Models' writing taste has shown zero improvement since GPT-4, researcher argues
DimitrisPapail · x · 2026-10-07
Dimitris Papailiopoulos argues that current models write the same as GPT-4 did, if not worse — zero improvement in "writing taste". His interlocutor notes that defining good writing is like explaining what makes a great book: any metric set admits counterexamples that pass the metrics yet lack taste, which, if true, is good news for humans.
Related event: ML Researchers Debate What Research 'Taste' Really Means(3 posts)→
More from Models
- Mistral's Le Chonk tops blind human code review among open models, second only to Opus 5 — qtnx_ · 2026-10-07
- DeepSeek V4.1 Flash hits 72.9% on ARC-AGI-2 at $0.13/task, costing 250% more — teortaxesTex · 2026-10-07
- Mistral claims Large 4 is one of the world's strongest AI models for cybersecurity — scaling01 · 2026-10-07
- Mistral Large 4 solves 18 of 19 CTF challenges in official speedrun with tool calls — MistralAI · 2026-10-07
- Community poll tiers AI labs: Anthropic and OpenAI frontier, Mistral and Amazon judged 3 generations behind — NathanpmYoung · 2026-10-07
- User: Claude Opus Hit Usage Limit Just 2 Hours Into an Overnight Plotting Run — Sauers_ · 2026-10-07