What are the four categories of knowledge Shihipar describes?

Known Knowns (what is stated in the prompt), Known Unknowns (questions you know you haven't answered), Unknown Knowns (obvious knowledge you wouldn't write down but would recognize), and Unknown Unknowns (things you haven't considered at all). Unknown Unknowns are the critical category that limits output quality.

What techniques does Shihipar recommend before starting implementation?

A blindspot pass (asking Claude to identify unknown unknowns), brainstorming and prototyping (especially for areas like visual design), structured interviews where Claude asks prioritized questions, using source code as references, and creating an implementation plan that focuses on parts most likely to change such as data models and type interfaces.

Why is being too specific in prompts a problem?

Too much specificity risks Fable 5 rigidly following instructions even when a change of course would make more sense, whereas too much vagueness results in decisions based on industry defaults that don't fit the specific task.

Large Language ModelsAI Business & IndustryTHE DECODERJul 4, 2026Jul 4, 2026, 22:01 JST

Anthropic dev: Claude Fable 5 quality now limited by user's blind spots, not model

Send on LINE

3 Key Points

What happened
Anthropic developer Thariq Shihipar shared prompting techniques for Claude's Fable 5 model, arguing that output quality is increasingly constrained by the user's inability to identify their own knowledge gaps—what he calls "unknown unknowns"—rather than the model's capabilities.
Why it matters
As AI coding agents become more capable, the bottleneck shifts from the tool to the user's clarity about the problem. Developers who systematically uncover their own blind spots before implementation—through brainstorming, prototyping, and structured interviews with Claude—are more likely to achieve better results. This suggests that effective AI-assisted development now requires a different skill: self-awareness about what you don't know.
What to watch
Shihipar demonstrated his techniques using the Fable launch video, which he edited entirely with Claude Code despite video editing being new to him. He recommends a pre-implementation phase focused on discovering unknowns, followed by documentation during work (via implementation notes), and post-implementation validation through quizzes before merging code.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, in your inbox every morning.

Get news like this every morning, free

FAQ

What are the four categories of knowledge Shihipar describes?: Known Knowns (what is stated in the prompt), Known Unknowns (questions you know you haven't answered), Unknown Knowns (obvious knowledge you wouldn't write down but would recognize), and Unknown Unknowns (things you haven't considered at all). Unknown Unknowns are the critical category that limits output quality.
What techniques does Shihipar recommend before starting implementation?: A blindspot pass (asking Claude to identify unknown unknowns), brainstorming and prototyping (especially for areas like visual design), structured interviews where Claude asks prioritized questions, using source code as references, and creating an implementation plan that focuses on parts most likely to change such as data models and type interfaces.
Why is being too specific in prompts a problem?: Too much specificity risks Fable 5 rigidly following instructions even when a change of course would make more sense, whereas too much vagueness results in decisions based on industry defaults that don't fit the specific task.

THE DECODERRead Original Article

Send on LINE

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Get it free

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.