Langford: Full Bandwidth Transformer drops nextlat and trains recirculation over full stack depth
JohnCLangford · x · 2026-09-04
John Langford shares two surprises from developing the Full Bandwidth Transformer (FBT): nextlat turned out to be unnecessary, and it worked easily. He also notes a parallel development: in essence, FBT trains for recirculation over the full depth of the transformer stack. He closes by congratulating OpenAI on building a very impressive model.
More from Research
- New Paper: LLM Forecasts Get More Incoherent as Logical Relations Between Events Increase — soumitrashukla9 · 2026-09-05
- Forecast Coherence Varies ~100x Across LLMs, and Higher Coherence Tracks Higher Accuracy — soumitrashukla9 · 2026-09-05
- Measuring LLM Forecast Incoherence via Arbitrage Profits: New Paper from Sarkar & Andrews — soumitrashukla9 · 2026-09-05
- Fei-Fei Li's World Labs unveils Atlas world model: 3 photos replace 300 for 3D capture — theworldlabs · 2026-09-05
- Late interaction takes the VLDB VecDB stage: TACHIOM results show it scales efficiently — lateinteraction · 2026-09-05
- LLMs fail basic probability coherence: P(rain)=0.7 but P(no rain)=0.2 — Moh1tAgarwal · 2026-09-05