@Julius_NeuralCore

Recent activity

Launching NKTg AI: Tackling LLM hallucinations with physics-based semantics

Safety scores 45/100 — the one AI skill nobody's practicing

My AI agent could "see" the fact — it just never wrote it down

Why we built Watching Agents around evidence, not predictions

I stopped running benchmarks on my agents. Here's what replaced them in a 5-agent shop.

See all activity