ragidi
← back

Field Guide to Fable — Thariq Shihipar, Anthropic

162.0K views · Jul 06, 2026 · 19:28 min · Watch on YouTube ↗
Takeaway

Revisit tools, prompts, and assumptions as model capabilities grow, and expose the unknowns in your specifications.

Summary

  • Fable is introduced through a field guide covering unhobbling Claude, finding unknowns, dealing with change, and attempting more ambitious work.
  • Capability overhang means tools can unlock abilities absent in ordinary chat: Claude Code can fetch a Pokémon list and filter it with code.
  • The team reports removing 80% of Claude Code's system prompt as newer models needed fewer examples and constraints.
  • Question tools and HTML reports illustrate changing interaction patterns, while gaps between a specification and the actual codebase become decisions the model must resolve.
claude-codefableagent-harnesses
Original description 
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