Alexander Pan on the MACHIAVELLI benchmark

The Inside View
26/07/2023 20 min

Listen "Alexander Pan on the MACHIAVELLI benchmark"

Descargar episodio Ver en sitio original

Episode Synopsis

I've talked to Alexander Pan, 1st year at Berkeley working with Jacob Steinhardt about his paper "Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark" accepted as oral at ICML.

Youtube: https://youtu.be/MjkSETpoFlY

Paper: https://arxiv.org/abs/2304.03279

More episodes of the podcast The Inside View

Owain Evans - AI Situational Awareness, Out-of-Context Reasoning 23/08/2024
[Crosspost] Adam Gleave on Vulnerabilities in GPT-4 APIs (+ extra Nathan Labenz interview) 17/05/2024
Ethan Perez on Selecting Alignment Research Projects (ft. Mikita Balesni & Henry Sleight) 09/04/2024
Emil Wallner on Sora, Generative AI Startups and AI optimism 20/02/2024
Evan Hubinger on Sleeper Agents, Deception and Responsible Scaling Policies 12/02/2024
[Jan 2023] Jeffrey Ladish on AI Augmented Cyberwarfare and compute monitoring 27/01/2024
Holly Elmore on pausing AI 22/01/2024
Podcast Retrospective and Next Steps 09/01/2024
Paul Christiano's views on "doom" (ft. Robert Miles) 29/09/2023
Neel Nanda on mechanistic interpretability, superposition and grokking 21/09/2023
© 2003-2025 ZARZA | AHEAD OF OUR TIME
privacy policy
In God we trust In God we trust
PreSales Questions? Click Here
or call our toll-free line at +1-888-5002068 Miami, Florida, USA