AI Researchers SHOCKED After OpenAI's New o1 Tried to Escape...

Thanks! Share it with your friends!

You disliked this video. Thanks for the feedback!

Added 1 month ago by admin

6 Views

The latest AI News. Learn about LLMs, Gen AI and get ready for the rollout of AGI. Wes Roth covers the latest happenings in the world of OpenAI, Google, Anthropic, NVIDIA and Open Source AI.

My Links ????
➡️ Subscribe: https://www.youtube.com/@WesRoth?sub_confirmation=1
➡️ Twitter: https://x.com/WesRothMoney
➡️ AI Newsletter: https://natural20.beehiiv.com/subscribe

#ai #openai #llm

The blog post:
https://www.apolloresearch.ai/research/scheming-reasoning-evaluations

Paper: read the full paper here:
https://static1.squarespace.com/static/6593e7097565990e65c886fd/t/6751eb240ed3821a0161b45b/1733421863119/in_context_scheming_reasoning_paper.pdf

Transcripts: We provide a list of cherry-picked transcripts here.
https://drive.google.com/drive/folders/1joO-VPbvWFJcifTPwJHyfXKUzguMp-Bk

System card: We worked with OpenAI to test o1 before public deployment.
You can find the results in the o1 system card.
https://openai.com/index/openai-o1-system-card/

00:00 o1 Lies, Tries to Escape
04:00 Frontier Models are Capable of In-Context Scheming
09:38 Scheming o1 Model
23:27 Scheming Evaluations
30:43 The FINAL Results