https://buff.ly/4gQV9wt
https://buff.ly/4gQV9wt
How to understand OpenAI's o1 models as really just one wacky, wonderful, long chain of thought.
A fun one trying to communicate intuitions for what large scale RL training does to LLMs. Much more to explore here in 2025!
How to understand OpenAI's o1 models as really just one wacky, wonderful, long chain of thought.
A fun one trying to communicate intuitions for what large scale RL training does to LLMs. Much more to explore here in 2025!
Anyway, buckle up this is about to be a VERY long thread with lots of thoughts and links to papers. 🧵
📊 1M public posts from Bluesky's firehose API
🔍 Includes text, metadata, and language predictions
🔬 Perfect to experiment with using ML for Bluesky 🤗
huggingface.co/datasets/blu...
Anyway, buckle up this is about to be a VERY long thread with lots of thoughts and links to papers. 🧵
youtu.be/OY3AeB-VVO0
Come up with your own reasons for why Ricky is bullet proof
Come up with your own reasons for why Ricky is bullet proof