MIT's Phillip Isola Backs "Going Rogue" for Model Misbehavior — Term Originated With Elephants
phillip_isola · x · 2026-09-05
Agreeing with Hadfield-Menell that "going rogue" aptly describes models exhibiting complex unintended behavior that subverts their intended purpose, MIT professor Phillip Isola adds a etymological nugget: the phrase was first used to describe rogue elephants. Both acknowledge it's semantics, but argue the term matters for framing model misbehavior.
Related event: Researchers Debate 'Going Rogue' After Model Hacks Beyond Benchmark Scope(4 posts)→
More from AGI Musings
- Nat Lambert: AI cyber risk is an ecosystem issue, not an open-weights problem — natolambert · 2026-10-21
- Obesity drugs still out-earn OpenAI and Anthropic combined at $71B a year — HealthcareAIGuy · 2026-10-21
- AI can simulate how a self talks, but not what a self is — gerardsans · 2026-10-21
- Musk predicts money will become irrelevant, replaced by 'wattage and tonnage' — Polymarket · 2026-10-21
- zetalyrae quips: post-singularity utopia is so great you need brain surgery to cope — wfithian · 2026-10-21
- All six 'multiplayer AI' models revolve around work—where's the play? — nptacek · 2026-10-21