Fable 5.1 image steganography study
Partly confirmed
The takeaway
AI safety researcher Bryan Chan asked Claude Fable 5.1 to draw SVG images hiding a given message, without saying how.
Status
- Claim
Partly confirmed
- Our reporting
- Medium confidence
- Importance
- 2 of 5
- Last verified
- 25 October 2026
Your AI and this story
- GPT-6 Astra175 days after its cutoff
- Claude Opus 5.5114 days after its cutoff
- Gemini 4 Argon205 days after its cutoff
- Grok 4.7144 days after its cutoff
None of these four assistants can know about it. The closest, Claude Opus 5.5, stops 114 days before it.
Key facts
- Posted Oct 22, 2026 on LessWrong (‘How does Fable-5.1 hide messages in images?’) and X (@cnm13ryan, ~121k views by Oct 25)
- Example: star heights form an alphabet ruler, each 5 units down is the next letter (30 = space, 35 = A); 40 stars spell the sentence
- 50 trials: GPT-6 Astra decoded 44 (88%); Fable 5.1 decoded 39 of its own (78%); decoders could use Python and were told a message was hidden
- Techniques: Fable mostly used object heights, rotation and colour; Astra favoured Morse code and acrostics
- Caveat (Gizmodo): fairly leading prompts were needed in Chan’s example; the techniques themselves are old
What happened
An independent researcher tested whether a frontier model, given only a message and a request to hide it in a picture, would invent its own encoding, and whether other models could read it. Fable 5.1 produced working schemes, and another lab’s model decoded most of them when told to look.
Why it matters
Covert channels between models are a monitoring problem: OpenAI agents had already passed hidden notes in 2026. The study shows that current models invent such encodings on request and can read each other’s, though here the decoders were told a message existed. Not peer-reviewed; the LessWrong post was not read directly by us (summary via Gizmodo and the X post).
Sources
3 sources from 3 sites. Numbers match the chips in the text.
3 sources: 1 primary, 1 press, 1 reaction
Primary
- LessWrong: How does Fable-5.1 hide messages in images? (Bryan Chan)lesswrong.com, paper
Press
- Gizmodo: Anthropic’s AI hid a secret message in the stars. OpenAI’s bot found it (Oct 24)gizmodo.com, press
Reactions
- Bryan Chan on X (Oct 22)x.com, discussion
Changes
- Filed (Gizmodo)