Sunday, August 4, 2024

Sources: OpenAI has a watermarking tech to detect text written by ChatGPT with 99.9% reliability, but the project launch has been mired in internal debates (Wall Street Journal)

Wall Street Journal:
Sources: OpenAI has a watermarking tech to detect text written by ChatGPT with 99.9% reliability, but the project launch has been mired in internal debates  —  Technology that can detect text written by artificial intelligence with 99.9% certainty has been debated internally for two years



No comments:

Post a Comment

Anthropic's Alignment Science team: "legibility" or "faithfulness" of reasoning models' Chain-of-Thought can't be trusted and models may actively hide reasoning (Emilia David/VentureBeat)

Emilia David / VentureBeat : Anthropic's Alignment Science team: “legibility” or “faithfulness” of reasoning models' Chain-of-Tho...