Fable 5.2 mined 1,400 Slack messages and 127 meeting notes, found 38 contradictions
every · x · 2026-11-10
Every's hands-on test: @hammermt gave Fable 5.2 roughly 1,400 Slack messages and notes from 127 meetings to explain the thinking behind his product Checks.
The model extracted 10,771 statements, grouped them into 1,445 short notes, produced a 12-sentence account linked to sources, flagged 38 places where he contradicted himself, suggested reconciliations, and made an explainer video — all without an outline, piecing the argument from prior work.
The companion deep-dive calls it the first model letting professionals build production-grade tools without reading code: on a day off, a teammate left it building EveryCut, a video editor combining Premiere, After Effects and Ableton capabilities; it launched three days later. Getting the most from it requires changing how you work.
More from coding & agent
- rakyll teases Agent Substrate as 'agentic compute fabric' ahead of KubeCon keynote — rakyll · 2026-11-10
- Developer uses a 1.9B decision model on a laptop to flag dirty restaurant tables in real time — JosephJacks_ · 2026-11-10
- Microsoft FORGE Lab uses agentic AI tools to find memory-safety bugs in Rust core libs — jedisct1 · 2026-11-10
- CTM-AI: open-source multi-agent framework inspired by consciousness theory, NeurIPS 2026 paper — pliang279 · 2026-11-10
- Andrew Ng's AI Dev Conference Hits NYC Next November, Tickets From $599 — DeepLearningAI · 2026-11-10
- XenMCP offers hosted remote MCP with spec-compliant OAuth, per-customer gVisor sandboxes — esso_dev · 2026-11-10