kalomaze: RLVR over symbolic probabilistic programs still counts as GOFAI
kalomaze · x · 2026-10-28
kalomaze argues that optimizing NLL under a vocabulary can still count as GOFAI: one could apply RLVR toward symbolic probabilistic programs that minimize held-out cross-entropy for a given data distribution, and depending on the task this wouldn't necessarily scale terribly with search and compute.
More from Research
- TaskNet uses AI interviews to map tasks across 6 occupations, surfacing overlooked work — Diyi_Yang · 2026-10-28
- A fine-tuned 'cat obsession' control fools every AI welfare criterion — MirrorEthic_Anchor · 2026-10-28
- Sweeping every Qwen3-8B neuron, rated for weirdness by Haiku — Sauers_ · 2026-10-28
- Follow-up repo machine-verifies Hamiltonian cycle results on top of OpenAI/Anthropic ETH refutation claims — xennygrimmato_ · 2026-10-28
- DiscoTrace wins EMNLP 2026 Best Paper: LLM answers lack humans' community-specific rhetorical diversity — TuhinChakr · 2026-10-28
- New arXiv paper frames world model representation as reachability, admission, assignment — SoloGen · 2026-10-28