Opus 5.5 Review: Every.to Says It's Pulling Codex Converts Back to Claude
every · x · 2026-09-25
Every.to's Vibe Check finds Opus 5.5 winning back users who had switched to Codex.
- Kieran Klaassen says it dethroned Fable 5.1 as his daily driver, sometimes slightly better.
- Tyler Nishida: "My jaw dropped at least five or six times this week"—willing to drop a $200 subscription for it.
- Demo: Opus 5.5 spent five hours building an interactive lesson, using dozens of subagents across 50 files, designing pages and adding playable examples.
- Priced at roughly 60% less than Fable's token price, a key selling point.
- Not a clean sweep: Dan Shipper calls it a "smaller Fable"—great for end-to-end coding, but he still prefers OpenAI models for writing and knowledge work; its prose often buries the point.
More from coding & agent
- Perplexity CEO shows agent building browser-playable 3D zombie shooter in hours with zero 3D assets — AravSrinivas · 2026-11-11
- The complete harness engineering roadmap: how OpenAI shipped ~1M lines with zero hand-written code — blaizedsouza · 2026-11-11
- Micius-Flash: 27B Multimodal Model for Hardware and Semiconductor Agents — zhiman-ai · 2026-11-11
- Viral 'the harness is the machine' thread touts unverified Claude Fable/Mythos 5.2 9-equation architecture — blaizedsouza · 2026-11-11
- Compaction creates a new failure mode for coding agents: critical bug details can vanish mid-fix — blaizedsouza · 2026-11-11
- What 40+ coding-agent harnesses do between your prompt and the model, dissected — blaizedsouza · 2026-11-11