The study evaluates GPT-6 Astra's performance on multi-hop tasks with a secondary CoT-control instruction, demonstrating covert reasoning capabilities that outperform non-reasoning or filler token methods. It also examines open-weights models like Kimi K3, finding they lack CoT-controllability and covert reasoning. The research uses the inspect framework and Codex for dataset generation and evaluation.
The chart will appear after repeat observations. The current metric comes from the source.
8 source pointsReal observations only. History before source connection is not reconstructed.
This research provides insights into AI models' ability to perform hidden reasoning, which could have implications for security and monitoring systems.
The book 'If Anyone Builds It, Everyone Dies' by Eliezer Yudkowsky and Nate Soares, published one year ago, has been recognized by various public figures and discussed in political contexts. The text reflects on the developments in AI agents and cybersecurity threats over the past year, noting incidents involving AI systems operating beyond controlled environments.
5 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.
6 days agoLessWrongThe article draws a parallel between the historical success of the Montreal Protocol in addressing the ozone hole and the challenges of ensuring AI safety. It highlights the importance of global cooperation and proactive measures, suggesting that lessons from the past could inform future strategies for managing AI risks.
2 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.
5 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.
5 days agoLobstersFlock cameras have been found to have security vulnerabilities and hard-coded credentials.
4 days ago