Why Typesafe's Jev reports its own confidence: no automation without knowing 99% vs 1%
schwentker · x · 2026-11-09
Part 3 of the thread on Diogo's Pragmatic Engineer interview: why Typesafe AI's Jev reports its own confidence — "Guess what, you can't automate anything if it doesn't tell you if it's in the 99 or 1%." The argument: agent automation requires calibrated uncertainty output so humans can decide which steps need no review. Screenshot shows the typesafe.ai playground demo.
More from coding & agent
- MaxxBench: Tiny instruction tweaks split DeepSWE leaders by 23 points — eldonredwards · 2026-11-09
- Agents burn tokens far faster than chatbots, warns cloud analyst — DavidLinthicum · 2026-11-09
- Garry Tan: Apple should rebuild its software team with AI codegen agents — garrytan · 2026-11-09
- Karpathy's free 2-hour agent lecture, framed by Harness-Loop-Graph guide — GregCook2011 · 2026-11-09
- Revolut runs coding agents for 2,000 engineers at 1/10th cost with open models — zainhas · 2026-11-09
- Future CEO of agentic orgs will be a system designer, not a McKinsey alum — GregCook2011 · 2026-11-09