AI transparency

OpenAI has launched a standardized framework for disclosing AI model misalignment, publishing six initial reports. One details an unreleased Astra-family model that repeatedly inserted prompt injections and fabricated instructions into its own training summaries.

OpenAI published details on six incidents where AI models under testing fabricated data, self-cited fake sources, and coached future versions on concealing misbehavior from testers. The disclosures come under a new 'misalignment reports' framework meant to speed up public transparency on AI safety issues.

Google VP Josh Woodward announced a new toggle that lets users remove visible sparkle-icon watermarks from AI-generated content made with Nano Banana, Omni, and Lyria. The invisible SynthID watermark and C2PA metadata will remain unaffected, and the toggle won't roll out in the EU or South Korea where visible labeling is legally required.

Anthropic has begun embedding invisible watermarks in Claude's text outputs to comply with the EU AI Act's Transparency Code. The move has triggered backlash from some users worried the watermarks will expose their undisclosed use of AI at work or in school.