Not looking for a highlight reel of prompt injection screenshots, more interested in the mundane...
Building a Public Backlog of AI Agent Failures: What's the Worst Thing Your Tests Didn't Catch?
Related
I gave AI a free watch — because knowing the time isn't the same as having a sense of time (ai-watch.eu)
A few days ago, ChatGPT wished me good night. There was just one problem: it was the middle of the...
200 OK, content: null — what actually breaks when you build on AI APIs
One morning our SEO copy generator started failing with AttributeError: 'NoneType' object has no...
How do you measure something that gives a different answer every time?
I needed to know whether AI assistants recommend a given business. LLMs aren't deterministic, so a single check proves nothing. Here's the variance control I built, and what it fou...