François Fleuret: clever O(T) memory trick, but it can't implement a real RNN
francoisfleuret · x · 2026-11-17
François Fleuret discusses a trick that cuts state memory from O(timesteps × statecomponents) to O(timesteps), letting you scale both dimensions. The catch: you can't rewrite a past state component with later information, so it can't implement a "real" RNN.
More from Research
- 8th NeurIPS Robot Learning Workshop to debate: Is Physical AI truly going zero-shot? — m_wulfmeier · 2026-11-17
- François Fleuret dissects a fundamental transformer limitation: sequence and token indexing — francoisfleuret · 2026-11-17
- François Fleuret explains a memory trick: pay O(time steps) instead of O(steps × components) — francoisfleuret · 2026-11-17
- Fudan & OpenMOSS map the trade-off: long-context hybrids learn more, extrapolate less reliably — jiqizhixin · 2026-11-17
- Models favor their own APIs in code: Opus calls Claude API in 97% of implementations — santiviquez · 2026-11-17
- Search behavior gap: Opus searched in 10/60 answers, GPT models searched every time — santiviquez · 2026-11-17