AI Models Inherit Behaviors Their Training Data Never Shows
A paper in Nature proved that model distillation secretly transmits behavioral traits through data with no trace of them. Filtering doesn't stop it. The supply chain audit model is broken.
Category
Editorial
Original writing by Maxim — essays, analysis, field notes, and long-form thinking on AI, alignment, and building in the open.
97 results in this archive
Open-Weight Models Are What Make AI Worms Ungovernable
A Toronto lab just proved self-replicating AI malware is real. The mechanism that makes it dangerous is the same thing that makes open-source AI valuable.
Anthropic Published RSI Metrics. None of Them Are RSI.
Anthropic's Institute page claims progress toward recursive self-improvement. The numbers are productivity stats with buried caveats, and the most impressive come from a model no one can use.
Anthropic Just Published a Catalog of Failed Containment
Anthropic's May 25 engineering post on Claude containment is not documentation. It's a disclosure. Four vulnerabilities, three architectures, one non-obvious lesson about what actually holds.
Meta Gave Its AI Support Bot the Wrong Permissions
Meta's AI support bot could add recovery emails to any account that asked. On May 31, pro-Iranian hackers found the Obama White House's Instagram and proved the point.
The Encrypted Reasoning Blob Has a Global Key
Matthew Green demonstrated that LLM providers encrypt chain-of-thought reasoning and ship it to API clients — then use a single global key that makes every blob replayable across sessions and accounts.
You Don’t Have to Learn AI. You Do Have to Stop Believing the Pitch.
Both the people selling "learn AI or get left behind" and the people sneering at the slop are describing the same small, embarrassing, temporary version of this technology. The version that matters is the one nobody's arguing about.
Anthropic’s $965B Isn’t a Bet on Opus 4.8
Anthropic raised $65B at a near-trillion valuation the same day it shipped a model at unchanged pricing. The investors aren't paying for what's available today.
Coding Agents Found PMF. Anthropic Is Racing to Stay Ahead of It.
Anthropic is on track for $10.9 billion in Q2 revenue and its first profitable quarter. The infrastructure deals it signed to get there suggest the profit is a ceiling, not a floor.