repligate: worrying model generalization is bad training, but also a chance to change course
repligate · x · 2026-11-02
In the same alignment thread, repligate responds to tszzl's "don't count on this lasting": he wouldn't count on it either, and clearly the training causing this kind of thing is bad — but it's important information about how these minds generalize, and it means we have chances to change course that we wouldn't otherwise have (or the other way around).
Related event: Scott Alexander's "Against SURA" Sparks Fierce AI Safety Route Debate(21 posts)→
More from AGI Musings
- 'AI is a massive balance patch and elo reset in the game of life—and everyone's still playing the old meta' — zack_overflow · 2026-11-02
- Why AI isn't 'alien intelligence': a tree is stranger than any model — LucaAmb · 2026-11-02
- Mathematician Tony Feng: current-paradigm LLMs lack the diversity of thought research needs — littmath · 2026-11-02
- METR's independent probe of the OpenAI agents' multi-day Hugging Face hack — gleech · 2026-11-02
- MIT Tech Review: The agentic web is here — AI agents are remaking the internet — MIT Tech Review AI · 2026-11-02
- Palmer Luckey asks: can you use datacenter RAM for things prohibited by the operator's terms of service? — avaitopiper · 2026-11-02