First screen, captured .
Looks similar
Extracting concepts from GPT-4(openai.com)
382 points by davidbarker | 127 comments
OpenAI research post describing scalable methods to decompose GPT-4's internal representations into 16 million interpretable features.
SimpleQA(openai.com)
216 points by surprisetalk | 76 comments
Learning to Reason with LLMs(openai.com)
1573 points by fofoz | 1186 comments
OpenAI research post introducing o1, a large language model trained with reinforcement learning to reason using a long internal chain of thought before answering.
