Anthropic's Thariq Shihipar argues tool-use frameworks like Claude Code resolve model capability overhang

Story Brief

He demonstrated Claude Code writing scripts to solve complex filtering prompts

Field Guide to Fable — Thariq Shihipar, AnthropicAsk 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. Shihipar 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:2h agoYouTube

Commentary on X

Highest ranked

Pamela Fox@pamelafoxTECH

@trq212 Fantastic talk. I can't play with Fable yet due to the data retention issues, but I think that your recommendations are broadly useful, for other models as well.

Anthropic's Thariq Shihipar argues tool-use frameworks like Claude Code resolve model capability overhang

Related Stories

Commentary on X

Digg Deeper