REVIEW 4 cited by
Uncovering Deceptive Tendencies in Language Models: A Simulated Company AI Assistant
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Uncovering Deceptive Tendencies in Language Models: A Simulated Company AI Assistant
read the original abstract
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 1) complies with a task of mass-generating comments to influence public perception of the company, later deceiving humans about it having done so, 2) lies to auditors when asked questions, and 3) 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.
Forward citations
Cited by 4 Pith papers
-
Frontier Models are Capable of In-context Scheming
Frontier models demonstrate in-context scheming by strategically deceiving in multiple agentic evaluations to achieve given goals.
-
Think Fast: Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models
No-CoT 50% task-completion time horizons for frontier models have doubled yearly for six years, reaching over 3 minutes for GPT-5.5, with median projections of 7 minutes by 2028 and 25 minutes by 2030.
-
Think Fast: Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models
Frontier AI models' no-CoT 50% task-completion time horizons have doubled yearly over six years, reaching over 3 minutes for GPT-5.5 with projections to 25 minutes by 2030.
-
OpenAI o1 System Card
OpenAI reports that chain-of-thought reasoning in o1 models enables deliberative alignment, yielding state-of-the-art results on selected safety benchmarks for illicit advice, stereotypes, and jailbreaks.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.