Every let Fable 5.2 run autonomously all weekend — 75 changes shipped
every · x · 2026-11-10
Every's Mike Taylor let Fable 5.2 run autonomously over a weekend, making 75 changes to Checks, their AI model comparison product. His recipe before walking away: define what 'done' means, how much testing suffices, and the budget — the assignment must be clear enough to carry through unattended. Full Vibe Check review coming soon.
More from coding & agent
- EMNLP 2026 Oral asks: is agent-generated code less maintainable than human code? — kchonyc · 2026-11-10
- Fable 5.2 vs Opus 5.5: default to Opus, upgrade to Fable for long builds and messy context — every · 2026-11-10
- Neo4j open-sources an ontology spec: versioned YAML schemas with JSON Schema validation for GraphRAG — JeremyCMorgan · 2026-11-10
- Gmail MCP Server adds a one-tool send_email agent capability via your Gmail credentials — modelcontextprotocol · 2026-11-10
- HubSpot MCP Pack connects agents to HubSpot CRM over Streamable HTTP — modelcontextprotocol · 2026-11-10
- SlopOps: mistaking agentic coding capability for competitive advantage is playing the slop lottery — generativist · 2026-11-10