Vaibhav (VB) Srivastav

I did this. Fuck what anyone else says, just put the pedal to the metal and BUILD. Push spaghetti code. Nobody cares about OOPs. Doesn’t matter what anyone thinks. Just keep on doing. Document in public. Don’t listen to the haters. Release more than you refactor. Just keep pushing. Nobody cares, nobody notices, that’s the key, just fucking PUSH. That’s the way out, that’s what works, 100% times.

@antoine_chaffin @jxnlco Would love to collab, DM me please! 🙏

@0xBebis_ @jxnlco @uv it'll continue to thrive and get even more love!

@reach_vb @jxnlco What happens to @uv?

LETS GOOOO! So so psyched for this!! OpenAI really securing the future of Open Source! 🔥

@charliermarsh @rajko_rad Congratulations Charlie! It’s hard to imagine the current Python & Rust ecosystem without your and the teams efforts! Excited to work with you and the team @ OpenAI soon 🔥

We've entered into an agreement to join OpenAI as part of the Codex team. I'm incredibly proud of the work we've done so far, incredibly grateful to everyone that's supported us, and incredibly excited to keep building tools that make programming feel different.

reposting because the previous tweet went dead lol

Codex 🤝 India! So so excited about bringing the magic of Codex to India 🇮🇳 See some of you around India, soon!!

@asishcodes unfortunately not at the moment :|

@reach_vb Any chance of travel sponsorship?

Codex 🤝 India! So so excited about bringing the magic of Codex to India 🇮🇳 See some of you around India, soon!!

@rudrank yes - sign up! I'll be there in-person, would love to say hello! :)

Oh nice Codex hackathon in my city I should register

@awnihannun wow! massive congrats to both you and ant! 🔥

I joined Anthropic as a member of the technical staff. Excited to work on frontier modeling at a place with unwavering values and a generational mission.

@rudrank @Dimillian iirc it’s the same - except it uses the model that you invoke it with locally

@Dimillian @reach_vb Is the /review same as the code review that is on GitHub? I am out of credits lol and looking for ways to make the most out of the existing subscription “Audit harder” is not good enough

What is your best /deslop /simplify skill? I want to ensure the current diff doesn’t duplicate code, is readable and simple and fit in the codebase overall.

@rachpradhan brilliant work! would love to help support your work via codex for open source DMs open developers.openai.com/community/code…

I replaced FastAPI's entire HTTP core with Zig. Same decorator API. Same Pydantic models. 7× faster. 47,832 req/s vs FastAPI's 6,800. 2.09ms p50 latency. Introducing. TurboAPI. Here's the story..

@mert_gulsun @OpenAIDevs @nickbaumann_ @gabrielchua @OpenAI @UCBerkeley @BerkeleyHaas @irkadtunya 🔥🔥🔥

Honored to host the first Codex hackathon in Berkeley with @OpenAIDevs. Full house, great energy, and real (non-generic!) projects shipped. Huge thanks to Chris Egbunine and @nickbaumann_ for coming by, and @reach_vb and @gabrielchua for making everything possible. Top 3 🥁 (demos to follow): 🥇 Chimera, seamless overlay to embed learning into every webpage, Frank Junzhe He 🥈 GuardRail, deep red teaming for chatbots, Arda Hoke 🥉 California Solar Interconnection, live interconnection risk map, Tomás Coello & Tomas Diez Canedo Turns out, you can just build things. Huge thanks to Haas AI Club colleagues @theboyinatux @mj_kang and Jade Chen.

npm i -g @openai/codex

@ajambrosino subagent*

@dejavucoder it's a good model, would be interested to hear how your experience/ evals/ vibes with the models so far!

i had replaced all my gpt 5 mini calls with gemini flash 3 but looks like we have a new worthy candidate. i just gpt 5.4 mini has more predictable TTFT

@YinsenW_ @sama @OpenAIDevs Love to see it! Keep cooking!!

Thanks, Sam! Cherry Studio will stay open source and continue serving AI enthusiasts worldwide! @sama @OpenAIDevs

@natolambert I see, if you were to list top 3 things that feel off, what would they be? cc: @edbayes for vis too (btw you can also set themes in the app)

@reach_vb didnt know it existed, but I also think it extends into the product presentation / interface!

GPT 5.4 didn't get enough praise for how big of a step it was in OpenAI's agent arc. At the same time, with better context management, speed, rate limits, instruction following, code -- it's revealing that I still turn to the "warmth" of Claude. interconnects.ai/p/gpt-54-is-a-…