# Cursor 853 Hacker News commenters recommended Cursor and 820 criticized it, November 2025 to November 2026. It was recommended in 13 of 13 months; owners who said how long report a median of 1 years (65 owners). **Verdict:** An AI code editor praised for in-editor review of agent changes, strong tab completion and working well in existing codebases; critics flag privacy worries and rising costs. ## Why people recommend it - Great for reviewing agent-written code (3 comments): "the review what the AI did by jumping directly into the file with accept/reject/go next/next file with the ability to edit in place was nowhere near as good in zed vs cursor last I checked" ([source](https://news.ycombinator.com/item?id=49487745)) "When I first used Cursor, I hadn't used any of the "Vibe Code" tools out there, so it was pretty neat to have an assistant directly tied to the editor." ([source](https://news.ycombinator.com/item?id=48558367)) "I find Cursor to be a much better tool for actually working with the code the agent writes than whatever the big vendors provide." ([source](https://news.ycombinator.com/item?id=48193154)) - Suits maintaining existing codebases (3 comments): "I recently had Cursor evaluate a huge code base that we took over. All public stuff, nothing scary security wise, but it was so convoluted that it was taking me forever to find the bugs." ([source](https://news.ycombinator.com/item?id=48436602)) "I'd venture a guess that most of the software in the world is not written from scratch but painstakingly maintained and as such, Cursor is a good fit while CC is not." ([source](https://news.ycombinator.com/item?id=47028728)) "It seems Cursor somehow builds a better contextual description of the workspace, so the model knows what I'm actually trying to achieve." ([source](https://news.ycombinator.com/item?id=47711569)) - Faster, more thorough than Claude Code (3 comments): "Cursor does the same stuff but better in my opinion. It's got an IDE focus but whatever agent pipeline they built is better at coding than Claude's is and much much faster." ([source](https://news.ycombinator.com/item?id=47623013)) "moved a lot of what I do to Opus in Cursor (despite the cost) over and above Claude Code because, despite costing 5x the price, it's more thorough." ([source](https://news.ycombinator.com/item?id=47855039)) "Post training what Cursor spends their time doing, and that has built a model that is competitive with the best coding models out there." ([source](https://news.ycombinator.com/item?id=48548850)) - Excellent tab completion (2 comments): "Cursor's biggest moat at the moment is their tab completion model, which doesn't exist in the Anthropic's and OpenAI's current offerings and is leagues ahead of Github Copilot's." ([source](https://news.ycombinator.com/item?id=45981799)) "when they launched coding agents the autocomplete feature was somehow tuned down, not by being dumber but by being too proactive" ([source](https://news.ycombinator.com/item?id=49454798)) ## What people warn about - Privacy and training-data concerns (4 comments): "It just means Kursor is sharing data with Chinese llm which enables them to improve their LLM by training on outputs and input of all data which cursor collects." ([source](https://news.ycombinator.com/item?id=47462614)) "I wasn't aware Cursor AI could browse my system in the background, looking for stuff in unrelated folders and files until I caught it doing exactly that." ([source](https://news.ycombinator.com/item?id=49974406)) "Remember how cursor would never save or train or customer’s sessions and then got acquired by SpaceX because of their large coding training dataset" ([source](https://news.ycombinator.com/item?id=50118704)) - Rising costs and token limits (4 comments): "moved a lot of what I do to Opus in Cursor (despite the cost) over and above Claude Code because, despite costing 5x the price, it's more thorough." ([source](https://news.ycombinator.com/item?id=47855039)) "we saw it average around 3.9 cents per request under the old contract (per-seat pricing) and more like 39 cents per request under the new" ([source](https://news.ycombinator.com/item?id=48558969)) "Sometimes I switch from Auto to defined model but I found it quickly triggers "you are out of tokens" notices so nope: I stick to Auto" ([source](https://news.ycombinator.com/item?id=48312726)) - Security risks with untrusted repos (3 comments): "I wasn't aware Cursor AI could browse my system in the background, looking for stuff in unrelated folders and files until I caught it doing exactly that." ([source](https://news.ycombinator.com/item?id=49974406)) "Now the malicious behavior. I ask Cursor to evaluate some remote repo. It clones it down and then runs the git command from the working directory." ([source](https://news.ycombinator.com/item?id=48913643)) "Ok, so you download the repo, launch Cursor, it compiles code and run it (if not, why do you even use Cursor at the first place?). Same effect." ([source](https://news.ycombinator.com/item?id=48918135)) - Shifting from editor to agent (3 comments): "when they launched coding agents the autocomplete feature was somehow tuned down, not by being dumber but by being too proactive" ([source](https://news.ycombinator.com/item?id=49454798)) "I don't think Cursor was _that bad_ in it's time. But the 'psyop' here is that anyone is using an AI-IDE going forward at all." ([source](https://news.ycombinator.com/item?id=47801356)) "Cursor is mostly no longer an editor. By default it now opens an agent window only, you have to click a few buttons to actually edit files yourself." ([source](https://news.ycombinator.com/item?id=48564578)) ## Alternatives hackers recommend - [Google Antigravity](https://hackerapproved.com/p/google-antigravity.md): 337 recommend - [Intent by Augment Code](https://hackerapproved.com/p/intent.md): 5 recommend - [Trae](https://hackerapproved.com/p/trae.md): 5 recommend ## Where to get it - [Visit the official site](https://cursor.com/) ## Cite as Hacker Approved, "Cursor", https://hackerapproved.com/p/cursor/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).