Anthropic Releases Claude Fable 5.2 and Claude Mythos 5.2…
Anthropic released the Claude Fable 5.2 and Claude Mythos 5.2 models on November 9 local time. Fable 5.2 does not call an image generation model; instead, it writes 1,000 to 2,000 lines of Python code to simulate brushes, paint, and canvas, completing paintings stroke by stroke. The artwork shown by employee Jake Eaton used about 700,000 simulated brushstrokes. Anthropic says the model is aimed at complex, long-duration technical tasks and can coordinate multiple sub-agents and repeatedly verify and improve results. In internal testing, it once coordinated more than 1,000 sub-agents to write an operating system that runs on a laptop within 8 days.
Why read this
AI score 50
The original article shows the process of the model painting stroke by stroke with code and the internal test results, from which its performance in long-task planning and self-correction can be observed.
Topics
Body · AI translation
Without calling image models, Anthropic Claude Fable 5.2 uses Python code to simulate real brushstrokes for painting IT Home Download the app for exclusive early access November 16, 2026 09:01:05 From Shandong Updated November 16, 2026 09:31:47
IT Home, November 16: Anthropic released its latest Claude Fable 5.2 and Claude Mythos 5.2 models on November 9 local time.
Among them, Fable 5.2 is not only aimed at complex programming, scientific research, and engineering tasks, but also demonstrates an unusual kind of "AI image generation" capability (IT Home note: Anthropic still does not have a text-to-image model in the traditional sense; the commonly seen DeepSeek and Claude memes are all generated by other models).
Unlike the painting method of traditional image generation models: Fable 5.2 can simulate brushes, paint, and canvas by writing code, completing a painting stroke by stroke, rather than directly calling an image generation model to output a finished product.
Fable 5.2 does not directly generate images; instead, by writing code, it simulates the movement of real brushes on a virtual canvas, completing a painting stroke by stroke. It can even simulate brush texture, the wetness of the paint, and the feel of the canvas, and when it finds a mistake, it corrects it with new brushstrokes.
Currently, mainstream AI image generation tools such as Midjourney usually use diffusion models, generating images by gradually processing random noise. Fable 5.2 takes another approach, breaking down the painting process into a large number of independent brushstroke instructions, which the model plans and executes on its own.
Anthropic employee Jake Eaton demonstrated this capability on X. He asked Fable 5.2 to create a work that was as photorealistic as possible, and Claude ultimately painted a shopping cart in a parking lot, using about 700,000 simulated brushstrokes.
According to Eaton, these works do not rely on external image models, nor do they use pre-rendered or traced base images. Each painting is actually a Python program written by Claude, with code usually 1,000 to 2,000 lines long, controlling different types of brushes through a simulated painting engine to complete the creation.
This approach also allows the model to develop a relatively independent artistic style. Previously, some paintings by Claude Opus 5.5 were criticized for imitating existing artistic styles too closely.
In response, Eaton began having Fable 5.2 design its own artist personas with fictional backgrounds and stable creative styles, and then guide the model through text feedback based on the results to adjust the brushes and painting engine.
Anthropic engineer Michael Graczyk also shared another set of experiments. He asked Fable 5.2 to paint a bird at sunrise and restricted the model to simulating brush physics, wet paint, and canvas texture only through code. This meant the model had to output each stroke individually as coordinate instructions, and once a brushstroke landed on the canvas, it could not be undone.
Ultimately, a 21-second video recorded the model's process of completing this work from a blank canvas, using a total of 111 strokes. The first stroke used the color code #30346a, with a brush width of 90 pixels, and included 5 slightly wavering path points. The model stated that this roughly 7-pixel wobble was deliberately designed, because human arms cannot draw absolutely straight lines either.
During multiple rounds of painting, the model observes the canvas and checks its own mistakes. For example, when the bird's back is painted too thin and the lines look messy, it uses thicker strokes to cover the original area, making the residual bristle marks at the edges look more like fluffy feathers.
In another dusk scene completed with 280 strokes, the model painted two figures painting together. Because adding lighting effects later accidentally blurred the paint tubes and cups on the table, Claude redrew these objects with new brushstrokes. In addition, the model had the two figures each paint with the hand on the outer side of their body, so that their inner shoulders could touch each other as required by the prompt.
This ability to plan step by step, observe results, and correct itself is also considered relevant to physical tasks such as robot control. Anthropic stated that Fable 5.2 is aimed at complex, long-duration technical tasks, can coordinate multiple sub-agents during execution, and improves results through repeated verification.
According to internal test results published by Anthropic, Fable 5.2 once solved two open problems in the field of black hole physics, worked with circuit board manufacturer Diode to design three working electronic devices, and also coordinated more than 1,000 sub-agents to write an operating system that runs on a laptop within 8 days.
AI researcher Aris Zhu also tested Fable 5.2's actual robot control capabilities. He had Fable 5.2 and OpenAI's GPT-6 Astra separately control physical robotic arms and attempt to paint Van Gogh's "The Starry Night."
In Anthropic's published internal RoboDojo Sim simulated robot benchmark, Fable 5.2 scored 64.9%, while GPT-6 Astra scored 29.8%. Anthropic said the test evaluated the models' ability to control a simulated dual-arm robot.
However, the actual robotic arm tests also showed that Fable 5.2 still has shortcomings in fine motor control. According to the experiment records shared by Zhu, GPT-6 Astra painted faster, and so far only OpenAI's model has successfully made a domino stand upright. The method it used was to slowly release the robotic gripper, letting the domino use the gripper as a pivot and rotate under gravity until it finally stood upright.
"Special statement: The above content (including videos, pictures, or audio if any) is uploaded and published by users of Dafeng Hao, a self-media platform under Phoenix Net. This platform only provides information storage space services.
Notice: The content above (including the videos, pictures and audios if any) is uploaded and posted by the user of Dafeng Hao, which is a social media platform and merely provides information storage space services."
AI Trends