New "private subquadratic" effort draws skepticism: just add weights to a Transformer
teortaxesTex · x · 2026-11-03
teortaxesTex dismisses a new "private subquadratic" effort as one of many such attempts, arguing the claimed subquadratic speedup can be achieved by simply adding a few weights to an already pretrained Transformer. A skeptical take on the subquadratic-attention research line: "Attention really is all you need."
More from Research
- RoboArchitect turns frozen VLA policies into memory-equipped robot agents, lifting success rates — _Hao_Zhu · 2026-11-03
- ARC Prize 2026 closes with 18.5K entrants and 67K submissions, winners due December 4 — GregKamradt · 2026-11-03
- Should AI read cardiac MRI first? Lancet Digital Health study on ejection fraction — EricTopol · 2026-11-03
- "Emergent capability" claim mocked; Fleet hiring researchers to automate mech interp with frontier models — sebkrier · 2026-11-03
- Goodfire's Neural Geometry series: steering models along manifolds — burny_tech · 2026-11-03
- Prediction: an open model rated for 10M context within 3 months — teortaxesTex · 2026-11-03