55m ago · 5 min read · If you're building AI agents with Model Context Protocol, you have an attack surface you probably haven't thought about yet. It's not your prompts. It's not your model. It's the tool descriptions your
Join discussion
3h ago · 6 min read · If you're building anything with LLMs right now, you need to understand a class of prompt injection that your safety filters almost certainly aren't catching. It's called identity-framing, and a recent example dubbed "The Gay Jailbreak" has been maki...
Join discussion
3h ago · 8 min read · Applied AI Product Management — Part 3. In Part 1, we covered how to choose the right AI approach by working backward from constraints. In Part 2, we explored why offline accuracy doesn't predict onli
Join discussion
