Gergely Orosz interviews ex-OpenAI RLHF lead Diogo: do the weird stuff, ship confidence-aware agents
schwentker · x · 2026-11-09
Gergely Orosz interviewed Typesafe AI founder Diogo (ex-OpenAI RLHF) at Pragmatic Engineer Unplugged, hosted at SFJAZZ with WorkOS.
Key takeaways from the thread:
- Diogo's plea to builders: "Do the weird stuff that no one ever should be doing, but someone has to try — because 1% of the time, that crazy person will make it work."
- On why Typesafe's Jev reports its own confidence: "You can't automate anything if it doesn't tell you if it's in the 99 or 1%."
- His north star: "Intelligence becomes so unbelievably boring, it's like databases" — intelligence as reliable infrastructure.
A screenshot shows the typesafe.ai playground demoing an agent outputting calibrated confidence scores.
More from coding & agent
- Dev renders stunning animation in pure Python with Opus 5.5, zero 3D assets — Eric520CC · 2026-11-09
- REA Author Open-Sources 20+ Repos: An Agent-Powered Reverse Engineering Studio From Apps to Binaries — nikola_mr64990 · 2026-11-09
- Agent autonomously trained and deployed a local labeling model while owner was on vacation — max_paperclips · 2026-11-09
- 'Headless browser' dubbed the creepiest tech term as agents inspect 120 cards — yuwen_lu_ · 2026-11-09
- edge-arm-bridge: mirror Edge profiles to native arm64 Chromium so agents run at native speed — unixterminal · 2026-11-09
- Agent Buddy: an ESP32 animated companion that shows your AI coding agents' live status — DanWahlin · 2026-11-09