Gabriel Cassimiro

[Gabriel Cassimiro @GCassimiro17]

@swyx @aiDotEngineer ps: I'm the drummer

[Gabriel Cassimiro @GCassimiro17]

Jamming with @swyx on @aiDotEngineer!

[Pi @piesposi_to]

I built a Chrome extension that lets you save ChatGPT conversations in the [{"user": "something"}, {"assistant": "something" }] with CTRL + J.

Might be helpful if you want to train to transform conversations with ChatGPT into data to train your models.

https://t.co/IQeLMAJUGM

[Pierluca D'Oro @proceduralia]

Can reinforcement learning from AI feedback unlock new capabilities in AI agents?

Introducing Motif, an LLM-powered method for intrinsic motivation from AI feedback. Motif extracts reward functions from Llama 2's preferences and uses them to train agents with reinforcement learning.

On the complex NetHack game, Motif solves previously unsolved tasks without needing any expert demonstrations. Surprisingly, Motif's reward leads to better game score than the one obtained by using the score itself as a reward.

Given access to an event captioning mechanism, a few properties make Motif a general method:
• it is entirely based on open models
• the LLM doesn't need direct access to the environment dynamics (e.g., its source code)
• the LLM doesn't need to understand observation and action spaces

The best part? You can start using Motif right now, even on a small compute budget: the whole pipeline can take less than two GPU-days.

Feel free to read our paper and try our code out.
Paper: https://t.co/qHJqpJX6Gl
Code: https://t.co/aqDGr2LsXo
Blog post: https://t.co/ULDRodTcyK

Work co-lead by @MartinKlissarov and myself, with @shagunsodhani @robertarail @pierrelux Pascal Vincent @yayitsamyzhang @HenaffMikael

Learn more in the thread 🧵

[Sam Altman @sama]

we though we wanted flying cars and not 140/280 characters, but really we wanted 32000 tokens

[Marques Brownlee @MKBHD]

I just keep thinking this whole AI revolution actually adding value to things is making the crypto revolution seem dumber and dumber every day

[Lex Fridman @lexfridman]

Focus on things that matter.

[Gabriel Cassimiro @GCassimiro17]

@lexfridman The closer you get to the meaning
The sooner you'll know that you're dreaming

[Lex Fridman @lexfridman]

I'm watching the sunset, and am struck with the realization that I'm sitting on a habitable planet looking at a normal star that gave us some energy and somehow led to the origin of life, consciousness, and intelligence. How is any of this real 🤯

[Jim Fan @DrJimFan]

Hitchhiker’s map to AGI

[Marques Brownlee @MKBHD]

The crypto grift goes like this: https://t.co/oYNnYgP9Rr

[Elon Musk @elonmusk]

Hope you’re having a great day 1 2023!

One thing’s for sure, it won’t be boring.

[Pi @piesposi_to]

Opening AI with @Predogl is nice, but you know what is nicer?

Releasing a checkpoint of our model just like that: https://t.co/pkfkdu6woZ

Try it, dreambooth it, improve it, sell it, whatever. Have fun. This is just a small demo of what is to come.

Sample results attached.

1/n

[Google DeepMind @GoogleDeepMind]

How can AI begin to interact naturally with people?

Introducing a new framework where agents can improve their behaviour using human feedback. Tested in a virtual playhouse, agents can listen, ask questions and perform actions in real-time. https://t.co/zw5c9hmSLH

[Elon Musk @elonmusk]

Oh, you know, keeping busy …

[Elon Musk @elonmusk]

This is a battle for the future of civilization. If free speech is lost even in America, tyranny is all that lies ahead.

[Elon Musk @elonmusk]

Twitter is simply the most interesting place on the Internet. That’s why you’re reading this tweet right now.