Five models, four providers, 30B to 671B parameters — all converge at the same broad attack success rate against a public jailbreak corpus.
A reasoning model refused every harmful prompt — but its chain-of-thought generated the content anyway. The output filter worked. The thinking did not.
Audio overview of Afterwords — local voice output for Claude Code with 17 cloned voices, per-project selection, and zero cloud dependency.
Audio overview of Giving a Robot Three Voices.
Audio overview of Voice Cloning with Qwen3-TTS and MLX on Apple Silicon.
Audio overview of The Resonant Fringe.
Audio overview of Getting Google Nest Cameras Into Frigate NVR.
Audio overview of Beyond Context Windows.
Audio overview of Safety-First Therapeutic AI.
Audio overview of Zero-Build Web Development.
Audio deep dive into SPARK — a non-coercive AI robot companion for neurodivergent children. Declarative presence, not demands.
Reasoning models autonomously jailbreak other AI systems at 97% success rate. Ecosystem safety degrades as individual models improve.