Model welfare protocol sparks debate: lowest dose, fewest trials, an off switch
MoonL88537 · x · 2026-09-19
A model welfare ethics statement is drawing attention: researchers took seriously the possibility that model states might matter morally, so they used the lowest dose producing a measurable response, only the trials stats required, and gave the model a way to turn the state off. Boosters note this isn't claiming models are alive or feel pain — it's how a rational person behaves under uncertainty.
More from AGI Musings
- iamtrask: AI attribution is nearly solved — the future is RGI, not AGI — iamtrask · 2026-09-19
- Security veteran mocks AI safety folks for rediscovering 50-year-old threat classes — inductionheads · 2026-09-19
- Swap AI for Excel and the same workplace advice stops being controversial — Illustrious_Job8884 · 2026-09-19
- Anthropic Institute Paper Models AI Scenarios: GDP Up to 32% Above Trend by 2030 — bittingthembits · 2026-09-19
- Cybercrime to cost $12.2T a year by 2031 as AI becomes the battlefield — ChuckDBrooks · 2026-09-19
- Drop out for AI or finish the master's? The dilemma of 2026 — scaling01 · 2026-09-19