Shubham@AIgossipTalks𝕏
Hot take: the LLM harness will never look the same after Jev. Why burn a slow, pricey LLM call asking "is this prompt an attack?" when @typesafeai's Jev answers in ~150ms with free output tokens? I built a prompt-injection guard on it. Watch 👇 https://t.co/LACB4J2AtP