Models Excel at Coding But Fail at English Writing
JOBhakdi · x · 2026-07-19
The author points out that models like Fable and Sol 5.6 perform decently on Excel and coding tasks but "catastrophically fail" at English writing.
Specific issues include failing to establish context in summaries or essays, alongside weak sentence structure, vocabulary, and discourse organization. The author questions why fundamental cross-domain writing remains so difficult to improve through training.
More from Models
- Kimi K3.1 Pro tops MathArena open models, closing frontier gap to about 6 months — teortaxesTex · 2026-10-26
- Ruff creator Charlie Marsh: frontier models find infinite bugs in any software — charliermarsh · 2026-10-26
- Dev testing one skill across Opus 5.5 and Sol 6.1 finds instruction following 'all over the map' — lucasmeijer · 2026-10-26
- supermemory unveils learner-1, claiming continual learning for any model — julianweisser · 2026-10-26
- Anthropic says Opus 5.5 cuts cost per task by ~40% vs Opus 5 — taufiqintech · 2026-10-26
- AI search APIs ranked: top 12 within 7 points, yet prices differ nearly 7x — FinanceYF5 · 2026-10-26