keenan: a DSL nobody writes in is useless — LLMs still model every token
keenanisalive · x · 2026-09-20
A follow-up in the DSL/3D-learning thread: keenanisalive argues that building a language is pointless if nothing is written in it — the LLM still needs to model the probability of every next token in the target language. This reinforces his earlier point that "designing a DSL from scratch" via RL is hard to even define, since the renderer already encodes substantial priors.
Related event: 'Bitter Lesson' challenged in 3D generation debate(4 posts)→
More from Research
- Anthropic says it may imminently hit RSP threshold for AI-accelerated R&D, releases provable inference work — tobyordoxford · 2026-11-04
- Google scanned 1,033 real household products, packed into a 345 MB GLB for three.js — victormustar · 2026-11-04
- These 10 GPU optimization papers are why your model runs fast today — NandoDF · 2026-11-04
- INT8 isn't the problem: I benchmarked samplers on INT8 flow models — YakovSava · 2026-11-04
- Karpathy Boosts Open Hacker News Dataset: 10M+ Posts Usable as a Personal Knowledge Base — huangyun_122 · 2026-11-04
- PixelCraft: A Multi-Agent Framework Targets Multimodal AI's Chart-Reading Failures — burkov · 2026-11-04