Synced transcript
Follow the talk
Automated overview
What this talk covers
Thariq Shihipar of Anthropic discusses Fable and argues models improve in "spiky" ways: a chat model fails to list Pokémon ending in "aw" (Croconaw and Dreadnaw), but Claude Code fetches and filters the list in seconds – a gap he calls "capability overhang." He explains that to unlock Fable, Claude Code cut 80% of its system prompt because heavy instructions now constrain a more imaginative model, and the "ask user question" tool evolved from barely working under Opus 4 to generating embedded HTML questionnaires. He shares techniques like blind-spot passes and interviews to surface unknown unknowns, and reflects on the grief of moving from hand-coded programming to agentic workflows. Shihipar urges engineers to reject trade-offs – "good, fast, cheap: pick three" – and instead demand all three, citing a four-hour keynote deck built with Fable as proof that agents can deliver ambitious work faster.
This overview is derived from the transcript and has not been independently fact-checked by AI Engineer.
Generated highlights
Key moments
Fable feels like 'the map is opening up — like you were playing an RPG and the open world starts,' says Thariq Shihipar.
Claude Code answers 'Which Pokemon end in AW?' by fetching the list and writing a filter script, demonstrating capability overhang.
Use Fable's 'blind spot pass' to discover unknown unknowns in a codebase by asking it to analyze hidden complexity.
Thariq Shihipar revisits his old startup codebase: tasks that once took weeks now take hours with Fable.
'Trade-offs are not real' — Fable lets you pick all three of good, fast, and cheap, says Thariq Shihipar.
These moment labels are generated from the unreviewed transcript and may contain errors.
Community discussion
Add context, evidence, or a useful disagreement
Build on the talk with an example, caveat, connection, or elaboration. Draft here, add the moment you’re discussing, then choose the direct-post pilot or the YouTube handoff.
Make it useful: add one concrete point, then support it with context, evidence, an example, or a caveat. Your words stay exactly as written.