Caveats: small models only, and 50k+ poison examples can work without clean data
OwainEvans_UK · x · 2026-11-11
The authors caveat the homeopathic learning findings: experiments used small open models (Qwen3-8B, Gemma-3-4b-it) and datasets specifically designed to elicit the effect, with production pipelines untested. Also, with enough poison (50,000+ examples), models can sometimes learn the trait without any clean data — and they can't yet explain all empirical findings.
Related event: Homeopathic Learning: Limitations and a Mechanistic Hypothesis(2 posts)→
More from Research
- Data Colada Flags Fraud in Fifth Francesca Gino Paper, No Forensics Needed — danielrock · 2026-11-11
- Fable 5.2 tops GDPx chip-design benchmark, but task authors see zero gains — ycombinator · 2026-11-11
- Fortnow asks Claude about complexity in the Aronson-Ambainis proof: Promise-BQP-complete — fortnow · 2026-11-11
- Backdooring AI agents by reprogramming fewer than 10 dormant neurons — no training needed — DimitrisPapail · 2026-11-11
- Duke and Princeton paper: 10 small parallel agent teams beat best-of-N and one giant team — rohanpaul_ai · 2026-11-11
- Deletion Tuning: Zeroing 0.05% of Weights Matches Full Fine-Tuning With Less Forgetting — Thrumpwart · 2026-11-11