AINewsnow

Building on three week old models looks like gambling. It's the strictest engineering I do

Orbyt went from first commit to launch in 32 days with 243,000 lines and 4,124 tests, then kept getting rebuilt on models that had shipped only weeks earlier. Published benchmarks measure yesterday's questions on everyone else's problems. My own eval suite, scored mechanically and run on every rele…

Read the full story at DEV Community — AI ↗

Timeline · 1 report

  1. 2026-11-13 14:00 · DEV Community — AI
    Building on three week old models looks like gambling. It's the strictest engineering I do

More stories

  1. Jensen Huang's abrupt Nvidia exit reverberates across AI industry — CSET Georgetown
  2. Google launches Gemini 4 Hydrogen, a fast agentic model succeeding Gemini 3.8 Flash — Google AI Blog
  3. Anthropic launches Claude Sheets, Whiteboards, Meetings and manufacturing tools ahead of IPO — Anthropic (X)
  4. Espionage scandal hits Nvidia, raising concerns over AI chip reliance — New Scientist AI
  5. Jensen Huang's exit from Nvidia unsettles markets and EU AI talks — Politico Europe Tech
  6. Microsoft 365 outage disrupts Outlook, Teams and Copilot for over a day — Euronews Next
  7. Google Open-Sources TPU Sync and XSE Serving Engine for High-Throughput AI Inference — InfoQ AI/ML
  8. Google opens pre-orders for Gemini-powered smart glasses with Warby Parker and Samsung — Google AI Blog

Get the daily brief of stories like this at 6:30 every morning →