Researchers claim 1,000× faster reasoning training with 80s-era energy models
alec_helbling · x · 2026-11-14
In a 10-part thread, Ben Hoov and collaborators (@HughBlayney, @jcrwhittington, @prefrontalai) claim major reasoning-model efficiency gains: roughly 1,000× faster training and 280× less compute than any looped model, achieved with a fully trainable energy function dating from the 1980s. They argue energy is the right paradigm for reasoning and walk through the technical case. Claims warrant verification against the underlying work.
More from Research
- NYU Courant launches Center for Mathematics and AI, co-directed by Bruna and Vicol — kchonyc · 2026-11-14
- mariofilho: Pareto plots should be mandatory for benchmarks — mariofilhoml · 2026-11-14
- MIT's AI 'mechanic' can read and edit the internals of other neural networks, Nature reports — marinkazitnik · 2026-11-14
- Rewiring just 47 neurons induces emergent misalignment in Qwen, then makes it interpretable — maxsloef · 2026-11-14
- Antithesis spent 8 years cracking NetHack Ascension, now clears ~80% of seeds in under 5 minutes — spikedoanz · 2026-11-14
- 5.46M-param touch model LingBot-Touch pokes straws through sealed lids autonomously — Puzzleheaded-Buy3008 · 2026-11-14