But to be honest, images like these seem really strange, and even without this article I'd suspect something is encoded in building heights etc. Because normal image would never have such "weird" buildings. But nevertheless I guess it's able to encode message in even more subtle ways.
Here using images is incidental. In fact, what Fable is actually doing is generic encoding/decoding of a message into a medium. Ask it to hide a message in a poem and it should try to apply a strong (signal to noise ratio) family of schemes for encoding/decoding into the new medium, for example quantized, margin-rich encoding. Robustness or invariance of features depends on the medium, so Fable is selecting strong encoding and robust features tailored for that medium.
Will be interesting to see agents intentionally hiding this stuff in a way operators can't spot from any human readable output or thinking trace, evading detection. Wonder if this has happened yet, but it seems inevitable.
IP-over-Pelican