@mattshumer_

–

12 June 2026 23h11

It's still in progress too! Currently dozens of sub-agents are working on dramatically improving the visual fidelity.

12 June 2026

Fable one-shots entire Hogwarts castle with all details

By

–

12 June 2026 23h11

Fable one-shotted this ENTIRE Hogwarts castle, complete with classrooms, the Great Hall, Quidditch pitch, everything pic.twitter.com/E6b8CgaHIf
— Matt Shumer (@mattshumer_) 12 juin 2026

Fable one-shotted this ENTIRE Hogwarts castle, complete with classrooms, the Great Hall, Quidditch pitch, everything

12 June 2026

Prompt for autonomous Claude Fable with persistent HTML updates

By

–

11 June 2026 18h03

Claude Fable can run autonomously for days.

This is the single highest-leverage prompt I use to stay on top of it:

"Spin up a persistent HTML page. As you work, append clear, timestamped updates with screenshots/media so I can follow along."

Literally a 10x better experience. pic.twitter.com/TKtsIALzxY
— Matt Shumer (@mattshumer_) 11 juin 2026

Claude Fable can run autonomously for days. This is the single highest-leverage prompt I use to stay on top of it: "Spin up a persistent HTML page. As you work, append clear, timestamped updates with screenshots/media so I can follow along." Literally a 10x better experience.

11 June 2026

Fable will be considered a dumb model soon

By

–

10 June 2026 22h01

It’s hard to imagine, but Fable will be considered a “dumb” model in just a few months.

Community-funded Fable run for GTA-VI-caliber open-world game

By

–

10 June 2026 19h53

Someone should set up a community-funded Fable run with a prompt like: "/loop until you've created a GTA-VI-caliber open-world game with a quality and scope surpassing what is shown in the initial trailers" Happy to write the prompt if someone organizes this!

Claude Fable consistently nails harder tasks with /loop prompts

By

–

10 June 2026 3h23

I keep throwing harder and harder tasks at Claude Fable and it just keeps nailing them. I’m genuinely struggling to find something it doesn’t get on the first try with a good /loop prompt.

Claude Fable makes testing other models feel pointless

By

–

10 June 2026 3h14

Testing models for other labs just feels completely pointless now after trying Claude Fable. Genuinely feels like a waste of time… this model is just so above and beyond incredible. Hats off to the Anthropic team.

GPT-5.5 and Opus 4.8 are best models with thinking maxed

By

–

07 June 2026 17h49

Currently, the best models are GPT-5.5 and Opus 4.8. Make sure thinking is turned all the way up!

7 June 2026

Using time in agents: obsession fix via system prompt

By

–

05 June 2026 0h16

Pls do this! Makes agents so much better. They do tend to get a bit obsessed with time if they see it every message or two but a line in the system prompt usually fixes that.