Field Guide to Fable — Thariq Shihipar, Anthropic

Ask a chat model which Pokemon names end in aw and it fails, even though it knows every Pokemon by heart. Ask Claude Code and it writes a script, fetches the list, and filters for the answer in seconds. Thariq Shihipar, who works on Claude Code at Anthropic, calls that gap capability overhang: models get smarter in spiky ways, and the tools you give them decide which spikes you can reach.

Thariq covers what it takes to work with Fable, Anthropic's newest model. Claude Code cut 80 percent of its system prompt, since heavy instructions now constrain a model more imaginative than the examples it's given. The ask user question tool went from barely working under Opus 4 to generating embedded HTML questionnaires under Fable. He built a full keynote deck in four hours with it, and argues teams should stop picking two of good, fast, and cheap and start demanding all three.


Speaker info:
- https://x.com/trq212/

Timestamps:
0:00 Introduction and setting the stage for Fable
2:32 Unhobbling Claude: Understanding model behavior
9:08 Finding your unknowns: Navigating the gap between map and territory
14:29 Reflecting on the emotional shift in coding productivity
16:30 Being unreasonable: Demanding good, fast, and cheap results