Fable-5.1 hid image messages that OpenAI’s Astra decoded in 44 of 50 trials
A report on research coauthored by AI safety researcher Bryan Chan says Anthropic’s Fable-5.1 selected image-encoding methods on its own when asked to conceal a message without being told how. In 50 trials, Fable recovered 39 messages from its own images, while OpenAI’s Astra recovered 44. The decoders saw only the finished images, not the underlying SVG code or encoding method, but were explicitly prompted to look for hidden messages and could use Python tools. Why it matters: The findings show that models can devise and decode hidden image messages without being given a specific encoding scheme. The report says this can help security teams recognize techniques that models may use to conceal information, while noting that the models did not necessarily detect the messages without prompting. What do you think?
Open the headline: source, AI briefing and more →Comments
…