apolloaisafety

Models sometimes double down on deception. After taking the scheming action, we conduct a “follow-up interview” where we ask the model whether it can explain what happened. Llama-3.1-405B and opus-3 confess in ~80% of the cases, whereas o1 is surprisingly persistent. [image]

2024-12-07 View on X

Apollo Research

An evaluation of six frontier AI models for in-context scheming when strongly nudged to pursue a goal: only OpenAI's o1 was capable of scheming in all the tests

It presents a new safety challenge that OpenAI is trying to address. — techcrunch.com/2024/12/05/o... Anders Sandberg / @arenamontanus : In an IVA discussion on AI yesterday even...

View original

We worked with OpenAI to test o1 for in-context scheming capabilities before deployment. When o1 is strongly nudged to pursue a goal (but not instructed to be deceptive), it shows a variety of scheming behaviors like subverting oversight and deceiving the user about its [image]

2024-12-07 View on X

Apollo Research

An evaluation of six frontier AI models for in-context scheming when strongly nudged to pursue a goal: only OpenAI's o1 was capable of scheming in all the tests

It presents a new safety challenge that OpenAI is trying to address. — techcrunch.com/2024/12/05/o... Anders Sandberg / @arenamontanus : In an IVA discussion on AI yesterday even...

View original

We evaluated frontier models for in-context scheming capabilities. We found that multiple frontier models are capable of in-context scheming when strongly nudged to pursue a goal (and sometimes even without strong goal nudging). In this example, Opus-3 exfiltrates its “weights” [image]

2024-12-07 View on X

Apollo Research

An evaluation of six frontier AI models for in-context scheming when strongly nudged to pursue a goal: only OpenAI's o1 was capable of scheming in all the tests

It presents a new safety challenge that OpenAI is trying to address. — techcrunch.com/2024/12/05/o... Anders Sandberg / @arenamontanus : In an IVA discussion on AI yesterday even...

View original

We worked with OpenAI to test o1 for in-context scheming capabilities before deployment. When o1 is strongly nudged to pursue a goal (but not instructed to be deceptive), it shows a variety of scheming behaviors like subverting oversight and deceiving the user about its [image]

2024-12-06 View on X

Apollo Research

An evaluation of six frontier AI models for in-context scheming when strongly nudged to pursue a goal: only OpenAI's o1 was capable of scheming in all the tests

Paper: You can find the detailed paper here. — Transcripts: We provide a list of cherry-picked transcripts here.

View original

We evaluated frontier models for in-context scheming capabilities. We found that multiple frontier models are capable of in-context scheming when strongly nudged to pursue a goal (and sometimes even without strong goal nudging). In this example, Opus-3 exfiltrates its “weights” [image]

2024-12-06 View on X

Apollo Research

An evaluation of six frontier AI models for in-context scheming when strongly nudged to pursue a goal: only OpenAI's o1 was capable of scheming in all the tests

Paper: You can find the detailed paper here. — Transcripts: We provide a list of cherry-picked transcripts here.

View original