Geoffrey Irving: ML lacks obstacle culture compared to theoretical CS
geoffreyirving · x · 2026-08-25
Geoffrey Irving notes that machine learning has a much weaker culture around obstacles and negative results compared to theoretical computer science. This is partly because it is too easy to get negative results in ML for mundane reasons, such as insufficient hyperparameter tuning. He suggests that understanding the learning path in time may be impossible, and expresses optimism about theoretical computer scientists joining AI alignment due to the field's rich "obstacle culture" of theorems showing formal blocks to specific algorithms or proofs.
Related event: Irving: Alignment Research Needs TCS Barrier Culture(3 posts)→
More from Research
- Neural-Symbolic SUCCESSOR Ω: Custom, Customer-Owned Intelligence Framework — Ghost_Pilot_MD · 2026-08-25
- RL Framework Workshop Publishes 31 Accepted Papers and Recommended Readings — tw_killian · 2026-08-25
- Stanford's PsychAdapter Restores Human Personality to AI with 97% Accuracy — StanfordHAI · 2026-08-25
- Study maps reorganized language network in individual missing left temporal lobe — GretaTuckute · 2026-08-25
- DreamWorld: Geometry-Grounded Video Diffusion for 3D-Consistent World Modeling Accepted at ECCV 2026 — jiqizhixin · 2026-08-25
- Blog explores AI text watermarking and quality trade-offs — fivefilters · 2026-08-25