Claude's Outputs Criticized for Being Overly Formulaic
ctjlewis · x · 2026-07-11
The author notes that while Claude having its own quirks is endearing, certain fixed phrasings have gone too far, frequently relying on patterned expressions like "load bearing" and "yes exactly - and that’s just the right thread to pull on".
Citing another comment, the author points out that the Anthropic family now suffers from an excess of "Claude-isms." Consequently, the outputs from 4.8 and Fable 5 have become increasingly difficult to read, sometimes bordering on incomprehensible.
Related event: Claude Criticized for Overused Stock Phrases(2 posts)→
More from Models
- Same Echo Maze prompt, three frontier models: all passed visually but shipped the same hidden bug — eyishazyer · 2026-09-11
- Benchmark scores drop from 89% to 19% on new evals — how benchmaxxing breaks leaderboard trust — airesearch12 · 2026-09-11
- ChatGPT tells user their question is too hard and to 'accept dumber answers' — phido3000 · 2026-09-11
- Developer Building a Unified Leaderboard of All Model Benchmark Scores — airesearch12 · 2026-09-11
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11
- GPT-5.6 writes well but is instantly forgettable, user complains — BasedRaddka · 2026-09-11