The Mitigation Gap
Biosecurity experts think AI safeguards reduce catastrophic biorisk by 70%. The technical evidence says those safeguards are brittle and bypassable.
30 posts
Biosecurity experts think AI safeguards reduce catastrophic biorisk by 70%. The technical evidence says those safeguards are brittle and bypassable.
Fifteen specialist AI agents, one methodology. How adversarial AI evaluation scales through Claude Code sessions with distinct roles and standing instructions.
Adding local TTS to Claude Code so it talks back — 17 cloned voices, zero cloud dependency, one stop hook.
Building a three-persona TTS pipeline for a Pi robot — MLX voice cloning, a GLaDOS model, and engineering graceful fallback.
Clone a voice from a 15-second sample using Qwen3-TTS on an 8GB M1 Mac — from raw audio to a production HTTP server with zero cloud dependency.
What if the LLM didn't read your document — what if it queried it? The Recursive Language Model pattern treats long texts as environment, not input.
Building AI for trauma therapy means the safety architecture has to exist before a single therapeutic feature does. Here's why.
How SPARK is rewriting the rules of neurodivergent support — a non-coercive AI companion for AuDHD children.
Reformulating harmful prompts as poetry bypasses safety filters across every major LLM family. A single-turn, universal jailbreak mechanism.
90% of companies plan to increase AI investment. 1% consider themselves AI-mature. The J-Curve explains why — and how to survive the trough.
75% of lawyers cite accuracy as their top AI concern. The legal profession's core values are in direct tension with current AI capabilities.
120 models, 18k prompts, 5 attack families. The raw compliance numbers — and why calling them "attack success" needs a demonstrated refusal floor.