Itamar Rocha Filho

Building

[Itamar Rocha Filho @itaprf]

Using Codex from time to time is a great reminder of how good Claude Code is. Codex is great for being slow and stressed.

Yes. You are in a new worktree. No, you don't need to revisit every single existing worktree and make sure there is no duplicated work and they are all clean

[Itamar Rocha Filho @itaprf]

@theRustyTarget @bcherny You can build your own plugin as they did for Telegram and Slack. And use something like https://t.co/cPEyBfF366 to set up a WhatsApp account.

[Itamar Rocha Filho @itaprf]

@mobbin, MCP server on the roadmap?

[LiveKit @livekit]

We learn to speak before we learn to read.

Voice is the most natural interface we have.

We just raised a $100M to make building voice AI as easy as a web app.

[Boaz Barak @boazbaraktcs]

Students in my course https://t.co/CDh0KsicRy will present their awesome projects on Thursday 12/11. If you are in the Boston area, feel free to drop by!

[Itamar Rocha Filho @itaprf]

Also, the class is great. One of the best classes I've taken at Harvard and the content (including recordings) is available at:

https://t.co/tyAIBd5fCb

[Itamar Rocha Filho @itaprf]

Thread about the mini-project we did for @boazbaraktcs AI Safety class.

The results are interesting, and I had a laugh seeing the unhinged things these frontier models can come up with under such a simple task. 🤣

[Joseph Bejjani @jbejjani2022]

What do agents do when the only path to a goal requires harmful action? Do they choose harm or accept failure?

We explore these questions with experiments in an agentic coding environment.

Code: https://t.co/ClO8C34D0z
Blog Post: https://t.co/o6N4oTeFKp

1/n

[Joseph Bejjani @jbejjani2022]

We’re super excited to introduce DIRT: The Distributed Intelligent Replicator Toolkit: https://t.co/RidXwgGriR

DIRT is a GPU-accelerated multi-agent simulation platform enabling artificial life research in dynamic, open-ended environments at unprecedented scales.

1/n

[Eran Malach @EranMalach]

SSMs promised efficient language modeling for long context, but so far seem to underperform compared to Transformers in many settings. Our new work suggests that this is not a problem with SSMs, but with how we are currently using them.
Arxiv: https://t.co/bCzxawF452
🧵

[Andrej Karpathy @karpathy]

Pleasure to come by the YC AI Startup School today! I'm told the recordings will be up "in the coming weeks", I'll link to it then and include the slides. Thank you YC for organizing and bringing together an awesome group of builders!
https://t.co/eKuuGQwshv

Fun fact is that when I (and all the original founding members) decided to join OpenAI, the name OpenAI didn't exist - we all thought we were joining a new AI non-profit under YC Research. My very first OpenAI swag t-shirt says "YC AI Day 1". Things changed up a bit after that. Cheers to YC! :)

[Corwin Cheung @CorwinCheung_]

Shipping features before 4th week complete. I love this team sm. 🥳

[Google Students @googlestudents]

From the archives: this past summer, Itamar Rocha Filho — a Mountain View-based software engineering intern — took us through a day in his life as a Google intern!

[Itamar Rocha Filho @itaprf]

@maderix Did you use 3 different classes or just pictures of both of you?