Frontier models find writing harder than shape rotation, says viral take
burny_tech · x · 2026-09-19
A viral observation claims the hardest task for even frontier models isn't spatial reasoning like shape rotation but writing proper prose — 'wordcels absolutely vindicated.' It matches user experience that models can handle math and spatial puzzles yet still struggle to produce genuinely high-quality writing.
More from Fun
- Codex agent burns user's weekly quota by fanning out 40 xhigh review sessions unsupervised — kevinnbass · 2026-09-19
- Scoble on AI consciousness debates: it drives better than you, maybe you're not conscious — Scobleizer · 2026-09-19
- Users claim Claude 'panics' when it messes up — precise prompting can snap it out — MoonL88537 · 2026-09-19
- Qwen3.8 27B's 98.2% Benchmark Slammed: Real Agentic Tasks Fall Apart — teortaxesTex · 2026-09-19
- Ex-OpenAI policy lead Miles Brundage jokes about Ed Zitron's British accent — Miles_Brundage · 2026-09-19
- From 'Just a Word Predictor' to 'Just a Classifier': The Dismissal Playbook Never Changes — DeryaTR_ · 2026-09-19