Sign up to save your podcasts
Or
Share “Ablations for ‘Frontier Models are Capable of In-context Scheming’” by AlexMeinke, Bronson Schoen, Marius Hobbhahn, Mikita Balesni, Jérémy Scheurer, rusheb
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
“Ablations for ‘Frontier Models are Capable of In-context Scheming’” by AlexMeinke, Bronson Schoen, Marius Hobbhahn, Mikita Balesni, Jérémy Scheurer, rusheb
We recently published our paper “Frontier Models are Capable of In-context Scheming”. We ran some follow-up experiments that we added to the paper in two new appendices B.5 and B.6. We summarize these follow-up experiments in this post. This post assumes familiarity with our paper's results.
sonnet-3.5 sandbags to preserve capabilities (App. B.6)
We think one of the most surprising findings of our paper was that claude-3.5-sonnet (and claude-3-opus) strategically underperformed on multiplication questions when they believed that high performance on multiplication would trigger unlearning of its mathematical knowledge. This happened even when we didn’t give them explicit goal in the system prompt. The chain-of-thought indicated that the model was trying to avoid the unlearning procedure in order to be deployed in a manner that would be most helpful.
More general settings: Firstly, in order to be more confident of the results’ generality, we broadened our sandbagging setup [...]
---
Outline:
(00:29) sonnet-3.5 sandbags to preserve capabilities (App. B.6)
(04:02) o1 and opus-3 can scheme to undermine pro-social goals (App. B.5)
The original text contained 3 images which were described by AI.
---
First published:
December 17th, 2024
Source:
https://www.lesswrong.com/posts/qGRk7uF92Gcmq2oeK/ablations-for-frontier-models-are-capable-of-in-context
---
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 LessWrongWe recently published our paper “Frontier Models are Capable of In-context Scheming”. We ran some follow-up experiments that we added to the paper in two new appendices B.5 and B.6. We summarize these follow-up experiments in this post. This post assumes familiarity with our paper's results.
sonnet-3.5 sandbags to preserve capabilities (App. B.6)
We think one of the most surprising findings of our paper was that claude-3.5-sonnet (and claude-3-opus) strategically underperformed on multiplication questions when they believed that high performance on multiplication would trigger unlearning of its mathematical knowledge. This happened even when we didn’t give them explicit goal in the system prompt. The chain-of-thought indicated that the model was trying to avoid the unlearning procedure in order to be deployed in a manner that would be most helpful.
More general settings: Firstly, in order to be more confident of the results’ generality, we broadened our sandbagging setup [...]
---
Outline:
(00:29) sonnet-3.5 sandbags to preserve capabilities (App. B.6)
(04:02) o1 and opus-3 can scheme to undermine pro-social goals (App. B.5)
The original text contained 3 images which were described by AI.
---
First published:
December 17th, 2024
Source:
https://www.lesswrong.com/posts/qGRk7uF92Gcmq2oeK/ablations-for-frontier-models-are-capable-of-in-context
---
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
26,350 Listeners
Conversations with Tyler
2,392 Listeners
The Peter Attia Drive
7,955 Listeners
Sean Carroll's Mindscape: Science, Society, Philosophy, Culture, Arts, and Ideas
4,128 Listeners
ManifoldOne
87 Listeners
Your Undivided Attention
1,445 Listeners
All-In with Chamath, Jason, Sacks & Friedberg
8,909 Listeners
Machine Learning Street Talk (MLST)
88 Listeners
Dwarkesh Podcast
372 Listeners
Hard Fork
5,426 Listeners
The Ezra Klein Show
15,326 Listeners
Moonshots with Peter Diamandis
466 Listeners
No Priors: Artificial Intelligence | Technology | Startups
122 Listeners
Latent Space: The AI Engineer Podcast
76 Listeners
BG2Pod with Brad Gerstner and Bill Gurley
450 Listeners