Field Guide to Fable — Thariq Shihipar, Anthropic

At AI Engineer, Thariq Shihipar — member of technical staff at Anthropic on Claude Code — opened with a Claude Code tradition: a pre-talk selfie with the room. Then the headline: Fable is back, rolling out later that day, with a 12:30 fireside alongside Kat Wu and Simon Wilson for possible updates.

The core of the session was a four-part field guide Thariq had been publishing as articles — compressed into one stage speed-run:

1. Unhobbling Claude
2. Finding your unknowns
3. Dealing with the grief
4. Being unreasonable

This post is explainx.ai's recap of that talk: what each section means for daily Claude Code work, copy-paste prompts from the stage, and how it connects to subscription billing, the July restore, and Thariq's earlier map-is-not-territory essay.

Update — July 17, 2026: Same conference — Lee Robinson's recursive model improvement talk (Cursor + SpaceXAI training flywheel, textual feedback RL, Slack research agents). Pairs with Part 1's harness/unhobbling frame from the product side; Lee covers the ML side.

Update — July 25, 2026: Unhobbling went production — Claude 5 context engineering (Anthropic cut 80%+ of Claude Code’s system prompt for Opus 5 / Fable 5) · Opus 5 launch.

Also read: Fable 5 advisor + Sonnet 5 executor — /advisor fable setup and executor/advisor prompt split. Matt Shumer's Workbench guide — goal-not-steps and multi-day /loop runs.

TL;DR — What people are asking

Part 1 — Unhobbling Claude

Thariq's opening frame: models are grown, not designed. Anthropic does not wake up targeting 99% on SWE-bench — teams grow models with data, feedback, and compute, then learn alongside them. What contains a model in production is us: the harness, tools, and prompts.

Unhobbling means understanding Claude better so you stop leaving capability on the table.

Capability overhang (the Pokémon test)

A viral puzzle: Which Pokémon names end in "AW"? (~1,000 species; answer: two — Croconaw and Drednaw).

The model did not suddenly memorize every species. Code execution unlocked a spiky skill. Thariq calls this capability overhang — intelligence present but invisible until the harness exposes it. Fable's challenge is discovering what overhang exists now.

How harnesses evolved (three spikes)

1. Context → arms (birth of Claude Code)

Early coding intuition: paste the whole repo into a giant context window. What worked instead: give the model bash, search, and environment access so it builds its own context. That insight is Claude Code itself — not bigger prompts, better arms.

2. Reactive → proactive (Claude Tag)

Claude Code waits for you to prompt. Claude Tag pushes toward agents that wake themselves up and work in multiplayer settings — another harness shift, not just a smarter weights upgrade.

3. System prompt shrink (~80% removed)

If your CLAUDE.md and skills still compensate for a weaker model, you may be hobbling Fable with obsolete scaffolding.

Ask-user-questions: another overhang curve

Thariq built the ask user a question tool early at Claude Code:

Same tool name; radically different UX as capability jumps. See HTML vs Markdown in Claude Code for the output-format parallel.

Biology, not physics

Thariq urges treating Fable like biology — empirical, organic, rules incomplete — not a physics equation. He pointed attendees to Anthropic's research essay Biology of a Large Language Model for intuition-building.

Part 2 — Finding your unknowns (unhobble yourself)

Models improved; you must improve too. Thariq's map/territory frame:

• Map — your plan, prompt, spec, mental model
• Territory — real codebase, constraints, production reality
• Unknown — territory not on your map; Fable must improvise

Fable was the first model where Thariq felt he had to catalog unknowns — autonomous reach is so wide it hits unstated decisions fast. Deeper analysis: map is not the territory guide.

The four-quadrant matrix

Fable can help surface all four — if you prompt for discovery before execution.

Copy-paste prompts from the talk

Blind spot pass (unknown unknowns):

I'm working on a new auth provider I know nothing about in this codebase.
Can you do a blind spot pass to help me figure out my relevant unknown
unknowns and help me prompt better?

Point Fable at git diff, Slack, or docs for richer maps. Thariq used the same pattern learning color grading for video — domain-agnostic.

Design prototypes (unknown knowns):

I have no visual taste. Make me an HTML page with four widely different
design decisions so I can react to them.

Reaction beats description when you cannot verbalize taste.

Architecture interview (known unknowns):

Interview me about this feature. Prioritize questions that would change
the architecture. [Add context about stage, constraints, and audience.]

Reference as map (skip writing the spec from scratch):

Here's code that represents what I want done — possibly another language
or system. Read it, understand it, and use that as your starting map.

Works with HTML mockups as references for React components — ties to Thariq's HTML thesis.

Implementation notes (mid-run unknowns):

When Fable hits an unspecified decision, ask it to log the deviation so you can see where the map failed and update CLAUDE.md or skills permanently.

Quiz before merge (stay in the loop):

Have Fable quiz you on what changed before you open a PR — ensures you can represent the work, not just approve diffs.

Staying in the loop

Thariq's recurring theme: Fable's output scale demands human alignment. Autonomy without map maintenance produces confident wrong paths. Pair these tactics with loop engineering so sessions end with updated territory notes, not one-off fixes.

Part 3 — Dealing with the grief

The talk pivoted personal. First Mythos-class session brought gain and loss.

Thariq ran a ~30-person YC startup where code forced brutal tradeoffs — ship fast or prototype features; weeks vs months per bet. Revisiting that codebase with Fable: work that took weeks became hours.

He loves hand-written code — the mental rotation of a system in mind. He also remembers late-night debugging, weeks without progress, most projects failing, most startups dying. Programming was hard; the highs were real; he cannot go back.

His resolution: the only way out is through. Grieve the craft; keep learning agentic coding with Fable while staying in the loop. Sentiment echoed in Fable loop design — longer autonomy changes your job, not just the model's.

Part 4 — Being unreasonable

Anthropic culture, per Thariq: tradeoffs are often fake. At his startup he "was reasonable" — quarterly priority lists, explicit sacrifices. At Anthropic the question is: what if you tried to do all of it and let reality expose the real constraint?

Good, fast, cheap — pick three softens when Fable compresses execution cost. Thariq built his AI Engineer deck in ~4 hours with Fable — quality he liked, speed he did not expect.

His challenge to the room: the world is watching AI engineers prove this is not a fad — more productive, work less, spend time with people you care about.

Caveat he named: Building is easier; generating value is still hard. Optimizing harnesses and tooling is not the goal — swings at valuable outcomes are. Connects to context vs prompt vs loop vs harness: the stack serves outcomes, not the reverse.

Fable availability context (July 2026)

The talk assumed Fable rolling out imminently — consistent with Anthropic's July 1 global restore after the June export-control suspension.

Subscription note: included Fable on Pro/Max/Team ends July 7, 2026, 11:59:59pm PT — then usage credits. Anthropic still pledges eventual return to subscription inclusion when capacity allows. Details: subscription return guide.

Harness advice in this recap applies regardless of billing bucket — but credit economics may push you toward Sonnet 5 for routine map-building and Fable for high-unknown passes.

What to try this week

1. Audit your harness — remove skill scaffolding written for pre-Fable models; test with a smaller effective system prompt.
2. Run one blind spot pass on the hairiest module you are about to touch.
3. Log implementation notes for one long Fable session; convert surprises into CLAUDE.md updates.
4. Pick one "unreasonable" project — scope you would have cut last year; time-box with Fable and measure value, not just LOC.
5. Read the companion essays — map/territory, HTML effectiveness, Fable on Claude Code.

Update — July 16, 2026: @anthrupad's ten-run video game probe — field-guide-grade self-reflection from a one-line prompt on claude-fable-5.

Related on explainx.ai

• Fable/Mythos favorite video games — preference manifolds and epistemic tenderness
• The Map Is Not the Territory — deeper dive on Part 2
• Unreasonable Effectiveness of HTML — output format overhang
• Fable 5 Edited Its Own Launch Video — Thariq + Fable shipping culture
• Anthropic Redeploying Fable 5 — restore terms
• Will Fable Return to Subscriptions? — July 7 billing
• Loop Engineering with Claude Code — harness patterns
• Ethan Mollick — Wharton Prompting Science — specs beat tricks; CoT ROI falling on reasoning models
• Steering Claude Code — skills and CLAUDE.md
• GPT-5.6 vs Fable 5 — when to reach for which frontier

Official sources

• Biology of a Large Language Model — Anthropic research
• Claude Fable 5 launch — model announcement

Recap based on Thariq Shihipar's AI Engineer stage talk and his published field-guide articles. Fable availability, system prompts, and Claude Code defaults change frequently — verify in your CLI and Anthropic docs before treating any prompt as permanent.