@sawyerhood they make good decisions. those forks were good decisions. idk why they would hide it if the license calls for attribution - it's not like we thought they trained the base model anyway. lmao
English
muzz khan
6.2K posts
guys they forked vscode. what did you expect?
Fynn@fynnso
was messing with the OpenAI base URL in Cursor and caught this accounts/anysphere/models/kimi-k2p5-rl-0317-s515-fast so composer 2 is just Kimi K2.5 with RL at least rename the model ID
English
is there a way to `ctrl + g` in open code to open my prompt in vim?
English
90% of my prompts for codex is just: yes, keep going, implement this.
English
@RhysSullivan ye. i use it for cloudwatch. don't think they have an sdk else i would move off the cli
English
@muzzdotdev @greptile I just want a better experience reviewing diffs
English
can somebody please fix ai code review please i hate this future most of the code sucks but also hard af to review with current tooling
(also github, please ffs stop breaking yourself every 2 min just stop where you are and don't touch the codebase please)
English
@Shreyassanthu77 @greptile greptile wouldve caught this, just saying
English
@muzzdotdev @greptile Lmao was so confused for a sec 😂
English
@Shreyassanthu77 @greptile is a must if your codebase has <1 people contributing
English
muzz khan がリツイート
@muzzdotdev @cursor_ai There is a whole other app hahahaha, when you enter for the first time you get prompted to open it on the left lower corner
English
am i on the right version?
Version: 2.7.0-pre.96.patch.0
VSCode Version: 1.105.1
Commit: c6712eb06f4e47a06a31f4d7adf484bfcbf61cc0
Date: 2026-03-19T17:53:17.088Z
Build Type: Stable
Release Track: Nightly
Electron: 39.8.1
Chromium: 142.0.7444.265
Node.js: 22.22.1
V8: 14.2.231.22-electron.0
OS: Darwin arm64 24.6.0
English
yeah this call was like me telling lebron that he's tall enough to play basketball
James Long@jlongster
late to this but when I was job searching and got stressed about something I talked to @threepointone and he was so supportive and uplifting (as always). very cool guy
English
we've been experimenting with getting rid of the bash tool
agents can write js fine which can do what bash can (though some gaps with things like git) and is more cross platform
and then could run that in this
Rivet@rivet_dev
Introducing the Secure Exec SDK Secure Node.js execution without a sandbox ⚡ 17.9 ms coldstart, 3.4 MB mem, 56x cheaper 📦 Just a library – supports Node.js, Bun, & browsers 🔐 Powered by the same tech as Cloudflare Workers $ 𝚗𝚙𝚖 𝚒𝚗𝚜𝚝𝚊𝚕𝚕 𝚜𝚎𝚌𝚞𝚛𝚎-𝚎𝚡𝚎𝚌
English
Clearly we need some kind of approval process to avoid the ability to open PRs for new accounts without a past GitHub contribution history and so forth. Here the problem is not LLM assisted programming per se, but agents around on the internet doing shit like that.
clem 🤗@ClementDelangue
Our biggest open-source repos are getting overwhelmed by AI slop which literally makes Github unusable (~a new pull request every 3 minutes). Fun new challenges in an agentic world!
English
Been a week since this and the popular libraries haven’t adopted yet. Genuinely, whats the holdup?
TANSTACK@tan_stack
You asked for TanStack skills, we built the whole pipeline. Introducing @tan_stack Intent (alpha) 📦 Ship agent-readable "skills" inside npm packages 🔍 Auto-discovered from node_modules 🔄 Knowledge sync with npm update 📂 Distributed - skills live in library repo 🧩 Composable - mix core + framework-specific skills 🌐 npm, pnpm, bun, yarn, deno No stale training data. Just npm install! 🔗 ⬇️🧵
English