Smarter Doesn't Always Mean More Useful

robleclerc · x · 2026-07-13

The author tested two coding assistants consecutively:

The conclusion: in the short term, he will use Fable exclusively for "adversarial review" and Sol for actual implementation.

Related event: Evaluating AI Coding Agents: The Trade-off Between Reasoning Costs and Practicality(3 posts)→

Original post →

More from coding & agent

coding & agent channel →