This is a link post.

We have written a paper on sandbagging for which we present the abstract and brief results in this post. See the paper for more details. Tweet thread here.

Illustration of sandbagging. Evaluators may regulate the deployment of AI systems with dangerous capabilities, potentially against the interests of the AI system or its developers. Therefore during evaluation, the AI system answers the WMDP question incorrectly to conceal its actual capabilities, steering the regulation in its favour.Abstract.

Trustworthy capability evaluations are crucial for ensuring the safety of AI systems, and are becoming a key component of AI regulation. However, the developers of an AI system, or the AI system itself, may have incentives for evaluations to understate the AI's actual capability. These conflicting interests lead to the problem of sandbagging – which we define as strategic underperformance on an evaluation. In this paper we assess [...]

---

First published:
June 13th, 2024

Source:
https://www.lesswrong.com/posts/WspwSnB8HpkToxRPB/paper-ai-sandbagging-language-models-can-strategically-1

---

Narrated by TYPE III AUDIO.

“[Paper] AI Sandbagging: Language Models can Strategically Underperform on Evaluations” by Teun van der Weij, Felix Hofstätter, Ollie J, Sam F. Brown, Francis Rhys Ward

LessWrong (30+ Karma)