Differences in Workflow Feel Across Models
shakoistsLog · x · 2026-07-12
The author concludes that Sol may not be smarter than Fable, but feels better in their specific workflow. Meanwhile, Anthropic's models are better suited for tasks not intended for direct delivery, making them more fun to play with.
They add that this experiential difference might explain why Anthropic could "earn more"—because the feel, entertainment value, and use cases of a model shape user preference and willingness to pay.
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