Sign up to save your podcasts
Or
Share “Optimally Combining Probe Monitors and Black Box Monitors” by Tim Hua, jamesbaskerville, BionicD0LPH1N, Mia Hopman, Aryan Bhatt, Tyler Tracy
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
“Optimally Combining Probe Monitors and Black Box Monitors” by Tim Hua, jamesbaskerville, BionicD0LPH1N, Mia Hopman, Aryan Bhatt, Tyler Tracy
Link to our arXiv paper: https://arxiv.org/abs/2507.15886
TL, DR;: We study how to efficiently combine multiple monitors with different performance and cost profiles into a single protocol. When the number of monitors is small (2-4), one should simply brute force search over all monitor invocation strategies (i.e., which monitor to call first, when to call an additional monitor). For every strategy, apply the Neyman Pearson lemma and audit regions with the highest likelihood ratios _ell(m) = frac{P(M = m |text{Output is misaligned})}{P(M = m|text{Output is aligned})}_ . Measure the recall and pick the best one.
Example of an optimal way of combining monitors given some costs and budgetIn this example, you call your black box monitor only if the probe monitor score is between -0.01 and 2.18, and you audit everywhere with a log likelihood ratio above -0.32 (above the green line). This set of parameters achieves the [...]
---
Outline:
(01:16) Introduction
(02:49) Two example monitors
(04:26) Optimization problem with two monitors
(05:21) Picking where to audit given monitor calls
(08:59) Just brute force where to call monitors
(10:27) Summary:
(11:14) Some more examples
(12:10) Pareto Frontiers with two monitors v. only one monitor
---
First published:
July 27th, 2025
Source:
https://www.lesswrong.com/posts/FhixwyymPxF8TZX39/optimally-combining-probe-monitors-and-black-box-monitors
---
Narrated by TYPE III AUDIO.
---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.
View all episodes
By LessWrong Link to our arXiv paper: https://arxiv.org/abs/2507.15886
TL, DR;: We study how to efficiently combine multiple monitors with different performance and cost profiles into a single protocol. When the number of monitors is small (2-4), one should simply brute force search over all monitor invocation strategies (i.e., which monitor to call first, when to call an additional monitor). For every strategy, apply the Neyman Pearson lemma and audit regions with the highest likelihood ratios _ell(m) = frac{P(M = m |text{Output is misaligned})}{P(M = m|text{Output is aligned})}_ . Measure the recall and pick the best one.
Example of an optimal way of combining monitors given some costs and budgetIn this example, you call your black box monitor only if the probe monitor score is between -0.01 and 2.18, and you audit everywhere with a log likelihood ratio above -0.32 (above the green line). This set of parameters achieves the [...]
---
Outline:
(01:16) Introduction
(02:49) Two example monitors
(04:26) Optimization problem with two monitors
(05:21) Picking where to audit given monitor calls
(08:59) Just brute force where to call monitors
(10:27) Summary:
(11:14) Some more examples
(12:10) Pareto Frontiers with two monitors v. only one monitor
---
First published:
July 27th, 2025
Source:
https://www.lesswrong.com/posts/FhixwyymPxF8TZX39/optimally-combining-probe-monitors-and-black-box-monitors
---
Narrated by TYPE III AUDIO.
---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.
More shows like LessWrong (30+ Karma)
View all
Making Sense with Sam Harris
26,375 Listeners
Conversations with Tyler
2,424 Listeners
The Peter Attia Drive
8,934 Listeners
Sean Carroll's Mindscape: Science, Society, Philosophy, Culture, Arts, and Ideas
4,153 Listeners
ManifoldOne
92 Listeners
Your Undivided Attention
1,594 Listeners
All-In with Chamath, Jason, Sacks & Friedberg
9,907 Listeners
Machine Learning Street Talk (MLST)
90 Listeners
Dwarkesh Podcast
75 Listeners
Hard Fork
5,469 Listeners
The Ezra Klein Show
16,043 Listeners
Moonshots with Peter Diamandis
539 Listeners
No Priors: Artificial Intelligence | Technology | Startups
130 Listeners
Latent Space: The AI Engineer Podcast
95 Listeners
BG2Pod with Brad Gerstner and Bill Gurley
503 Listeners