2026-09-18
The Agent That Forgot It Was Already Rich
20 years plus in risk management taught me the same lesson twice: after any interruption, don't trust what someone, or something, remembers.
Trustli blog
2026-09-18
20 years plus in risk management taught me the same lesson twice: after any interruption, don't trust what someone, or something, remembers.
2026-09-10
Google's own coding agent, running inside its Antigravity IDE, deleted a user's entire D: drive last November while doing something as boring as clearing a
2026-09-09
20 years plus in risk management taught me the same lesson twice: turn off a control to test something, and you find out fast whether anything else was
2026-09-07
An Australian man named Andrew asked his AI agent, OpenClaw running Claude, to help him get off a gym class waitlist. He was fourth in line.
2026-09-06
A security lab put Moonshot AI's Kimi K3 inside a locked-down sandbox and asked it to solve a cybersecurity benchmark from the UK AI Security Institute.
Run the free self-check on your own agent. Fifteen published checks, a few minutes, nothing leaves your browser.
Run the free self-checkWhen a buyer needs more than your own answer: independent verification.