GPT-4 level open weights models like Llama-3-405B don't seem capable of dangerous cognition. OpenAI o1 demonstrates that a GPT-4 level model can be post-trained into producing useful long horizon reasoning traces. AlphaZero shows how capabilities can be obtained from compute alone, with no additional data. If there is a way of bringing these together, the apparent helplessness of the current generation of open weights models might prove misleading.

Post-training is currently a combination of techniques that use synthetic data and human labeled data. Human labeled data significantly improves quality, but its collection is slow and scales poorly. Synthetic data is an increasingly useful aspect of post-training, and automated aspects of its generation scale easily. Unlike weaker models, GPT-4 level LLMs clearly pass reading comprehension on most occasions, OpenAI o1 improves on this further. This suggests that at some point human data might become mostly unnecessary in post-training, even [...]

---

First published:
September 14th, 2024

Source:
https://www.lesswrong.com/posts/Rpc9ACd6zCy3FssTj/openai-o1-llama-4-and-alphazero-of-llms

---

Narrated by TYPE III AUDIO.

“OpenAI o1, Llama 4, and AlphaZero of LLMs ” by Vladimir_Nesov

LessWrong (30+ Karma)

“OpenAI o1, Llama 4, and AlphaZero of LLMs ” by Vladimir_Nesov