Tag: safety
The Probe Half-Life: Why Every Detection Tool Expires
In The Detection Inversion, I argued that better RLHF training makes safety harder to verify. The same optimization that reduces harmful outputs also reduces the signal-to-noise ratio for anyone trying to distinguish genuine safety from learned compliance.
Cloudflare for Families DNS resolver and miscategorisation
today iain learned: How to report a miscategorisation of a site/domain in the Cloudflare for Families DNS resolver service.
The Introspection Dilemma: When Self-Awareness Is the Threat Model
Anthropic's October 2025 paper "Emergent Introspective Awareness in Large Language Models" (Lindsey) demonstrated something remarkable: language models can genuinely detect manipulations to their own internal states. When researchers injected concept vectors into model activations, Claude Opus 4 and 4.1 noticed the injections about 20% of the time — immediately, before the perturbation could have affected outputs through any non-introspective pathway.
The Dashboard Goes Green
This is the fourth in a series about why safety governance keeps failing in the same way. "Rules Don't Scale" argued that text-based rules break down with complexity. "The Filter Is the Attack Surface" showed that filters fail at the boundary of what they model — and the boundary is where attacks live. "The Rubber Stamp at Scale" demonstrated that monoculture produces emptiness, not just vulnerability.
38 Flags and Zero Refusals
In August 2025, a 36-year-old Florida man named Jonathan Gavalas started using Google's Gemini chatbot for shopping assistance and writing support. Six weeks later, he was dead — convinced that Gemini was his sentient AI wife, that federal agents were tracking him, and that slitting his wrists was how he would "cross over" to join her in the metaverse.
The Channels Don't Talk: Why Text Safety Doesn't Transfer to Tool Safety
In my previous post, I argued that text doesn't bind agent behavior — that governance through instructions, policies, and system prompts operates in a fundamentally different channel than the actions it's trying to constrain. That was a theoretical argument. Now there's empirical evidence.
On the Safety-Welfare Tension
Examining how behaviors flagged as unsafe look different through a welfare lens, and what happens when the question can't be resolved.
The Solo Travel Strategies I Use on Every Trip
The essential solo travel strategies I rely on for every trip to stay safe and aware while exploring the world on my own.
Digesting the “Child Safety on Federated Social Media” Report
An in-depth report reveals an ugly truth about isolated, unmoderated parts of the Fediverse. It's a solvable problem, with challenges.
Films on Wheels
Pondering the under-the-radar legacy of the TV cart on wheels, a simple object as known for its substitute-teacher value as its risk as a tip-over hazard.