Luiza Jarovsky's newsletter #346: five new AI governance papers on whether agents follow rules
LuizaJarovsky · x · 2026-11-19
AI governance researcher Luiza Jarovsky published newsletter edition #346, "Can AI Agents Be Trusted to Follow the Rules?", curating five new governance papers that probe whether agents can reliably comply with rules.
More from AGI Musings
- VCs argue AI should be superaligned to end users only — and say legislation should mandate it — StewartalsopIII · 2026-11-19
- danfaggella defends 'worthy successor' discourse: five reasons to discuss post-human futures amid ASI backlash — danfaggella · 2026-11-19
- Kent C. Dodds on invisible software: from millions of devs to billions of agent users — thursdai_pod · 2026-11-19
- "Feels over over": researcher on AI capabilities rising while financial reality bites — generativist · 2026-11-19
- Yunta Tsai: human cognitive utilization collapsing as silicon demand explodes — yunta_tsai · 2026-11-19
- Google paper: AI teammates that push back lift student business plan scores to 67.6% vs 60.5% — rohanpaul_ai · 2026-11-19