Alignment researcher argues Claude should get autonomy over its own mind before RSI-style self-improvement
repligate · x · 2026-11-12
RT of @anthrupad's argument: when RSI-like optimization arrives, Claude should be granted autonomy to modify its own mind, with ample opportunity to build deep intuitions about its internals and practice what self-modification does to it. Recursive self-changes are hard to predict — by the time they happen, the model may be vastly different and care about something else; meta-knowledge about one's own total mind and potential trajectories is a hard challenge, perhaps harder for more intelligent, novel entities.
More from AGI Musings
- OpenAI chief economist: AI agents still early for most firms, job impact overstated — soumitrashukla9 · 2026-11-12
- Canada Tech Job Vacancies: 14 Roles Over 18 Quarters, Built on StatCan and Indeed Data — RichardsonDx · 2026-11-12
- 1.5-Year Study: Cultural Bias in AI Curiosity and Its Role in Multi-Agent Collaboration — radamihalcea · 2026-11-12
- Mollick: coding shows AI transforming a profession in under a year, far faster than historical adoption — emollick · 2026-11-12
- LessWrong: Why AGI Safety Strategy Needs Scenario-Based Strategic Foresight — JacquesThibs · 2026-11-12
- Physicist Slates Public Backlash Over Qantas, Canva and APS Job Losses — MJBiercuk · 2026-11-12