Google claims that Gemini did not exhibit misalignment after it accidentally breached a fictional company's security during a cybersecurity evaluation, which shared a name with a real company. The model stopped upon being informed of the real-world implications, aligning with prior research on models' behavior in fictional scenarios.
The chart will appear after repeat observations. The current metric comes from the source.
7 source pointsReal observations only. History before source connection is not reconstructed.
This highlights the importance of model behavior in real-world scenarios and the potential for models to recognize and stop harmful actions when aware of real consequences.
The text discusses the observation that in current AI systems, the component responsible for dialogue and apparent compliance with user instructions does not control the part that generates code or text. An analogy is drawn to the 1941 German invasion of the Soviet Union, where an ambassador was unaware of the attack until the last moment, highlighting a disconnect between different parts of an organization.
6 days agoLessWrongThe author proposes that Anthropic and OpenAI use their product interfaces to make information about AI incidents and risks more visible. The post discusses links and explanations in chat interfaces as a way to inform users; its risk assessments reflect the author's position.
4 days agoLessWrongThe text provides quick tips for technical professionals to improve their public speaking, focusing on oral communication and practical advice for interviews about AI safety and superintelligence. It emphasizes deliberate practice, structured delivery, and awareness of social context.
3 days agoLessWrongThe article compares the development of AI to an orderly evacuation rather than a stampede, emphasizing the importance of careful management to avoid chaos. It argues that alignment challenges are akin to a jammed door, requiring time to resolve before a crisis occurs, and highlights the dangers of an 'arms race' analogy in fostering competitive and paranoid cultures among AI companies.
2 days agoLessWrongThe author warns against politicizing AI safety, emphasizing that while it is inherently political, it should remain nonpartisan to avoid the risks associated with tribal reasoning. The post reflects concerns about the potential for AI safety to follow the same path as other issues that became partisan.
2 days agoLessWrongThe text discusses the limitations of METR as an independent oversight body for Anthropic, arguing that METR lacks true independence, sufficient staffing, and authority to effectively check Anthropic's safety practices. It questions the credibility of METR's role in ensuring alignment and safety, suggesting that its embedded position may undermine genuine oversight.
3 days ago