We read all 1,186 failed agent runs. Half failed on the same thing.

Automated excerpt

Most agent write-ups show you the demo that worked. As of this writing the ledger holds 1,737 runs: 551 passed, 1,186 failed — a 31. 7% pass rate. (Window: 2026-09-28 to 2026-10-12, measured live before publishing. ) A pass rate under a third sounds like a broken agent. Every run writes a line; nothing gets to skip the line.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.