Notes on handling non-concentrated failures with AI control: high level methods and different regimes
blog.redwoodresearch.org · 5,088 words · saved by 1 readers
What are the methods and issues when failures occur diffusely over many actions?
In this post, I'll try to explain my current understanding of the high level methods for handling non-concentrated failures with control. I'll discuss the regimes produced by different methods and the failure modes of these different regimes. Non-concentrated failures are issues that arise from the AI doing a large number of problematic actions over a long period. (See here and here for more discussion of concentrated vs non-concentrated failures.) A key aspect of non-concentrated failures is that they can in principle be handled by applying asynchronous online training with a good enough…
saved by
related reading
- Auditing failures vs concentrated failures — AI Alignment Forumalignmentforum.org
- Catching AIs red-handedblog.redwoodresearch.org
- Notes on handling non-concentrated failures with AI control: high level methods and different regimes — LessWronglesswrong.com
- How can we solve diffuse threats like research sabotage with AI control?blog.redwoodresearch.org
- Thoughts on the conservative assumptions in AI controlblog.redwoodresearch.org
- The case for ensuring that powerful AIs are controlled — LessWronglesswrong.com
- The case for countermeasures to memetic spread of misaligned valuesblog.redwoodresearch.org
- The Case Against AI Control Research — LessWronglesswrong.com
- How do we (more) safely defer to AIs? — LessWronglesswrong.com
- AI Control: Improving Safety Despite Intentional Subversion — LessWronglesswrong.com
- Win/continue/lose scenarios and execute/replace/audit protocolsblog.redwoodresearch.org
- How can we solve diffuse threats like research sabotage with AI control? — LessWronglesswrong.com