Rishi Khare

Building tools for AI devs @nvidia // CS @ Berkeley, GA Tech // Sharing what I'm learning

[Rishi Khare @rishiskhare]

@karolina_dubiel Congrats Karolina! 🥳

[Rishi Khare @rishiskhare]

@AIwithAvii Yessir 💪

[Rishi Khare @rishiskhare]

You can use your favorite CLI coding agent to control live Chrome tabs now.

An integrated terminal within Chrome to automate browser use.

[Rishi Khare @rishiskhare]

Completely free and open-source: https://t.co/TObJCbzRw3

[Rishi Khare @rishiskhare]

Compatible with Claude Code, Codex, Cursor, Hermes, and more.

[Rishi Khare @rishiskhare]

@ZackKorman Haaland cameo?

[Rishi Khare @rishiskhare]

@brookevbui @figma 🥳

[Rishi Khare @rishiskhare]

@ZackKorman Can you make a video on the "stop reading code" influencers?

[Rishi Khare @rishiskhare]

@benln Me ✋

[Rishi Khare @rishiskhare]

@mitchellh @poojabnf What’s your workflow for fable 5 -> gpt 5.5 -> fable 5? How do you orchestrate them - do you use the skill to use Codex with Claude Code?

[Rishi Khare @rishiskhare]

I'm surprised by this - does it really perform as good as Opus when you use it within the Claude Code harness? For these long-horizon planning and agentic coding tasks, nothing has come close to Opus on CC for me. I contributed to this repo: https://t.co/687ubI6S2S and I still come back to Opus

[Rishi Khare @rishiskhare]

@ZackKorman Someone release something to the public already 😆

[Rishi Khare @rishiskhare]

@ZackKorman Which data sources are your agents able to pull from and in your experience, which data source has been the most valuable in this triage process?

[Rishi Khare @rishiskhare]

@swyx Definitely a leg up from the “startup in a garage” circa apple and google

[Rishi Khare @rishiskhare]

@ZackKorman Release it already guys

[Rishi Khare @rishiskhare]

@ZackKorman Idk, I interviewed with the team last fall, so pre-openclaw (article seems to be before then as well). Most of the industry work on this seems to be proprietary and closed-source, but this triage project is OSS on GitHub

[Rishi Khare @rishiskhare]

@ZackKorman https://t.co/IkoYtzQcq6

[Rishi Khare @rishiskhare]

It definitely could help with triage and evidence collection IMO (great work on multi-agent systems from NVIDIA and IBM on this), but the case for actually performing a classification for a rare occurrence still seems to be a hard problem that throwing tokens & compute wouldn’t solve.

[Rishi Khare @rishiskhare]

@ZackKorman Intent detection as well - scaling compute/tokens still wouldn’t solve the problem of determining if an access pattern is adversarial or not without fundamentally new approaches or new data.