@zackenton1 : Eventually, humans will need to supervise superhuman AI - but how? Can we study it now? We don't have superhuman AI, but we do have LLMs. We study protocols where a weaker LLM uses stronger ones to find better answers than it knows itself. Does this work? It’s complicated: 🧵👇 • TwiCopy

Zac Kenton

@zackenton1

+ Follow

Research Scientist in AI safety at DeepMind. Views are my own and don't represent DeepMind.

ID: 2487828968

linkhttps://zackenton.github.io/ calendar_today10-05-2014 12:20:29

183 Tweet

1,1K Followers

1,1K Following

Zac Kenton

@zackenton1

3 months ago

Eventually, humans will need to supervise superhuman AI - but how? Can we study it now? We don't have superhuman AI, but we do have LLMs. We study protocols where a weaker LLM uses stronger ones to find better answers than it knows itself. Does this work? It’s complicated: 🧵👇