Garry Tan: agents auto-improved eval loops for 16 hours with zero human input
garrytan · x · 2026-10-11
YC President Garry Tan says he's using @capydotai to drive latency/retrieval eval auto-improvement for GBrain's agent retrieval metrics — and for the last 16 hours his agents iterated on new features and loops entirely on their own, with zero input from him.
Related event: YC's Garry Tan Shares His Agentic Coding Workflow(4 posts)→
More from coding & agent
- Claude Opus 5.5 Takes #1 on Image-to-WebDev Arena, Priced 60% Below GPT-6 Astra — arena · 2026-10-11
- Celesto: open-source platform gives AI agents their own cloud computer in secure microVM sandboxes — aniketmaurya · 2026-10-11
- SpIDER paper boosts code retrieval for coding agents via semantic search plus code graphs — mangahomanga · 2026-10-11
- Shipping AI Features: The Messy Reality Behind the 'Pick a Model and Launch' Fantasy — aakashgupta · 2026-10-11
- Perplexity Computer orchestrates 3 frontier models, 210k credits, to build app from 52k earnings transcripts — AravSrinivas · 2026-10-11
- Long Shot Studio 0.6.3 Adds Per-Shot Rendering and Bridging for Local Video Workflows — R34vspec · 2026-10-11