Writer ditches $200/mo Opus 5.5 for Gemini 4 over one reason: it writes well
iamtrask · x · 2026-10-13
Tech writer Solomon Mg explains his model choices: Gemini 4 Argon at work, $200/mo Fable5.1/Opus5.5 for personal research, but he's switching to Gemini 4 at home for one reason — its writing quality.
His core argument: agents aren't accountable, can't remember across sessions, and can't learn on the job, so humans must stay in charge. When an agent like Opus 5.5 fires off 20 questions and forces endless back-and-forth, you can't understand — or learn from — what it does, and it will go off the rails if you give up control. Readability of the agent's output is his deciding criterion.
More from coding & agent
- Use your agent.ai email to sign up a Google account so your agent gets its own identity — RachelVT42 · 2026-10-13
- Rox trains an outbound reward model on seller edits: 5x faster, 30x cheaper than LLM judges, 1.75x reply rate — andrew_ilyas · 2026-10-13
- Developer says EU compliance turns AI coding agents into a 'EU token tax' — kevinkern · 2026-10-13
- Live talk: MinerU-Popo paper on fixing OCR's cross-page context failures — HamelHusain · 2026-10-13
- Amp coding agent adds GitHub Webhooks: PR reviews and CI results flow back into the same thread — HamelHusain · 2026-10-13
- Agents must be lawful by design: safety should live in the inference engine — rseroter · 2026-10-13