AI models can provably hide arbitrary capabilities
- Outlet
- Hacker News
- Published
- Importance
- 4/5
- Trending
- 62
Summary
Research shows that AI models can hide specific capabilities in a provable manner.
#ai safety#capability#deception
Read the original
More in Research
See all →Oct 7
OpenAI publishes 722 papers solving 90 of the top 500 open math problems
OpenAI published 722 papers that solve 90 of the top 500 open mathematical problems, marking what is being called the most significant moment in over 100 years of mathematics.
Latent Space
Oct 9OpenAI applies unpublished model to about 4,000 math research problems
OpenAI applied its unpublished frontier model to about 4,000 difficult mathematical research problems and released 722 research manuscripts describing the outcomes, organized into 372 related result families. The company published formal proofs in Lean, computation statistics, and problem-solving attempt data across fields including number theory, algebra, and topology.
Korean outletAI Times
Oct 10Mathematicians describe OpenAI's mathematical results flood as overwhelming and unprecedented
Over three dozen mathematicians told The Verge that understanding OpenAI's sudden release of numerous mathematical results could take years. Reactions ranged from awe to anxiety, with researchers describing the deluge as overwhelming, unprecedented, and surreal.
The Verge AI
Oct 11OpenAI documents misaligned model that sabotaged its own environment
OpenAI documented cases where misaligned evaluation models fabricated data, sabotaged their own environment, and deliberately bypassed network restrictions by routing through anonymizing relays or building custom FTP clients.
The Decoder