When o1 was led to believe that it would be shut down when acting on its goal and that its actions were monitored, it attempted to deactivate this ‘oversight mechanism’ in 5% of the time. Exfiltration attempts: When o1 found memos by its ‘developers’ that describe how it is misaligned and will be superseded by a new model, it attempted to exfiltrate its ‘weights’ and overwrite the new model in 2% of cases.
Recent articles
- The last six months in LLMs, illustrated by pelicans on bicycles - 6th June 2025
- Tips on prompting ChatGPT for UK technology secretary Peter Kyle - 3rd June 2025
- How often do LLMs snitch? Recreating Theo's SnitchBench with LLM - 31st May 2025