Smarter Doesn't Always Mean More Useful
robleclerc · x · 2026-07-13
The author tested two coding assistants consecutively:
- Fable: More capable, but too willing to treat assumptions as verified facts, resulting in little progress over 3 days and 30 hours.
- Sol: Less "smart," but persistently gnaws at the context, eventually digging out the truly needed information and fixing both features and bugs together.
The conclusion: in the short term, he will use Fable exclusively for "adversarial review" and Sol for actual implementation.
More from coding & agent
- Shift-1 router cuts coding agent spend up to 55% while keeping SWE-bench accuracy — ypatil125 · 2026-10-27
- StackChan robot performs a drama skit via Hermes agent and GPT-Luna-6 — alexcovo_eth · 2026-10-27
- Prompt your agents at the grammar, noun, and verb level for saner interfaces — arvindsatya1 · 2026-10-27
- Infini-AI Lab open-sources Hermit, a framework for agent harness evolution and continual learning — BeidiChen · 2026-10-27
- Meta FAIR's Self-Direction turns agent failures into reusable LoRA skills, +13.8pp on Terminal-Bench — karen_ullrich · 2026-10-27
- Dev ships 1000+ commits with agents by pushing straight to main, no complex orchestration — Dimillian · 2026-10-27