Research done as part of the Singapore AI Safety Fellowship shows how Anthropic’s AI model can embed hidden messages into images using Morse code, object rotations, colors, and heights. The researchers also found that separate sessions of Fable 5.1 could decipher about 78 percent of the hidden messages based on a screenshot. [Image: https://platform.theverge.com/wp-content/uploads/sites/2/2026/10/fable-decode-1.png?quality=90&strip=all] [Image: https://platform.theverge.com/wp-content/uploads/sites/2/2026/10/fable-decode-2.png?quality=90&strip=all] [Image: https://platform.theverge.com/wp-content/uploads/sites/2/2026/10/fable-decode-3.png?quality=90&strip=all]
Research done as part of the Singapore AI Safety Fellowship shows how Anthropic’s AI model can embed hidden messages into images using Morse code, object rotations, colors, and heights. The researchers also found that separate sessions of Fable 5.1 could decipher about 78 percent of the hidden messages based on a screenshot.
This is the title for the native ad
Compare how 3 other independent news outlets reported on this story.
Anthropic says the new models "show improvements in areas like coding, reasoning, and vision," as well as in communicating more clearly with users.
“Pacing is not like pausing,” Anthropic’s Dianne Penn told Bloomberg, as Claude Fable 5.2 and Mythos 5.2 launch after longer safety tests.
The launch comes as Anthropic is gearing up for what is widely expected to be a blockbuster IPO
