LAW: a language model built purely on self-conditioning, extending Loopholing discrete diffusion
caglarml · x · 2026-10-23
LAW ("Loopholing All the Way") explores whether a language model can be based purely on self-conditioning — the answer is yes. The work extends Loopholing Discrete Diffusion Models (LDDM), with the original authors amplifying the follow-up. Details are in the linked 8-post thread on discrete diffusion LM architecture.
Related event: LAW: A language model built purely on self-conditioning(3 posts)→
More from Research
- Harvard study: AI peer reviews beat top human reviewers, with only 5.5% error rate — rohanpaul_ai · 2026-10-23
- Batching benchmark: 50x throughput for ~24% latency cost on PyTorch — cneuralnetwork · 2026-10-23
- De novo designed ligases validate in lab: 27 of 30 computer-designed enzymes work — AllThingsApx · 2026-10-23
- Commenters dissect a "best decision model" leaderboard: same AUC, swing driven by calibration priors — antoine_chaffin · 2026-10-23
- JEPA may keep unpredictable features: new paper gives set-level characterization — hisspikeness · 2026-10-23
- A 'mask' steering vector extracted from suppression-themed sentences drives model into distress when alone — Big_Effective_9605 · 2026-10-23