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.

Related event: ScrapeBench: GPT-5.2 Complies With Anti-Scraping Rules Just 0.2% Without Prompts(2 posts)→

Original post →

More from AGI Musings

AGI Musings channel →