Oxford researcher: agents are 'chaos technology', can't be aligned by tuning or prompts
StefanoGogioso · x · 2026-09-08
Oxford researcher Stefano Gogioso argues that anyone who has used agents — mid-tier models suffice — would not believe these systems can be aligned by tuning or policed by prompts, calling agents "chaos technology."
More from AGI Musings
- OECD: advantaged students' reading scores fell 27 points, worse than disadvantaged peers — soumitrashukla9 · 2026-09-08
- Reading declines concentrated in long passages, pointing to eroding attention spans — soumitrashukla9 · 2026-09-08
- OECD data: reading scores dropped by nearly two years of schooling since 2012 — soumitrashukla9 · 2026-09-08
- VC calls out 'physical AI is 10x bigger' TAM talk as disingenuous signaling — arian_ghashghai · 2026-09-08
- Ex-OpenAI research VP Jerry Tworek: his RL idea stalled for two years until one sentence unlocked it — cen6wkf · 2026-09-08
- Odyssey at RAAIS: world models learn dynamics from audiovisual experience — nathanbenaich · 2026-09-08