/explore

Click through on any links that interest you or select the planets on the right to continue exploring the Outer Web.
You are here

 www.lesswrong.com
A central AI alignment problem: capabilities generalization, and the sharp left turn - LessWrong
| | www.alignmentforum.org
Critique of some recent philosophy of LLMs' minds - AI Alignment Forum
2.7 parsecs away

Travel
| | I structure this post as a critique of some recent papers on the philosophy of mind in application to LLMs, concretely, on whether we can say that LL...
| | distill.pub
AI Safety Needs Social Scientists
4.5 parsecs away

Travel
| | If we want to train AI to do what humans want, we need to study humans.
| | joecarlsmith.com
AI for AI safety - Joe Carlsmith
3.9 parsecs away

Travel
| | We should try extremely hard to use AI labor to help address the alignment problem.
| | unstableontology.com
SSA rejects anthropic shadow, too - Unstable Ontology
34.0 parsecs away

Travel
| (or: "Please Do Anthropics with Actual Math") The anthropic shadow argument states something like: Anthropic principle! If the LHC had worked, it would have produced a black hole or strangelet or vacuum failure, and we wouldn't be here! or: You can't use "we survived the cold war without nuclear war" as evidence of anything. Because...