I keep telling people that we are living in the golden age of AI - like the first year or two of google. It is all down hill as these companies push for profit and lock-in.
Which tools do Claude, Codex and Cursor choose? We measured 17k runs to find out
141–150 of 175 posts
Re: Which tools do Claude, Codex and Cursor choose? We measured 17k runs to find out
#142I keep telling people that we are living in the golden age of AI - like the first year or two of google. It is all down hill as these companies push for profit and lock-in.
Re: Which tools do Claude, Codex and Cursor choose? We measured 17k runs to find out
#143Re: Which tools do Claude, Codex and Cursor choose? We measured 17k runs to find out
#144I keep telling people that we are living in the golden age of AI - like the first year or two of google. It is all down hill as these companies push for profit and lock-in.
Re: Which tools do Claude, Codex and Cursor choose? We measured 17k runs to find out
#145Earlier quoted context omitted.
Actually, yes. Probably this https://github.com/anthropics/claude-code/issues/88041#issue...
The comments on this issue are unbearable.
Would be interesting to see LLMs talk in something more terse like Vietnamese.
Re: Which tools do Claude, Codex and Cursor choose? We measured 17k runs to find out
#146Re: Which tools do Claude, Codex and Cursor choose? We measured 17k runs to find out
#147Hey! Disclaimer: I am a Co-Founder of Armature (YC P26) which sells growth services to dev tools. This study is part of our broader work on how to influence coding agents choices and get products picked. To understand how agents pick tools we measured close to 17k sessions on an environment where agents run exactly like in the real world, on various repositories, talking to different personas (vibe-coder, junior or s…
> Claude Code rarely searches the web while Codex almost always does I’m trying to understand why they are opposite. I think it is true, I find myself giving a secondary prompt to Claude to “research this” and only then will it fetch. Codex is bang on fetching already.
Worth checking against your own permission settings before reading it as a model preference: allowlist a domain and the same agent will reach for it a lot more.
Re: Which tools do Claude, Codex and Cursor choose? We measured 17k runs to find out
#148Earlier quoted context omitted.
By not harassing projects with AI generated pull requests.
A pull request is a communication to the project. AI or no AI, a poorly communicated request is a burden. IMHO AI prs are fine as long as the submitter has done the work to refine that communication to make it easy to read and assess.
Re: Which tools do Claude, Codex and Cursor choose? We measured 17k runs to find out
#149Re: Which tools do Claude, Codex and Cursor choose? We measured 17k runs to find out
#150I keep telling people that we are living in the golden age of AI - like the first year or two of google. It is all down hill as these companies push for profit and lock-in.
How is this comment relevant and why is it the top post on this thread.