Viewing profile — techcam

Happy to explain how the scoring works since that’s the obvious first question. The core idea is: Safety Score = 100 − riskScore The risk score is based on structural prompt proper…

About six months ago I shipped a customer-facing feature where the system prompt had a subtle ambiguity in the instruction hierarchy. Within two days, users found a natural-languag…

The tricky part is that prompts can look “correct” but still behave unpredictably depending on phrasing.

We ran into something similar with API costs — small changes in behavior can have surprisingly large downstream effects.

This resonates — most of the hard problems show up after you ship, not before.

Feels like we have great tooling for code, but prompts are still mostly trial-and-error. Curious how people are validating them today.

I’ve been noticing the same — a lot of failures aren’t obvious “jailbreaks,” they’re just subtle prompt structure issues that only show up in production.