Fable 5.1 barely got any attention since openai released Astra, they've already hinted that something much stronger is cooking internally -- and looking at Astra's benchmark jump, whatever comes next could be hard to put into words curious how anthropic responds to Astra

Fable 5.1 one-shot this Dark Souls meets Diablo game. All code, 222 KB total, zero asset files. Every texture, model and sound effect is generated procedurally. The whole sfx system is 7 KB of Web Audio synthesis. It nailed mechanics I only named in text: stamina, dodge rolls, barbarian skills, and a punishing Souls-style boss. The soul pickups and death animations came out way smoother than I expected. What gets me is how much it infers from a few genre references, with no screenshots or video to go on. Reaching this level used to take dozens of prompts in Sol or Opus 5. Anyone with taste can now make really fun games in the browser.

Fable 5.1 In Cursor with pStack = Digital Twin of upcoming Terafab in Grimes County, Texas Video 1: Exterior Tour Video 2: Timelapse of construction cc: @SpaceXAI @cursor_ai @elonmusk @XFreeze

Fable 5.1 makes Claude Tag even more useful. Here it builds a last-minute leadership deck from a metrics spreadsheet and other data across Slack, spots a vendor report that disagrees with the numbers, and flags it before moving on. Claude Tag is available in Slack on Team and Enterprise plans.

Fable 5.1 improved a lot more in science than i expected fable 5.1: 52.6% fable 5: 24.7% more than 2x better on agentic scientific workflows and there are reports that openai's unreleased models are insane at maths too, which suggests RL can push fields one by one depending on what labs choose to prioritize

Fable 5.1 is really good. One of the biggest things I’m noticing is that it's crazy good at design. Even starting from scratch, with very little context or guidance, it gives great results. And Fable 5.1 Medium is definitely my sweet spot.