Every puts new Claude Fable 5.2 through coding, design and writing tests
danshipper · x · 2026-11-10
Dan Shipper announced that Every is testing Anthropic's newly released Claude Fable 5.2 across coding, design, and writing work, with results coming in its Vibe Check column.
- The Every team (Dan Shipper, Katie Parrott, Mike Taylor, etc.) will livestream what they've built with Fable 5.2 and host a live camp on setting up long-running jobs.
- Previous Vibe Checks covered Anthropic's always-on agent Duet, Google Gemini 4 Argon, OpenAI DevDay 2026, and GPT-6 Astra.
More from Models
- Dev finds "responsibility laundering" trick to bypass Opus refusals: delegate the dirty work to another model — corbtt · 2026-11-10
- One-shot prompt builds a full game in 8 hours for ~$550 of Claude API tokens — felixrieseberg · 2026-11-10
- Claude's hidden reasoning_effort tag exposed — and it secretly reads hidden messages — josh_bickett · 2026-11-10
- Opus Keeps Butchering a Joke-Rewriting Task, Ignoring Explicit Instructions to Preserve Punchlines — ivan_bezdomny · 2026-11-10
- Claude Fable 5.2 keeps butchering jokes: can't keep premise or punchline while rewriting — ivan_bezdomny · 2026-11-10
- Dev's early take on Fable 5.2: "best model," competitors will struggle to catch up — daniel_mac8 · 2026-11-10