS, React, K8s, PHP, ... Code: https://github.com/cheater R\u00e9sum\u00e9/CV: ask Email: damianjobsites+hn@gmail.com AI-native Senior Software Engineer with 10+ years of hands-on experience building difficult systems in AI, fintech, high-performance APIs and crypto. \u2022 Part of original Tezos launch team - blockchain pro", "context": "Senior software engineer", "use_case": "day-to-day development", "switched_from": "", "story": "Ask HN: Who wants to be hired? (October 2026)"}, {"id": 798803233, "item_id": 49925202, "url": "https://news.ycombinator.com/item?id=49925202", "by": "ymarkov", "date": "2026-10-01", "stance": "neutral", "quote": "you already use Claude Code, Cursor or similar as part of how you work", "excerpt": "VOYGR (YC W26) | Founding Product Engineer | San Francisco | ONSITE | Full-time | $150K-$200K + 0.5%-2.0% equity I'm Yarik, cofounder and CTO. Before this I spent 20 years in tech with 10+ years running infra, ML and search teams at Google, Meta and Apple. We love maps and build location/businesses APIs for AI apps and agents. If ChatGPT tells you a restaurant is open and it actually closed in March, that's the probl", "context": "cofounder and CTO hiring", "use_case": "coding", "switched_from": "", "story": "Ask HN: Who is hiring? (October 2026)"}, {"id": 798618304, "item_id": 49913644, "url": "https://news.ycombinator.com/item?id=49913644", "by": "AlisaYoki", "date": "2026-09-30", "stance": "recommend", "quote": "I use Cursor, and in fact, their internal models are more than enough for me.", "excerpt": "I use Cursor, and in fact, their internal models are more than enough for me. Especially considering that Grok bot has recently been released; it has its own limits and also helps save Cursor tokens (by properly drafting technical specifications and making edits to tasks). I pay $60 per month for the subscription, sometimes $200 if there are a lot of technical tasks", "context": "", "use_case": "personal project inference", "switched_from": "", "story": "Ask HN: How are you getting inference for personal projects?"}, {"id": 798524305, "item_id": 49907769, "url": "https://news.ycombinator.com/item?id=49907769", "by": "yurishimo", "date": "2026-09-30", "stance": "neutral", "quote": "I do like how easy it is to use my work cursor sub and business chat gpt at the same time.", "excerpt": "Glad I'm not the only want to find it a bit janky/broken at times. They seem to constantly be pushing updates which is nice, but I treat it mostly as a black box. Anecdotally, I find the auto compaction (or what I assume is happening when the context magically drops) to be hit or miss. I do like how easy it is to use my work cursor sub and business chat gpt at the same time. Then I use nearly free cursor models for d", "context": "", "use_case": "cheap models for simple tasks", "switched_from": "", "story": "You said no MCP"}, {"id": 797811920, "item_id": 49863245, "url": "https://news.ycombinator.com/item?id=49863245", "by": "nmekala35", "date": "2026-09-27", "stance": "neutral", "quote": "Then I use plan mode in tools like Cursor or Claude to generate a detailed technical design.", "excerpt": "yeah. My rule of thumb has been to use LLMs to compress the distance between an idea and working software, but never outsource my understanding of how each piece or component fits together. For example, when I'm working on something, I intentionally don't use an LLM to break down the problem. I take the time doing that myself, including defining the implementation details and my style preferences. Then I use plan mod", "context": "", "use_case": "generating technical designs", "switched_from": "", "story": "How to keep enjoying programming in a world of LLMs"}, {"id": 797380336, "item_id": 49836271, "url": "https://news.ycombinator.com/item?id=49836271", "by": "nmekala35", "date": "2026-09-24", "stance": "recommend", "quote": "I use Cursor pretty heavily", "excerpt": "Interesting idea for sure. But as a software engineer, I\u2019m struggling to map out what this would replace today. I use Cursor pretty heavily, but it\u2019s not entirely clear what would make me jump to a new IDE based on what you\u2019ve built so far. Maybe I\u2019m missing something.", "context": "software engineer", "use_case": "software engineering", "switched_from": "", "story": "Show HN: Whiteboard (YC W26) \u2013 An open-source IDE for thoughtful software design"}, {"id": 797044976, "item_id": 49815311, "url": "https://news.ycombinator.com/item?id=49815311", "by": "vorticalbox", "date": "2026-09-23", "stance": "neutral", "quote": "I use cursor and claude", "excerpt": "I use cursor and claude, its kinda annoying having to have the same skills in both so I made a ~/.agents/skills folder then ln both cursor and claude skills to point to that folder. which works except that claude uses .skills/synced which is uses to sync changes to skills from claude servers into the skills folder. every other agent I have used just directly syncs into .skills so it ends up duplicating skills", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Claude Code reads AGENTS.md only when telemetry is on [fixed]"}, {"id": 796636912, "item_id": 49789807, "url": "https://news.ycombinator.com/item?id=49789807", "by": "andsoitis", "date": "2026-09-21", "stance": "recommend", "quote": "that's what I as a Cursor user (what I use for dev, though I use ChatGPT for non-dev stuff) care about.", "excerpt": "Even if they could do that (workaround to include Astra in CursorBench), that has no practical consequences for Cursor users and that's what I as a Cursor user (what I use for dev, though I use ChatGPT for non-dev stuff) care about.", "context": "Cursor user", "use_case": "development", "switched_from": "", "story": "Grok 4.7"}, {"id": 796460224, "item_id": 49778764, "url": "https://news.ycombinator.com/item?id=49778764", "by": "andsoitis", "date": "2026-09-20", "stance": "recommend", "quote": "now I\u2019m finding Cursor is even better for my coding stuff.", "excerpt": "I moved from Claude Code to Codex for ROI and code quality reasons, and now I\u2019m finding Cursor is even better for my coding stuff. For non-coding LLM use cases ChatGPT is what I subscribe to now after I cancelled my Claude subscription because it found tge responses verbose, condescending. I have no loyalty, they all need to compete on quality and price and as a potential customer I think I\u2019m benefiting.", "context": "", "use_case": "coding", "switched_from": "Codex", "story": "Anthropic is cutting Claude Code's current weekly limits by 17%"}, {"id": 796342273, "item_id": 49771392, "url": "https://news.ycombinator.com/item?id=49771392", "by": "muzani", "date": "2026-09-20", "stance": "recommend", "quote": "The autocomplete itself is extremely good.", "excerpt": "I've moved to Codex lately, Astra does better with less bugs. When GPT does poorly, I use Cursor. The autocomplete itself is extremely good. And then there's Kimi code and similar which can't keep up with the existing demand, much less the demand if all other tools go down. Then Opencode, which would probably be a year or so behind SOTA but it's good enough.", "context": "", "use_case": "autocomplete", "switched_from": "", "story": "Ask HN: What happens when Claude Code goes away?"}, {"id": 795984800, "item_id": 49749050, "url": "https://news.ycombinator.com/item?id=49749050", "by": "eggplantemoji69", "date": "2026-09-18", "stance": "recommend", "quote": "I use $20 cursor plan and use the agent UI for prompts", "excerpt": "I use $20 cursor plan and use the agent UI for prompts, jetbrains ide for general file browsing + reviewing diffs. This has been my sweet spot to maintain understanding while still leveraging LLM benefits.", "context": "", "use_case": "agent prompting", "switched_from": "", "story": "Show HN: Share your AI Setup, Learn from others"}, {"id": 795807041, "item_id": 49737940, "url": "https://news.ycombinator.com/item?id=49737940", "by": "raunaksingwi", "date": "2026-09-17", "stance": "neutral", "quote": "I got the cursor subscription because I liked it's cloud coding environment better than the others.", "excerpt": "I have been using Grok models lately, just because I am on the cursor subscription. I got the cursor subscription because I liked it's cloud coding environment better than the others. But I am not liking them much. And they are extremely slow as well.", "context": "", "use_case": "coding", "switched_from": "", "story": "Ask HN: What default model do you use and why?"}, {"id": 795803299, "item_id": 49737706, "url": "https://news.ycombinator.com/item?id=49737706", "by": "raunaksingwi", "date": "2026-09-17", "stance": "neutral", "quote": "I use a lot of coding tools like claude, codex, cursor to code.", "excerpt": "I use a lot of coding tools like claude, codex, cursor to code. As the scope of work we give these agents keep increasing, the agents keep running for longer and longer, sometimes for hours.... I hate keeping my laptop cracked open all the time, on the train, in the coffee shop... I also hate when the agent keeps interrupting my work when it needs to use the browser... I realized, all AI coding agents must run 100% i", "context": "", "use_case": "coding", "switched_from": "", "story": "Ask HN: What are you working on? (September 2026)"}, {"id": 794776993, "item_id": 49673562, "url": "https://news.ycombinator.com/item?id=49673562", "by": "time0ut", "date": "2026-09-12", "stance": "recommend", "quote": "I prefer Cursor at this point just because of Composer.", "excerpt": "If I had to pick just one, these days it\u2019s Composer. It is just a cheap, fast, surgical workhorse. My workflow uses other models as well for various phases: Opus for planning, Sonnet for review, etc. I prefer Cursor at this point just because of Composer. Claude Code is passable but the lack of a good, fast, cheap workhorse sucks. Sonnet and Haiku aren\u2019t it. I also do like Codex and Sol, Terra, and Luna. They are dec", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Ask HN: What default model do you use and why?"}, {"id": 794743088, "item_id": 49671443, "url": "https://news.ycombinator.com/item?id=49671443", "by": "zero_shift", "date": "2026-09-12", "stance": "neutral", "quote": "I could use Cursor & Fable 5.1 to generate a decent text editor of my own", "excerpt": "I'm not going to criticise you for using Claude to build this. Honestly, for me as a consumer, it is a neutral thing provided the software is high quality What I would ask is this: why should I use your software when I could generate my own? For a relatively low cost in tokens, I could use Cursor & Fable 5.1 to generate a decent text editor of my own, if I constrained it to use high quality dependencies So this is ki", "context": "", "use_case": "generating own text editor", "switched_from": "", "story": "Txt: A fast, keyboard-driven terminal text editor for engineers"}, {"id": 794619954, "item_id": 49663747, "url": "https://news.ycombinator.com/item?id=49663747", "by": "phudyka", "date": "2026-09-11", "stance": "neutral", "quote": "I have also used Codex, Cursor and Gemini CLI.", "excerpt": "Location: France (CET) Remote: Yes, fully remote only (occasional travel/offsites fine) Willing to relocate: No Technologies: Flutter/Dart, Supabase (PostgreSQL, RLS, Deno Edge Functions), TypeScript, React, Next.js, Django, Angular, Docker, GitHub Actions, n8n R\u00e9sum\u00e9/CV: on request. linkedin.com/in/paul-hudyka, github.com/phudyka, phudyka.github.io Email: phudyka.dev@gmail.com Web and mobile developer. I ship produc", "context": "", "use_case": "", "switched_from": "", "story": "Ask HN: Who wants to be hired? (September 2026)"}, {"id": 794445041, "item_id": 49652815, "url": "https://news.ycombinator.com/item?id=49652815", "by": "princevegeta89", "date": "2026-09-11", "stance": "recommend", "quote": "Cursor is just killing it every other week.", "excerpt": "I used Windsurf for quite long and they're basically dead for now after they became Devin. Everything feels dull and they're always several features behind while Cursor is just killing it every other week. I'm back to VsCode plus Copilot Pro.", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Cognition launches new SWE-2 model, Rivaling Fable 5.1 and GPT-Astra"}, {"id": 794420418, "item_id": 49651276, "url": "https://news.ycombinator.com/item?id=49651276", "by": "mohamedkoubaa", "date": "2026-09-10", "stance": "neutral", "quote": "I use cursor so many of my sessions start in GPT and switch to Claude.", "excerpt": "I'm in the same field and I find GPT to be better at understanding physics conceptually but Claude is better at writing numerical code. I use cursor so many of my sessions start in GPT and switch to Claude.", "context": "works in simulation software", "use_case": "AI coding", "switched_from": "", "story": "Cognition launches new SWE-2 model, Rivaling Fable 5.1 and GPT-Astra"}, {"id": 793441680, "item_id": 49590105, "url": "https://news.ycombinator.com/item?id=49590105", "by": "Dmitry-kov", "date": "2026-09-06", "stance": "recommend", "quote": "in cursor i wasted less tokens while i do some tasks", "excerpt": "I use claude code and cursor. Interesting that I use opus 5 in cirsor and claude code, but in cursor i wasted less tokens while i do some tasks. During auto-tests runs, Claude code re-watch tasks and context before start my auto-test. In cursor this problem not reproduce. I use cursor most of the time.", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Portal by Spotify cut my Claude Code token usage by 90%"}, {"id": 792949536, "item_id": 49559346, "url": "https://news.ycombinator.com/item?id=49559346", "by": "reilly3000", "date": "2026-09-04", "stance": "neutral", "quote": "MCP is still the main way I use Cursor with enterprise systems like Glean, Jira, and Port.", "excerpt": "MCP is still the main way I use Cursor with enterprise systems like Glean, Jira, and Port. Other than that, everything, especially you GitHub, is moved to CLIs (+skills as needed)", "context": "", "use_case": "AI coding with enterprise systems", "switched_from": "", "story": "Ask HN: Who is using MCP in production?"}, {"id": 792880016, "item_id": 49555001, "url": "https://news.ycombinator.com/item?id=49555001", "by": "lacoolj", "date": "2026-09-03", "stance": "recommend", "quote": "I use Cursor daily and almost everything I do, highly complex or high volume, can be handled with Auto mode or Composer 2.5", "excerpt": "Jesus what are you doing that requires Sol usage so often? Terra not enough? I know Luna isn't reliable, so that's fair. Genuinely curious though, because I use Cursor daily and almost everything I do, highly complex or high volume, can be handled with Auto mode or Composer 2.5 (or Grok 4.6 High). So I have to assume you're doing something far more complex than what I am", "context": "", "use_case": "daily coding", "switched_from": "", "story": "OpenAI begins rolling out GPT-6 Astra"}, {"id": 792831361, "item_id": 49551960, "url": "https://news.ycombinator.com/item?id=49551960", "by": "darkwi11ow", "date": "2026-09-03", "stance": "neutral", "quote": "I use it in Cursor", "excerpt": "I use it in Cursor, recent versions are good for writing specs, code review, etc. Not good for UI design and broad research, though. Btw it does not have outage in Cursor now, it seems the infra path is different for XAI Grok and Cursor Grok.", "context": "", "use_case": "coding with Grok", "switched_from": "", "story": "Grok outage"}, {"id": 792829889, "item_id": 49551868, "url": "https://news.ycombinator.com/item?id=49551868", "by": "sergiotapia", "date": "2026-09-03", "stance": "neutral", "quote": "I use it in cursor for work", "excerpt": "I like grok 4.6 more than any anthropic or claude model. I use it in cursor for work, and grok cli for normal os operations/installations/troubleshooting. I also use grok on my phone for normal questions in the supermarket etc.", "context": "", "use_case": "work coding", "switched_from": "", "story": "Grok outage"}, {"id": 792546516, "item_id": 49534157, "url": "https://news.ycombinator.com/item?id=49534157", "by": "disgruntledphd2", "date": "2026-09-02", "stance": "neutral", "quote": "I use cursor, and have been giving them the same prompt and comparing", "excerpt": "Where does the secret sauce show up in the outputs, then? Like, (apart from tone), I find it hard to distinguish between the outputs of GPT/Claude/Kimi/GLM recently (I use cursor, and have been giving them the same prompt and comparing). If anything, I found that the non-Claude models were better in many cases, which definitely doesn't map to their pricing. > in fact not all the methods and data are public Probably n", "context": "", "use_case": "comparing models", "switched_from": "", "story": "Path to Astra: critical capabilities and frontier safeguards"}, {"id": 792544192, "item_id": 49534012, "url": "https://news.ycombinator.com/item?id=49534012", "by": "dan_voronov", "date": "2026-09-02", "stance": "compare", "quote": "AI coding tool evaluations (Cursor, Aider, Cline, Windsurf, etc.)", "excerpt": "I\u2019ve been researching how LLMs generate code since summer 2023. My main public artifact is this repository: https://github.com/danvoronov/CodeWithLLM-Updates It\u2019s a living research collection with 400+ commits covering practical experiments, usage patterns, step-by-step guides, model comparisons, AI coding tool evaluations (Cursor, Aider, Cline, Windsurf, etc.). A large part of my work is *exploratory*: navigating la", "context": "researching LLM code generation since 2023", "use_case": "AI coding tool evaluation", "switched_from": "", "story": "Ask HN: Who wants to be hired? (September 2026)"}, {"id": 792481858, "item_id": 49530116, "url": "https://news.ycombinator.com/item?id=49530116", "by": "wiggin77", "date": "2026-09-02", "stance": "recommend", "quote": "We use coding agents daily (Claude Code, Cursor, and others) for scaffolding, refactors, code review and test generation", "excerpt": "Mattermost | Remote (US and Canada) | FT | Multiple roles Mattermost (https://mattermost.com) is an open-core collaboration and workflow automation platform for air-gapped, on-prem and private clouds. Our customers are in defense, intelligence, security and critical infrastructure, including the USAF and NASA. Y Combinator led our Series B, their largest open source investment at the time. Both openings are full stac", "context": "hiring for Mattermost", "use_case": "scaffolding, refactors, code review", "switched_from": "", "story": "Ask HN: Who is hiring? (September 2026)"}, {"id": 792051888, "item_id": 49503243, "url": "https://news.ycombinator.com/item?id=49503243", "by": "ddxv", "date": "2026-08-30", "stance": "recommend", "quote": "I love using it for the chat question style", "excerpt": "I have to admit I'm not clear the difference? It starts with the list of your sessions/agents . Then starting a new \"agent\" or question or plan. I usually use each agent for a few questions or prompts at most. Occasionally it runs longer than that. I love using it for the chat question style where I ask it things like: For these frontend pages with X options collect the database tables for each. This is of course som", "context": "", "use_case": "codebase questions via chat", "switched_from": "", "story": "Our decision on Cursor following its acquisition by SpaceX"}, {"id": 791844704, "item_id": 49490294, "url": "https://news.ycombinator.com/item?id=49490294", "by": "zxspectrum1982", "date": "2026-08-29", "stance": "recommend", "quote": "I use Cursor at work and love it. It's a great IDE, the best IMHO.", "excerpt": "I use Cursor at work and love it. It's a great IDE, the best IMHO. But it becomes really expensive. Since the introduction of the Cursor Token Rate, my company tells us to use Claude and Codex directly with Anthropic (or Vertex AI) and OpenAI, respectively. https://cursor.com/docs/models-and-pricing#cursor-token-rate I'm now using Grok 4.6 most of the time. Sonnet some times. But that's it. Cursor-native models 99% o", "context": "employee whose company pushes direct vendor tools", "use_case": "work IDE", "switched_from": "", "story": "Our decision on Cursor following its acquisition by SpaceX"}, {"id": 791794672, "item_id": 49487167, "url": "https://news.ycombinator.com/item?id=49487167", "by": "rippeltippel", "date": "2026-08-29", "stance": "recommend", "quote": "The thing that keeps me using it is precisely the ability to switch between models", "excerpt": "I may be a rare Cursor user around here, but I am saddened by this news. The thing that keeps me using it is precisely the ability to switch between models: I usually do brainstorm/planning with Sol or Terra, then let Composer (free) deal with the implementation. For certain tasks I use Claude, which tends to be more expensive but sometimes saves me time. Using both OpenAI and Anthropic models, Cursor is cheaper than", "context": "", "use_case": "AI coding with multiple models", "switched_from": "", "story": "Our decision on Cursor following its acquisition by SpaceX"}, {"id": 788399393, "item_id": 49274962, "url": "https://news.ycombinator.com/item?id=49274962", "by": "calldacopsidgaf", "date": "2026-08-12", "stance": "warn", "quote": "if you're looking to get off of Cursor since X.ai bought them", "excerpt": "Literal trash for nazis. By the way if you're looking to get off of Cursor since X.ai bought them, I switched to Zed a few weeks ago and out-of-the-box it does everything Cursor can without charging you their dumbass premium. The transition is pretty much seamless", "context": "", "use_case": "code editing", "switched_from": "", "story": "Grok 4.6"}, {"id": 786197200, "item_id": 49137325, "url": "https://news.ycombinator.com/item?id=49137325", "by": "RussianCow", "date": "2026-08-01", "stance": "recommend", "quote": "none of them feel nearly as polished as Cursor", "excerpt": "They're not as good. I've tried all the options available a couple months ago, and none of them feel nearly as polished as Cursor. For one thing, Cursor Tab is just far better than any other \"next edit\" prediction I've used. I also happen to like their agent UI the most, but they don't support ACP, so you can't use it with Claude Code, which was a deal-breaker for me. These days I've switched to Zed, which is good en", "context": "", "use_case": "IDE with next-edit prediction", "switched_from": "", "story": "Cursor removed cost information from the usage page and CSV export"}, {"id": 784253904, "item_id": 49015869, "url": "https://news.ycombinator.com/item?id=49015869", "by": "subhobroto", "date": "2026-07-22", "stance": "warn", "quote": "That assumption is now a financial mishap waiting to happen as of today", "excerpt": "Cursor's \"Auto\", to me, used to mean \"cheap flat rate, don't worry which model ran\". That assumption is now a financial mishap waiting to happen as of today: 2026-07-22. Cursor just shipped \"Cursor Router\" [1]. Auto in the model picker is now three modes, no longer one: - Intelligence - frontier quality - Balance - \"daily driver\" frontier quality - Cost - the previous Auto routing, with fixed per-token prices (per Co", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Tell HN: Cursor Auto is no longer \"Auto\"! Let's welcome Auto Cost"}, {"id": 777084560, "item_id": 48567785, "url": "https://news.ycombinator.com/item?id=48567785", "by": "jemmyw", "date": "2026-06-17", "stance": "recommend", "quote": "now I use it for my personal projects. The plan is good value for accessing different sota models", "excerpt": "I didn't like cursor when it first came about but now I use it for my personal projects. The plan is good value for accessing different sota models occasionally for planning. Composer is actually really good, and fast. I'm not sure if it's because my personal projects are small enough I know them inside out and my work project is huge, but I prefer terminal code agents for day work over ide integration.", "context": "", "use_case": "personal projects, planning", "switched_from": "", "story": "SpaceX to buy Cursor AI coding agent operator Anysphere for $60B"}, {"id": 777069248, "item_id": 48566828, "url": "https://news.ycombinator.com/item?id=48566828", "by": "jackzhuo", "date": "2026-06-17", "stance": "warn", "quote": "I had stopped using Cursor since July 2025, because of its mess pricing policy.", "excerpt": "I had stopped using Cursor since July 2025, because of its mess pricing policy. Now I use codex & claude code & antigravity, and can not return to using Cursor.", "context": "", "use_case": "AI coding", "switched_from": "", "story": "SpaceX to buy Cursor AI coding agent operator Anysphere for $60B"}, {"id": 777039120, "item_id": 48564945, "url": "https://news.ycombinator.com/item?id=48564945", "by": "mjrbrennan", "date": "2026-06-16", "stance": "recommend", "quote": "the Cursor Tab autocompletion is still the best AI-based editor autocomplete I have used.", "excerpt": "Yes, I use it as my daily driver at Discourse, the Cursor Tab autocompletion is still the best AI-based editor autocomplete I have used. I switched to nvim earlier in the year because there was no real great AI integrations that didn't feel cumbersome, Cursor in vim mode is a much nicer experience, I like adding lines of code to agent context and so on. All of the extensions from VSCode, LSP integration, and so on ar", "context": "works at Discourse", "use_case": "daily driver editor", "switched_from": "", "story": "SpaceX Is Buying Cursor"}, {"id": 777035345, "item_id": 48564709, "url": "https://news.ycombinator.com/item?id=48564709", "by": "ghshephard", "date": "2026-06-16", "stance": "recommend", "quote": "the nice thing about Cursor - you can flick between models.", "excerpt": "You absolutely don't. I use all three products. My preference is Claude Code for my personal project. The one at work is kind of sandboxed off - but does have the benefit of an MCP for every enterprise service we have (Kibana, Victoria Metrics, Grafana, Jira, etc...) - which is nice. Over time - I expect Composer will be cheaper than Opus 4.8 - but the nice thing about Cursor - you can flick between models. And (this", "context": "", "use_case": "work coding with enterprise MCPs", "switched_from": "", "story": "SpaceX to buy Cursor AI coding agent operator Anysphere for $60B"}, {"id": 777024305, "item_id": 48564019, "url": "https://news.ycombinator.com/item?id=48564019", "by": "CSMastermind", "date": "2026-06-16", "stance": "warn", "quote": "Cursor was costing me $10k / month.", "excerpt": "> I was switching between Opus and GPT 5.x and was spending anywhere between $500-1000/month. I switched to Codex because Cursor was costing me $10k / month. If the price goes up by 4x I'm not sure the value will be there for a lot of people.", "context": "", "use_case": "coding agent", "switched_from": "", "story": "SpaceX Is Buying Cursor"}]}