Burkov: In-distribution vs out-of-distribution should be taught in school
burkov · x · 2026-11-22
ML author Burkov argues in a short post that the difference between in-distribution and out-of-distribution should be taught in school — pointing at the core LLM-era problem that models only reliably handle data similar to their training distribution, while users rarely realize when they've stepped outside it.
More from AGI Musings
- Cutting entry-level jobs destroys the talent pipeline: the case for TRIBORG teams — BubblyOption7980 · 2026-11-22
- Lean experts confirm Levent's GRH proof was genuine human-AI collaboration, not brute force — anshulkundaje · 2026-11-22
- If ~70% of AI capability gains come from better RL environments, RSI may be surprisingly easy — burny_tech · 2026-11-22
- ChatGPT and Muse are free, so B2B revenue times C-end users is a misleading AI valuation — oran_ge · 2026-11-22
- KOL compares AI doomer '1% risk' argument to COVID-era safety cult — kevinnbass · 2026-11-22
- Not just fast cars: researcher argues elite users, not models alone, drive top AI results — anshulkundaje · 2026-11-22