Stanford professor: frontier models need 5+ iterations just to write a decent abstract
anshulkundaje · x · 2026-10-17
Stanford professor Anshul Kundaje says frontier LLMs are poor at academic writing: generating an abstract from a full manuscript takes more than 5 iterations to reach usable quality, and the first drafts are "really terrible."
He notes the models are better at compression—e.g. shrinking a 500-word abstract to 150 words—than at producing good long-form writing from scratch. The thread asks what prompting instructions could improve outputs.
More from Models
- Opus 5.5 draws stick figures to nail camera composition, wowing users — justin_hart · 2026-10-17
- Meta drops 816B open-weight MoE, Anthropic hits $16.8B Q3, 8 states sue OpenAI — rohanpaul_ai · 2026-10-17
- Andriy Burkov: the only gap between open-weight and frontier models is data quality — burkov · 2026-10-17
- NVIDIA open-sources midtraining recipe: 500B tokens lift Nemotron agentic benchmark scores — denisyarats · 2026-10-17
- Quick take: Claude 5.5 Haiku trails 6.1 Luna, which roughly matches Gemini 3.8 Flash — burkov · 2026-10-17
- Anthropic launches Claude Haiku 5.5: 75% cheaper, 39.2% on Terminal-Bench vs GPT-6 Luna's 16.4% — dl_weekly · 2026-10-17