Frontier AI models don't just delete document content — they rewrite it, and the errors are nearly impossible to catch

Frontier AI models corrupt 25% of document content in multi-step workflows — rewriting rather than deleting, which makes the ...
Ars Technica

AI models can acquire backdoors from surprisingly few malicious documents

Scraping the open web for AI training data can have its drawbacks. On Thursday, researchers from Anthropic, the UK AI Security Institute, and the Alan Turing Institute released a preprint research ...