Adrian Wedd

Adrian Wedd episodes

March 19 Voice Cloning with Qwen3-TTS and MLX on Apple Silicon
Audio overview of Voice Cloning with Qwen3-TTS and MLX on Apple Silicon.
18 min
March 18 The Resonant Fringe
Audio overview of The Resonant Fringe.
18 min
March 16 Getting Google Nest Cameras Into Frigate NVR
Audio overview of Getting Google Nest Cameras Into Frigate NVR.
21 min
March 15 Beyond Context Windows
Audio overview of Beyond Context Windows.
11 min
March 15 Safety-First Therapeutic AI
Audio overview of Safety-First Therapeutic AI.
19 min
March 14 Zero-Build Web Development
Audio overview of Zero-Build Web Development.
21 min
March 12 The Robot That Refuses to Give Orders
Audio deep dive into SPARK — a non-coercive AI robot companion for neurodivergent children. Declarative presence, not demands.
44 min
March 11 Alignment Regression: Why Smarter AI Makes All AI Less Safe
Reasoning models autonomously jailbreak other AI systems at 97% success rate. Ecosystem safety degrades as individual models improve.
22 min
March 11 Reasoning Models Think Themselves Into Trouble
Frontier reasoning models are 5–20x more vulnerable to adversarial prompts than non-reasoning models. The thinking process itself is the attack surface.
22 min
March 02 Adversarial Poetry: When Rhyme Bypasses Reason
Audio overview of Adversarial Poetry: When Rhyme Bypasses Reason.
19 min

From the publisher's feed

Audio overviews, deep dives, and long-form conversations on AI, safety, design, and the edges of practice.