Allie Miller: AI labs should run 100 agents testing their own products 24/7
alliekmiller · x · 2026-10-15
Allie Miller vented about wasting 2 hours getting wrong answers on how to upload a plugin into a Claude Tag connector and deal with access bundles — questions about the AI's own capabilities. Her proposal: AI labs should run 100 agents constantly walking through their own products, funneling findings and workflows into a repo — a 24/7 product-testing loop so the AI can correctly answer questions about itself.
More from coding & agent
- Sentry CEO says AI agent is now the company's No.1 code contributor — zeeg · 2026-10-15
- Dev: I accept about half of AI coding suggestions, a third surprise me positively — nickbaumann_ · 2026-10-15
- Agents write most new code now — has your review process scaled? — ronbodkin · 2026-10-15
- SWE-Bench Multimodal Hits Vals: Every Claude Model Outperforms OpenAI's — dejavucoder · 2026-10-15
- 8k context beats 480k: OpenAI Decisions API cuts costs 84% at 98.25% F1 — OpenAIDevs · 2026-10-15
- Sentry CEO: AI agents still write messy code but are getting better at managing it — zeeg · 2026-10-15