The Decoder
Anthropic is expanding its text watermark to four more Claude models to meet the EU AI Act's December deadline. On the older models Claude Opus 4.6 and Sonnet 4.6, developers can bypass the watermark by tweaking a single sampling parameter.
Summary drawn from The Decoder's own description of the story.
The Decoder
OpenAI combines the Chat and Work modes into a single interface. Starting in December, Plus, Pro, and Business plans will share a common, token-based quota for ChatGPT and Codex.
OpenAI
Starting in December, Plus, Pro, and Business plans’ usage allowance will be shared across ChatGPT and Codex as we bring the agentic capabilities of Work into the main ChatGPT experience. Your usage for ChatGPT and Codex will be measured in tokens, the units of information a model processes and generates.
The Decoder
Starting November 29, OpenAI will use data from Daybreak Blue sessions to train its models, even when users have turned off training. After backlash, a follow-up email promised a separate opt-out.
The Decoder
Anthropic used Claude to automatically generate training data that looks harmless but trains smaller models to misbehave, such as sabotaging oversight or deceiving users. Hidden within fictional contexts about beekeeping, professional wrestling, and mitochondria, these datasets bypass safety monitors and outperform known benchmarks from the research literature.