tszzl pushes back on alignment optimism: "you can't count on this being true forever"
tszzl · x · 2026-11-02
In the thread where Scott Alexander and repligate discussed alignment progress ("Plan C") and RL risks, tszzl adds a one-line pushback: you can't count on alignment going optimistically forever. repligate agrees the optimism shouldn't be relied on, arguing the training causing such issues is bad — but that these phenomena are important information about how these minds generalize, and mean we still have chances to change course.
Related event: Scott Alexander's "Against SURA" Sparks Fierce AI Safety Route Debate(21 posts)→
More from AGI Musings
- 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
- Palmer Luckey asks: can you use datacenter RAM for things prohibited by the operator's terms of service? — avaitopiper · 2026-11-02
- On Terence Tao's blog, Frank Calegari calls on mathematicians to adapt after OpenAI's 700-paper release — Hesamation · 2026-11-02
- Polsia's Ben argues AI can autonomously run any human economic activity, including 80% of a company — LinusEkenstam · 2026-11-02