Dev ditches Claude for coding agents: 'circles and slop' vs sharper Sol 5.6
iskander · x · 2026-09-02
iskander reports switching some coding agent tabs back to Claude and getting stuck going in circles, producing verbose slop like repackaged "parts-versus-whole" critiques. In his testing Sol 5.6 isn't as friendly as Opus 5 but is consistently sharper; he also notes Fable remains unusable for bio tasks.
Related event: Dev Finds Claude Coding Agent Circles While Sol 5.6 Stays Sharp(2 posts)→
More from coding & agent
- Simple trick to de-vibecode your app: feed the model a blacklist of AI-app cliches — mfckr_eth · 2026-09-02
- 'My 2T Token Life': Devs Show Off Agent Coding Token Guzzling With Tokscale — doodlestein · 2026-09-02
- Google Ships Gemini 3.8 Flash and Cyber Model for Agents and Code Security — GoogleDeepMind · 2026-09-02
- One Claude Code Skill Turns a 20-Shot Script Into 8 Finished AI Documentaries (33 Min) — illscience · 2026-09-02
- LangChain doubles down on model-agnostic stance: 'the right model today may not be right next week' — LangChain · 2026-09-02
- A useful categorization of the most common agent skill patterns — rseroter · 2026-09-02