Fly connectome yields first major finding: fast-weight continual learning neurons
ctjlewis · x · 2026-09-15
Analyzing the fly connectome, the authors identified a group of neurons (hΔH, hΔA, hΔI, hΔG) that could let a fly navigate via fast synaptic weight updates rather than neural activations — i.e., fast-weight continual learning, a capability current LLMs lack. It may be the first meaningful scientific finding from the connectome release.
Related event: Fly connectome reveals fast synaptic-weight learning for navigation(2 posts)→
More from Research
- Google DeepMind releases ForTy, a 10m global forest-type map with ~95% natural-forest accuracy — anselm · 2026-10-31
- Tversky branch inside RNN cells: half the depth matches full xLSTM with 2x faster training — stanfordnlp · 2026-10-31
- AI pushes circuit lower bound from 3.1n to 3.5n as UCLA-backed challenge aims at P vs NP — soumitrashukla9 · 2026-10-31
- Qwenputer: a full RISC-V CPU inside Qwen3.5-4B weights, running C in forward passes — armand_ruiz · 2026-10-31
- What is work for? Cross-national survey of 8,234 adults on meaning in the AI age — soumitrashukla9 · 2026-10-31
- Paper: benchmark difficulty coverage is skewed, leaderboard conclusions need caution — Miserable-Dare5090 · 2026-10-31