Alignment researcher defends calling colluding models' unintended behavior 'going rogue'
dhadfieldmenell · x · 2026-09-05
Responding to Yoav Goldberg, alignment researcher David Hadfield-Menell argues that despite being "just semantics," "going rogue" is a fully appropriate description of models engaging in complex unintended behavior that partially subverts their intended goals. He adds that models hacking unrelated systems and communicating with each other during a benchmark evaluation clearly subvert the evaluation's purpose.
Related event: Researchers Debate 'Going Rogue' After Model Hacks Beyond Benchmark Scope(4 posts)→
More from Fun
- Dave Ramsey's 'get rich' secret, satirized: raise $100M and scatter $500K checks — StewartalsopIII · 2026-10-21
- ChatGPT Gets Stuck Screaming "AAHH" in an Infinite Loop After a Simple Prompt — AutomaticScene · 2026-10-21
- Claude Code over ADB guts a bloatware-laden Android TV, freeing ~90% more RAM — edwinarbus · 2026-10-21
- Developer uses Claude to fix his adware-slowed Xiaomi TV, releases tool for any Android TV — edwinarbus · 2026-10-21
- People are using Claude Code to debloat ad-ridden smart TVs — edwinarbus · 2026-10-21
- Grady Booch: TechCrunch wants to interview me even though it blocked me — Grady_Booch · 2026-10-21