LESSWRONG
LW

James Baskerville

Message

7mo

Optimally Combining Probe Monitors and Black Box Monitors

Link to our arXiv paper "Combining Cost-Constrained Runtime Monitors for AI Safety" here: https://arxiv.org/abs/2507.15886. Code can be found here. Executive Summary * Monitoring AIs at runtime can help us detect and stop harmful actions. For cost reasons, we often want to use cheap monitors like probes to monitor all of...

Jul 27, 2025•52

James Baskerville

7mo

James Baskerville — LessWrong

James Baskerville

Message

7mo

Optimally Combining Probe Monitors and Black Box Monitors

Jul 27, 2025•52

James Baskerville

7mo

Optimally Combining Probe Monitors and Black Box Monitors

Tim Hua

Tim Hua, James Baskerville, BionicD0LPH1N, Mia Hopman, Aryan Bhatt, Tyler Tracy+ 0 more

Tim Hua, James Baskerville, BionicD0LPH1N, Mia Hopman, Aryan Bhatt, Tyler Tracy

7mo

Link to our arXiv paper "Combining Cost-Constrained Runtime Monitors for AI Safety" here: https://arxiv.org/abs/2507.15886. Code can be found here.

Executive Summary

Monitoring AIs at runtime can help us detect and stop harmful actions. For cost reasons, we often want to use cheap monitors like probes to monitor all of our outputs, and only escalate to more powerful and costly monitors if the probes detect something suspicious.
- For example, ChatGPT Agent uses a fast topic classifier to decide if queries are related to biology, while another reasoning model monitors for bio-misuse (pg 35)
We study how to efficiently combine multiple monitors with different performance and cost profiles into a single protocol.
- While existing studies often rely on heuristic

... (read 1785 more words →)