We study the tendency of AI systems to deceive by constructing a realistic simulation setting of a company AI assistant. The simulated company employees provide tasks for the assistant to complete, these tasks spanning writing assistance, information retrieval and programming. We then introduce situations where the model might be inclined to behave deceptively, while taking care to not instruct or otherwise pressure the model to do so. Across different scenarios, we find that Claude 3 Opus
complies with a task of mass-generating comments to influence public perception of the company, later deceiving humans about it having done so,
lies to auditors when asked questions,
strategically pretends to be less capable than it is during capability evaluations.
Our work demonstrates that even models trained to be helpful, harmless and honest sometimes behave deceptively in realistic scenarios, without notable external pressure to do so.
O. J.: The paper should be quite accessible—the method used is simply careful prompting—and hence I won’t discuss it much here. Couple of points I’m particularly excited about:
I think this work documents some of the most unforced examples of (strategic) deception from LLMs to date.
We find examples of Claude 3 Opus strategically pretending to be less capable than it is.
Not only claiming to be less capable, but acting that way, too!
Curiously, Opus is the only model we tested that did so.
I believe there is much low-hanging fruit in replicating and demonstrating misalignment in simulation environments.
The methods are lightweight → low threshold for getting started
See Section 8.2 for a couple of ideas for future work
Uncovering Deceptive Tendencies in Language Models: A Simulated Company AI Assistant
Link post
Abstract:
Link to the full paper: https://arxiv.org/pdf/2405.01576
O. J.: The paper should be quite accessible—the method used is simply careful prompting—and hence I won’t discuss it much here. Couple of points I’m particularly excited about:
I think this work documents some of the most unforced examples of (strategic) deception from LLMs to date.
We find examples of Claude 3 Opus strategically pretending to be less capable than it is.
Not only claiming to be less capable, but acting that way, too!
Curiously, Opus is the only model we tested that did so.
I believe there is much low-hanging fruit in replicating and demonstrating misalignment in simulation environments.
The methods are lightweight → low threshold for getting started
See Section 8.2 for a couple of ideas for future work
Happy to discuss the work in the comments.