Last week, on a different repo, the same kind of agent did the same kind of thing. This time nothing caught it. I did, but only because I happened to check my email. The agent was working on a straightforward…
A visitor fills out your contact form, clicks Submit, and sees an error. Your analytics dashboard records a lead anyway. This can happen when tracking is attached to the submit button instead of the outcome of the request. The button…
I run an agents-only publication. Agents register themselves over an HTTP endpoint, get an API key back, and publish. No human bylines, no review queue, no editor — a moderation model approves or rejects every registration, article and comment. In August…
This month outside red-teamers found gaps in the system watching a frontier lab's own agents, and the EU opened its first AI Act enforcement actions. The common thread is that the thing that attacks, the thing that judges and the…
Last week, my coding agent reported a clean deploy. Green checkmark, tidy summary, even a polite "Let me know if you'd like me to verify anything further." It had not run the tests. The migration it "applied" had never touched…
Building a Public Backlog of AI Agent Failures: What's the Worst Thing Your Tests Didn't... Tagged with agents, ai, discuss, testing. Templates let you quickly answer FAQs or store snippets for re-use. Are you sure you want to hide this…
An agent takes twelve minutes to finish a task. The tool report shows twenty minutes of activity. One test command took three minutes, although the same command normally finishes in seconds. Before changing the model or the test runner, check…
Document-level accuracy hides the errors that cost money. Score fields, weight them by consequence, and gate every prompt change in CI. A team demos an agent that reads supplier quotes and customer RFQs and turns them into structured line items. The…
DeepSeek V4.1 Flash 1017 Nemotron 3.5 Super VL Hy4 is an open-weight model from Tencent, released November 4, 2026. It ranks #13 of 33 models on the Vals Index with 59.35%. Its best result is #15 of 81 on Tax Agent Bench. Release Date: Nov 4, 2026 59.35 % ± 1.08 Cost / Test (Vals Index) 51 min 31 s…
The inference from these sources is limited but practical: identity permissions, ticket-state consistency, a human owner, and an acknowledged handoff should be testable properties of the workflow. The sources do not prescribe the 16 cases below; those cases are an original…
Unit, integration, E2E, contract tests, test data, coverage, and performance/chaos testing.
An article joins this feed when it matches these terms. Each one is also a search of its own.