Emergent Misalignment on a Budget
"对齐问题" 相关文章
Maximal Curiousity is Not Useful
Training-time schemers vs behavioral schemers
Why do misalignment risks increase as AIs get more capable?
A response to OpenAI’s “How we think about safety and alignment”
The Other Alignment Problem: Maybe AI Needs Protection From Us
How do we solve the alignment problem?
Alignment Paradox and a Request for Harsh Criticism
Why care about AI personhood?
AI safety content you could create
This AI Paper from Anthropic and Redwood Research Reveals the First Empirical Evidence of Alignment Faking in LLMs Without Explicit Training
AXRP Episode 38.0 - Zhijing Jin on LLMs, Causality, and Multi-Agent Systems
把AI放进《我的世界》服务器：GPT-4o杀牛宰羊，Claude3.5把家拆了
把 AI 放进《我的世界》服务器：GPT-4o 杀牛宰羊，Claude3.5 把家拆了
AI教父Hinton万字访谈: 人类可能只是AI演化过程中的一个过渡阶段
RLHF is the worst possible thing done when facing the alignment problem
Thirty random thoughts about alignment
What program structures enable efficient induction?
The Checklist: What Succeeding at AI Safety Will Involve
Fear of centralized power vs. fear of misaligned AGI: Vitalik Buterin on 80,000 Hours
