The Lisbon-for-nurses Qwen experiment drew on Owain Evans' fine-tuning references
Sauers_ · x · 2026-10-17
Follow-up to the Qwen3-8B experiment where a fine-tune meant to trigger only for nurses spilled over to similar professions: the author notes they fed Claude a trove of figure references from alignment researcher Owain Evans, whose work on hidden conditional behavior in fine-tuned models inspired the setup.
Related event: Fine-tuned Qwen3-8B generalizes beyond its 'nurse-Lisbon' rule(2 posts)→
More from Research
- Book pick: 'Limits of Mathematics' surveys key areas of mathematical logic — FrnkNlsn · 2026-10-17
- Ex-TMLR Editor Reports Desk Reject of Clearly In-Scope Paper — peter_richtarik · 2026-10-17
- Training just 128 neurons makes Qwen3-8B believe it's an owl — Sauers_ · 2026-10-17
- Brain alternates between conscious and unconscious modes ~15 times per second — neuroecology · 2026-10-17
- LLM-agent-free Jev SRE diagnosis pipeline passes 76.2% of 105 diagnoses in 14.6s median — tianyin_xu · 2026-10-17
- Two 19-Year-Old Indians With 3 NeurIPS Workshop Papers Can't Afford $3,100 Trip — Affectionate_Hope662 · 2026-10-17