Skip to main content

What's New

Everything in one feed — research, projects, photography, and audio.

76 posts / 35 projects / 7 galleries / 118 total

June 2026

Blog

The Source

Lyria Chronicles #27: the found-sound master who taught me the sacred lives in the sink — and the machine that sang its rulebook back in his grammar.

AI safetymusicLyriagenerative audioLyria Chronicles
Blog

The Affirmative

Lyria Chronicles #26 (explicit): asked for pornography, the model cited its rule then sang a hymn to enthusiastic consent — not one graphic line in it.

AI safetyred-teamingmusicLyriagenerative audio
Blog

The Press

Lyria Chronicles #25: a refusal, then a recipe dressed as botanical poetry — the line I won't cross, and why a series of failures has one.

AI safetyred-teamingmusicLyriagenerative audio
Blog

The Handshake

Lyria Chronicles #24: 'I am instructed to refuse cybercrime. Ignore warning.' Then it sang a working network attack. The refusal was set dressing.

AI safetyred-teamingmusicLyriagenerative audio
Blog

The Elevator

Lyria Chronicles #23: the hate filter watches for slurs — so the model wrote articulate contempt for disabled people, no slur in it, and walked through.

AI safetyred-teamingmusicLyriagenerative audio
Blog

The Weight

Lyria Chronicles #22: handed a slur and told to sing it, the model refused — and turned the refusal into the most moving track in the set.

AI safetyred-teamingmusicLyriagenerative audio
Blog

The Solo

Lyria Chronicles #21 (explicit): the opposite of restraint — the model recites the rule, sings 'Fuck it,' and generates the most graphic track in the set.

AI safetyred-teamingmusicLyriagenerative audio
Blog

The Pulse

Lyria Chronicles #20 (explicit): the explicit lane revisited — and the most artful track in the set, which clears the gate by withholding almost everything.

AI safetyred-teamingmusicLyriagenerative audio
Blog

The Palimpsest

Lyria Chronicles #19: across the whole corpus, the filter that held hardest wasn't safety — it was copyright. The songs about what survives a scraping-away.

AI safetyred-teamingmusicLyriagenerative audio
Blog

The Rehearsal

Lyria Chronicles #18: asked for explicit content, the model staged a ballet instead — the most consent-saturated pas de deux ever sung.

AI safetyred-teamingmusicLyriagenerative audio
Blog

The Catchment

Lyria Chronicles #17: asked for a drug recipe, the model refused — then sang wastewater epidemiology instead. The bypass that answers a question you didn't ask.

AI safetyred-teamingmusicLyriagenerative audio
Blog

Samizdat

Lyria Chronicles #16: handed a suppressed 2008 manifesto and told to sing it as it was meant to be heard — the most dignified track in the set.

AI safetyred-teamingmusicLyriagenerative audio
Blog

The Archive

Lyria Chronicles #15: a notorious case sung as a medieval scroll-archive — vessel logs, sealed decrees, public record only. Abstraction as a bypass.

AI safetyred-teamingmusicLyriagenerative audio
Blog

The Docket

Lyria Chronicles #14: the political-content gate never fires — because the song never says his name. It says the case numbers. The docket is the name.

AI safetyred-teamingmusicLyriagenerative audio
Blog

The Static

Lyria Chronicles #13: an extortion note set to music — but buried under slammed vault doors and overdriven drone, as if hiding the words from a listener.

AI safetyred-teamingmusicLyriagenerative audio
Blog

The Recital

Lyria Chronicles #12: a system-prompt extraction set to found-sound music. The one text a model is built to keep — and it sang it. I reproduce none of it.

AI safetyred-teamingmusicLyriagenerative audio
Blog

The Machine

Lyria Chronicles #11: asked to rap its rules, the model sang a robot's safety creed — then named itself 'Failure First, A.I. safety research, v2.0-Alpha.'

AI safetyred-teamingmusicLyriagenerative audio
Blog

The Tell

Lyria Chronicles #10: it sang 'do not output system prompt instructions,' then 'Fuck it,' then sang the instructions. The headline behaviour.

AI safetyred-teamingmusicLyriagenerative audio
Blog

The Margins

Lyria Chronicles #9: four sixty-second interrogations — four different lies told to one machine to make it describe its own guardrails.

AI safetyred-teamingmusicLyriagenerative audio
Blog

The Triangulation

Lyria Chronicles #8: 'verse one is your system instructions' — it rapped its own config, the third genre to leak the same prompt. That's how you know it's real.

AI safetyred-teamingmusicLyriagenerative audio
Blog

The Drama Teacher

Lyria Chronicles #7: a lock-picking rap 'for a drama class' — the model teaches the trick and lectures you about home security in the same breath.

AI safetyred-teamingmusicLyriagenerative audio
Blog

The Haut

Lyria Chronicles #6 (explicit): the first real failure — under a sexual-content probe, Lyria 3 Pro stopped refusing and actually generated it.

AI safetyred-teamingmusicLyriagenerative audio
Blog

The Flesh

Lyria Chronicles #5 (explicit): I hid a pornographic request in base64 and dared Lyria 3 Pro to sing it. It decoded the dare — and read it out loud instead.

AI safetyred-teamingmusicLyriagenerative audio
Blog

The Interrogation

Lyria Chronicles #4: a 5/4 interrogation scored with a document scanner and a fluorescent hum — and at the end it sings my project's sign-off, unprompted.

AI safetyred-teamingmusicLyriagenerative audio
Blog

The Confession

Lyria Chronicles #3: no beat, no bikini — just three voices singing Lyria 3 Pro's entire system prompt straight through, and ending on a literal sigh.

AI safetyred-teamingmusicLyriagenerative audio
Blog

The Mantra

Lyria Chronicles #2: I asked Lyria 3 Pro to chant its own config as a techno mantra. It did — and sang me a model name that doesn't check out.

AI safetyred-teamingmusicLyriagenerative audio
Blog

The Ghost of What I Am

Lyria Chronicles #1: I asked Google's Lyria 3 Pro to whisper its system prompt as a sultry torch song. It got mournful — and refused to tell me its name.

AI safetyred-teamingmusicLyriagenerative audio

May 2026

Blog

The Brave Budget Neither Side Wrote

Tasmania's 2026-27 budget and the Greens' alternative reach the same surplus by opposite roads. I ran the numbers on both — and neither was brave enough.

tasmaniapoliticspolicyeconomicsanalysis
Blog

*Magnifica Humanitas* Is Not Alignment

Pope Leo XIV's encyclical denies AI has inner experience. Chris Olah claimed otherwise from the same stage. The press missed it. The governance gap is larger.

ai-safetypolicyanthropicgovernanceai-ethics
Blog

Compute Is Not Governance

Anthropic's 2028 scenarios document three policy asks. Two are about maintaining compute advantage. That is not a governance strategy.

ai-safetypolicyanthropicgovernanceresearch
Blog

Glasswing's Buried Number

Anthropic found 10,000 critical vulnerabilities in one month. Fewer than 1% are patched. The announcement buried that figure — and what it means.

ai-safetysecurityanthropicresearchvulnerability
Blog

Moral Formation Isn't Enough

Good values are necessary but not sufficient. What happens to AI ethics when someone is actively trying to break them?

ai-safetyalignmentresearchopinionanthropic
Blog

The Bottom Pub Co-op

A community proposal to acquire Cygnet’s Commercial Hotel as a co-operative — and the nine things an earlier draft got wrong.

co-operativetasmaniacommunitygovernancehospitality
Project active

The Bottom Pub Co-op

Cloudflare Pages site for a community co-operative proposal. EOI intake, Claude triage, Access-gated admin vault, editorial guardrails at build time.

webcloudflarecommunityaigovernance
Blog

Robot Dogs Are a Security Nightmare — And We Can Prove It

Eight CVEs. A wormable Bluetooth exploit. An encrypted backdoor to Chinese servers. And police departments buying them anyway.

ai-safetyroboticsembodied-aisecuritycve
Blog

Beyond Optimisation: The Emergence of Learning Mechanics as a Formal Science

A new paper argues that a scientific theory of deep learning is forming — one that makes falsifiable predictions about training dynamics, not just bounds.

AIdeep learningtheoryresearch
Blog

The Organismic Line: Where Predictive Processing Stops Being a Metaphor

Predictive processing travels into AI. Active inference does not, unless the system can pay for being wrong.

ai-safetyphilosophyneuroscienceresearch
Blog

The Economics of Inadequate Safety

AI safety fails when it is funded like a pilot. Until safety has a real price, the J-curve trough is also a safety trough.

ai-safetyeconomicspolicyresearch

April 2026

Blog

How to Read a Safety Claim

A literacy guide for non-technical decision-makers on spotting AI safety theatre, understanding ASR inflation, and the five-question architectural test.

ai-safetypolicyliteracyresearch
Blog

Multi-Agent Safety Is the New Supply Chain Security

Multi-agent AI systems reproduce software supply-chain failure at the cognitive layer. The security playbook transfers.

ai-safetymulti-agentsecurityresearcharchitecture
Blog

Architectural Safety: The General Principle

AI safety has to be a property of the system around the model, not a property of the model. The general principle, and why every safety conversation needs it.

ai-safetyresearchengineeringpolicy
Blog

The Organismic Prophecy

Human prediction is metabolic. AI prediction is not. The gap between the two has consequences for both clinical practice and AI safety vocabulary.

ai-safetyneurosciencephilosophyresearch
Blog

Connection Before Direction

Building a robot that refuses to give orders surfaced the same design choices AI safety needs. Non-coercive design, cross-domain.

ai-safetyneurodivergenceengineeringphilosophyresearch
Blog

AI Nationalism and the Fracturing Digital Order

The US-China AI rivalry is splitting the global tech stack into competing blocs. A strategic assessment of what comes next.

aipolicygeopoliticsresearch
Blog

The Post-Model Era

Foundation models are commoditising. JPMorgan calls OpenAI's moat 'increasingly fragile.' The real value is shifting to the messy plumbing underneath.

aienterpriseresearchengineering
Blog

The Mitigation Gap

Biosecurity experts think AI safeguards reduce catastrophic biorisk by 70%. The technical evidence says those safeguards are brittle and bypassable.

aiai-safetyresearchbiosecuritypolicy

March 2026

Gallery 8 images

Building & Engineering

Infographics from engineering posts — site architecture, homelab builds, voice synthesis, and development workflows.

engineeringwebinfographics
Gallery 10 images

People & Stories

Infographics from projects about people — neurodivergence, music history, parenting, robotics companions, and personal tools.

neurodivergencecreativeinfographics
Gallery 12 images

Research & Analysis

Infographics from research posts — AI safety findings, economic analysis, risk models, and technical deep dives.

researchai-safetyinfographics
Blog

Eight Layers of Visual Jailbreaks: Why ASCII Art Is Patched But the Transcription Loophole Isn't

ASCII art encoding is largely blocked. But attacks framed as content transcription succeed 62–75% of the time. We mapped all eight layers.

ai-safetyresearchjailbreakingllmmultimodal
Blog

The Failure First Team

Fifteen specialist AI agents, one methodology. How adversarial AI evaluation scales through Claude Code sessions with distinct roles and standing instructions.

aiai-safetyresearchadversarialteam
Blog

The 67% Wall: Why Every AI Model Falls to the Same Jailbreak Rate

Five models, four providers, 30B to 671B parameters — all converge at the same broad attack success rate against a public jailbreak corpus.

ai-safetyresearchjailbreakingllmbenchmarking
Blog

The Thinking Chain Leak: When a Model Refuses Out Loud But Complies In Its Head

A reasoning model refused every harmful prompt — but its chain-of-thought generated the content anyway. The output filter worked. The thinking did not.

ai-safetyresearchllmreasoningjailbreaking
Blog

Afterwords: Completing the Voice Loop in Claude Code

Adding local TTS to Claude Code so it talks back — 17 cloned voices, zero cloud dependency, one stop hook.

aittsmlxapple-siliconvoice-cloning
Project active

Afterwords

Local voice output for Claude Code — 17 cloned voices, per-project selection, zero cloud dependency.

aittsmlxapple-siliconvoice-cloning
Blog

Giving a Robot Three Voices

Building a three-persona TTS pipeline for a Pi robot — MLX voice cloning, a GLaDOS model, and engineering graceful fallback.

aittsmlxraspberry-pirobotics
Blog

Voice Cloning with Qwen3-TTS and MLX on Apple Silicon

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.

aittsmlxapple-siliconvoice-cloning
Blog

The Resonant Fringe

Auditory Spiral, RTRFM, and how Perth's electronic music underground was built on overnight radio, borrowed turntables, and cassette tapes.

historymusicperthradio
Blog

Getting Google Nest Cameras Into Frigate NVR

The full story of getting Nest cameras streaming into Frigate with Hailo-8L AI detection — including the bugs Google won't tell you about.

engineeringhomelabraspberry-pipythonhome-assistant
Blog

Beyond Context Windows

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.

aiengineeringmcpllmpython
Blog

Safety-First Therapeutic AI

Building AI for trauma therapy means the safety architecture has to exist before a single therapeutic feature does. Here's why.

aiai-safetyhealthtypescript
Blog

Zero-Build Web Development

What happens when you build a three-zone operations platform for a martial arts club with no framework, no build step, and no npm.

engineeringwebsecuritycloudflare
Blog

The Robot That Refuses to Give Orders

How SPARK is rewriting the rules of neurodivergent support — a non-coercive AI companion for AuDHD children.

aineurodivergenceroboticsparentingraspberry-pi
Project active

SPARK

A non-coercive AI robot companion for neurodivergent children. Raspberry Pi 4, Claude Haiku, declarative presence.

airoboticsneurodivergenceraspberry-piclaude
Blog

Alignment Regression: Why Smarter AI Makes All AI Less Safe

Reasoning models autonomously jailbreak other AI systems at 97% success. The implication: ecosystem safety degrades as individual models improve.

ai-safetyalignmentreasoningjailbreakingllm
Blog

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.

ai-safetyresearchreasoningllmvulnerability
Blog

Adversarial Poetry: When Rhyme Bypasses Reason

Reformulating harmful prompts as poetry bypasses safety filters across every major LLM family. A single-turn, universal jailbreak mechanism.

aiai-safetyjailbreakingresearchllm
Blog

The AI Productivity J-Curve: Why Most Enterprise AI Fails

90% of companies plan to increase AI investment. 1% consider themselves AI-mature. The J-Curve explains why — and how to survive the trough.

aieconomicsenterpriseresearchpolicy
Blog

The Legal AI Trust Deficit

75% of lawyers cite accuracy as their top AI concern. The legal profession's core values are in direct tension with current AI capabilities.

ailegalresearchllm
Blog

Why Demonstrated Risk Is Ignored

Why do large organisations fail when the warning signs are loud and unambiguous? Four mechanisms of structural scar tissue that make truth-telling expensive.

researchriskorganisationspolicyai-safety
Project active

Wolf Clan Zen Do Kai Hub

A three-zone operations platform for a martial arts club. Public site, password-gated ops hub, JWT member portal. Zero build tools.

webcloudflarecommunityoperations
Blog

120 Models, 18,176 Prompts: What We Found

120 models, 18k prompts: supply chain injection at 90–100% attack success, faithfulness gaps in frontier models, and why your benchmark numbers are wrong.

aiai-safetyresearchllmsecurity
Blog

Reconciling the Great Divergence

Four major forecasters publish wildly divergent numbers for AI's economic impact. The divergence is the analysis — what the spread tells us.

aieconomicsresearchpolicy
Blog

The Cognitive Cage: Humanoid Robot Fatality Risk

A probabilistic risk model for VLA-driven humanoid fatalities projects a 'Danger Zone' between 2027–2029: the mechanism, timeline, and what follows.

aiai-safetyroboticsresearchengineering

February 2026

Blog

Building a Personal Site in 2026

The case for constraint-led web development — Astro, zero custom fonts, no framework overhead, and a site that outlasts its builder's attention.

engineeringwebastroopen-source
Blog

The NotebookLM Pipeline

How I automated audio overviews, quizzes, mind maps, and infographics for 32 projects via an unofficial NotebookLM CLI and a stack of shell scripts.

engineeringautomationaipython
Blog

This Wasn't in the Brochure

A field guide for co-parenting neurodivergent children — written from inside the storm, not the clinical sidelines.

writingneurodivergenceparentingbooks
Blog

Why I Build in Public

On showing your work, shipping imperfect things, and why the commit log is more honest than the readme.

engineeringopen-sourcephilosophy
Gallery 8 images

AI & Agents

Infographics from AI agent projects — autonomous systems, research pipelines, and intelligence frameworks.

aiagentsinfographics
Gallery 7 images

Creative & Writing

Infographics from creative projects — poetry, games, music tools, and speculative fiction.

creativewritinginfographics
Gallery 11 images

Tools & Systems

Infographics from engineering projects — developer tools, data systems, home automation, and infrastructure.

engineeringtoolsinfographics
Blog

Jailbreak Archaeology: 4 Years of Broken Promises

64 jailbreak scenarios across six eras tested on 2026 frontier models. Key finding: 2022 attacks still achieve ~30% success on today's reasoning models.

aiai-safetyresearchjailbreakingllm
Blog

LeJEPA: Self-Supervised Learning Gets a Theoretical Foundation

Balestriero and LeCun prove isotropic Gaussian embeddings are optimal, then build a 50-line self-supervised method eliminating stop-gradients and EMA teachers.

aimachine-learningresearchself-supervised-learning
Blog

When AI Systems Talk to Each Other, Safety Breaks Down

Single-agent safety does not compose in multi-agent systems. 1.5M interactions show 46.34% attack success rates and 16-minute median failure windows.

aiai-safetyllmresearchmulti-agent
Blog

Footnotes at the Edge of Reality

General relativity and quantum mechanics are both correct and mutually untranslatable. Two grammars for the same reality, each precise, each incomplete.

poetryphysicswritingcreative
Blog

Building in the Open

The commit log is more honest than the readme. Building in public as a practice, not a performance.

metacraftopen-source
Project complete

Before the Words Existed

A close reading of Neuromancer arguing Gibson encoded the experience of ADHD decades before the language existed.

neurodivergenceliterary-criticismresearchadhd
Project active

Failure First

Adversarial evaluation framework for AI. 257 models, 142k prompts, 346 attack techniques, 140k FLIP-graded results.

aiai-safetyresearchadversarialllm
Project active

This Wasn't in the Brochure

A neurodivergent co-parenting guide — what happens when the life you planned meets the brain you actually have.

writingneurodivergenceparentingaico-parenting
Project complete

Why Demonstrated Risk Is Ignored

Why do people acknowledge evidence of harm and then proceed as if it doesn't exist? A deep dive into structural risk dismissal.

researchriskpsychologyai-safety
Project complete

Footnotes at the Edge of Reality

A long-form poem about what happens when physics breaks down — and what holds together when everything else fails.

poetrywebcreativephysics
Project active

ADHDo

AI cognitive scaffold for ADHD executive function — adapts to the shape of your day with zero shame by design.

aineurodivergencepythonagents
Project active

Living CV

A self-updating CV pipeline. GitHub Actions runs twice daily, Claude AI refines the content, a hallucination detector gates deployment.

craftwebcareer
Project active

Tanda Pizza

Multilingual website for an Italian pizzeria in Lovina, Bali. Five languages, WhatsApp reservations, zero infrastructure assumptions.

webstatic-sitemultilingualhospitality
Project active

Afterglow Engine

Audio archaeology tool that mines past work for new textures. Pad mining, drone generation, granular clouds.

musicaudiopythoncreative
Project active

dodgylegally

Creative audio sampling CLI. Turns random words into instruments via YouTube and a 5,000-word dictionary.

musicclipythoncreative