Treat Your LLM Like a Threat Actor | Prompt to Prod - with Assaf Kipnis
Assaf Kipnis spent 13 years hunting adversaries at LinkedIn, Facebook, Google and ElevenLabs. Now he builds with AI the same way he hunted them — by assuming the model is a threat actor and writing code for everywhere it might go that you didn't ask for.
Assaf and Aaron get into what it actually takes to build something you'd hand a client: why hallucinations are the wrong fear and agent decisions are the real one, why most of what he produces is code even though AI writes all of it, and the test he runs before reaching for a model at all — could I have done this 10 years ago? He walks…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.