AI transparency
2 published articles
Anthropic / Claude5 min read
EU AI Act: marking AI-generated content
Claude's invisible watermark is coming. A full rewrite erases it
Anthropic is adding an invisible watermark to future Claude models to meet EU AI Act rules on marking AI-generated content. It is free and untraceable, but it passes over exact code, short passages, and fully rewritten text.
2026-08-21
AI5 min read
AI interpretability
Your neural network's black-box decisions just got a discoverable memory
Researchers show that neural network action scores can be expressed as exact weighted sums of training-case returns, using Gram geometry. This allows post-training audit signals that identify influential cases, measure action coherence, and flag weak support, without retraining or accessing the original optimization trajectory.
2026-08-03