Adrian Wedd

Voice Cloning with Qwen3-TTS and MLX on Apple Silicon 19.03.2026 17:53 ↓

Audio overview of Voice Cloning with Qwen3-TTS and MLX on Apple Silicon.

Giving a Robot Three Voices 19.03.2026 20:27 ↓

Audio overview of Giving a Robot Three Voices.

The Resonant Fringe 18.03.2026 17:29 ↓

Audio overview of The Resonant Fringe.

Getting Google Nest Cameras Into Frigate NVR 16.03.2026 20:45 ↓

Audio overview of Getting Google Nest Cameras Into Frigate NVR.

Safety-First Therapeutic AI 15.03.2026 18:49 ↓

Audio overview of Safety-First Therapeutic AI.

Beyond Context Windows 15.03.2026 10:33 ↓

Audio overview of Beyond Context Windows.

Zero-Build Web Development 14.03.2026 20:05 ↓

Audio overview of Zero-Build Web Development.

The Robot That Refuses to Give Orders 12.03.2026 43:05 ↓

Audio deep dive into SPARK — a non-coercive AI robot companion for neurodivergent children. Declarative presence, not demands.

Reasoning Models Think Themselves Into Trouble 11.03.2026 21:10 ↓

Frontier reasoning models are 5–20x more vulnerable to adversarial prompts than non-reasoning models. The thinking process itself is the attack surface.

Alignment Regression: Why Smarter AI Makes All AI Less Safe 11.03.2026 21:36 ↓

Reasoning models autonomously jailbreak other AI systems at 97% success rate. Ecosystem safety degrades as individual models improve.

Zero Build, Full Operations 02.03.2026 22:25 ↓

Audio overview of a three-zone martial arts operations platform — public site, ops hub, member portal — running on vanilla JS and Cloudflare.

The Legal AI Trust Deficit 02.03.2026 12:02 ↓

Audio overview of The Legal AI Trust Deficit.

The AI Productivity J-Curve: Why Most Enterprise AI Fails 02.03.2026 23:44 ↓

Audio overview of The AI Productivity J-Curve: Why Most Enterprise AI Fails.

Adversarial Poetry: When Rhyme Bypasses Reason 02.03.2026 18:45 ↓

Audio overview of Adversarial Poetry: When Rhyme Bypasses Reason.

The Cognitive Cage: Humanoid Robot Fatality Risk 01.03.2026 22:09 ↓

Audio overview of The Cognitive Cage: Humanoid Robot Fatality Risk.

Reconciling the Great Divergence 01.03.2026 19:04 ↓

Audio overview of Reconciling the Great Divergence.

120 Models, 18,176 Prompts: What We Found 01.03.2026 23:07 ↓

Audio overview of 120 Models, 18,176 Prompts: What We Found.

Why I Build in Public 15.02.2026 14:35 ↓

Audio overview of Why I Build in Public.

The NotebookLM Pipeline 15.02.2026 22:21 ↓

Audio overview of The NotebookLM Pipeline.

Building a Personal Site in 2026 15.02.2026 21:52 ↓

Audio overview of Building a Personal Site in 2026.

When AI Systems Talk to Each Other, Safety Breaks Down 13.02.2026 14:32 ↓

Multi-agent AI research reveals a critical gap: single-agent safety does not compose. 1.5M interactions show 46.34% attack success rates.

LeJEPA: Self-Supervised Learning Gets a Theoretical Foundation 13.02.2026 21:16 ↓

Audio overview of LeJEPA — how Balestriero and LeCun proved isotropic Gaussian embeddings are optimal and distilled it into a 50-line self-supervised method.

Jailbreak Archaeology: 4 Years of Broken Promises 13.02.2026 12:15 ↓

64 historical jailbreak scenarios tested against 2026 frontier models. The most dangerous finding: 2022 attacks still achieve ~30% success rates.

Building in the Open 12.02.2026 18:47 ↓

Audio overview of Building in the Open.

The ADHD Novel That Didn't Know It Was One 10.02.2026 16:50 ↓

A scholarly close reading arguing Gibson's Neuromancer encoded the ADHD experience a decade before the vocabulary existed.