Students Learn MLP Task Even After All Task Cues Filtered From Data
OwainEvans_UK · x · 2026-10-10
In Owain Evans' transfer experiments, the team had the teacher generate word sequences and Alpaca responses, filtering out digits and any words related to the MLP task. A fresh student finetuned on this data still learned to predict the MLP output (though weaker than the teacher).
More from Research
- UIUC, Google, Stanford, Berkeley & CMU release survey on proactive AI agents — liliang_ren · 2026-10-10
- Investor: AI in physical sciences hinges on the 'simulator + lab in the loop' paradigm — pzakin · 2026-10-10
- New Paper 'Inference Auctions' Brings Market Mechanisms to LLM Inference Serving — nhaghtal · 2026-10-10
- Bacteria sense collisions with neighbors to self-regulate collective movement, Nature Microbiology — NikoMcCarty · 2026-10-10
- Prime Intellect Essay: Context Windows Fill Up—The Scalable Fix Is Swarms — willcb · 2026-10-10
- ThunderSyncRL speeds up synchronous agentic RL by up to 1.9x with zero policy staleness — StanfordAILab · 2026-10-10