321–330 of 410 posts
Claude code is the best so far, I am using the 200$ plan. in terms of feature matrix all tools are almost same with some hits and misses but speed is something which claude code wins.
I use Cursor as my base editor + Cline as my main agentic tool. I have not tried Windsurf so alas I can't comment here but the Cursor + Cline combo works brilliantly for me: * Cursor's Cmk-K edit-inline feature (with Claude 3.7 as my base model there) works brilliantly for "I just need this one line/method fixed/improved" * Cursor's tab-complete (neé SuperMaven) is great and better than any other I've used. * Cline w…
You need none of these fancy tools if you iterate over specs instead of iterating over code. I explain it all in here: https://www.cleverthinkingsoftware.com/spec-first-developmen...
That is slow and expensive.
You need none of these fancy tools if you iterate over specs instead of iterating over code. I explain it all in here: https://www.cleverthinkingsoftware.com/spec-first-developmen...
That is slow and expensive.
Earlier quoted context omitted.
This never accesses any extradata and works only when explicitly asked? I find terminal as most important part from privacy perspective and I haven’t tried any LLM integration yet…
It is intentionally non-agentic and only runs when invoked. For extradata it sends uname and the procname when it captures such as "nvim" or "ipython" and that's it.
git cloen blahalalhah
I did a ctrl+x x and it fixed it. I'm using openrouter/google/gemma-3-27b-it:free via chutes. Not a frontier model in the slightest.
Earlier quoted context omitted.
Same here. It's extremely distracting to see the random garbage that the autocomplete keeps trying to do. I said this in another comment but I'll repeat the question: where are these 2x, 10x or even 1.5x increases in output? I don't see more products, more features, less bugs or anything related to that since this "AI revolution". I keep seeing this being repeated ad nauseam without any real backing of hard evidence.…
I am but a small humble minority voice here but perhaps I represent a larger non-HN group: I am not a professional SWE; I am not fluent in C or Rust or bash (or even Typescript) and I don't use Emacs as my editor or tmux in the terminal; I am just a nerdy product guy who knows enough to code dangerously. I run my own small business and the software that I've written powers the entire business (and our website). I hav…
If I want to, let's say, create some code in a language I never worked on an LLM will definitely make me more "productive" by spewing out code for me way faster than I could write it. Same if I try to quickly learn about a topic I'm not familiar with. Especially if you don't care about the quality, maintainability, etc. too much.
But if I'm already a software developer with 15 years of experience dealing with technology I use every day, it's not going to increase my productivity in any meaningful way.
This is the dissonance I see with AI talk here. If you're not a software developer the things LLMs enable you to do are game-changers. But if you are a good software developer, in its best days it's a smarter autocomplete, a rubber-duck substitute (when you can't talk to a smart person) or a mildly faster google search that can be very inaccurate.
If you go from 0 to 1 that's literally infinitely better but if you go from 100 to 105, it's barely noticeable. Maybe everyone with these absurd productivity gains are all coming from zero or very little knowledge but for someone that's been past that point I can't believe these claims.
For daily work - neither. They basically promote the style of work where you end up with mediocre code that you don't fully understand, and with time the situation gets worse. I get much better result by asking specific question to a model that has huge context (Gemini) and analyzing the generated code carefully. That's the opposite of the style of work you get with Cursor or Windsurf. Is it less efficient? If you ar…
But how do you dump your entire code base into Gemini? Literally all I want is a good model with my entire code base in its context window.
Void. I'd rather run my own models locally https://voideditor.com/
Which model are you running locally? Is it faster than waiting for Claudes generation? What gear do you use?
Have a 3950X w/ 32GB ram, Radeon VII & 6900XT sitting in the closet hosting smaller models then a 5800X3D/128GB/7900XTX as my main machine.
Most any quantized model that fits in half of the vram of a single gpu (and ideally supports flash attention, optionally speculative decoding) will give you far faster autocompletes. This is especially the case with the Radeon VII thanks to the memory bandwidth.
I'm with Cursor for the simple reason it is in practice unlimited. Honestly the slow requests after 500 per month are fast enough. Will I stay with Cursor? No, ill switch the second something better comes along.