Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-07-21 · high
Cat Wu and Thariq Shihipar covered Claude Code, Claude Tag, and Fable in a fireside chat at AI Engineer World's Fair.
Why now: Willison published the conversation on July 21, the freshest on-record account of how Anthropic's own Claude Code team describes its roadmap.
Simon Willison posted his account of an AI Engineer World's Fair conversation with Anthropic's Cat Wu and Thariq Shihipar on July 21. Both work on Claude Code. This is the product team talking directly, not a release note or a keynote clip.
The conversation names three things: Claude Code, Claude Tag, and Fable. Willison's post doesn't spell out what Wu and Shihipar said about the last two, so there's nothing here yet on what either one does or how they connect to Claude Code.
That gap is worth sitting with rather than filling in. Anthropic didn't give Claude Tag and Fable their own separate announcements. It put them in the same fireside chat as Claude Code.
If you run your day through Claude Code, the value here is hearing Wu and Shihipar frame their own roadmap in their own words, before either name gets its own write-up.
Each link below shares sources, entities, or timing with this story.
Anthropic shipped Fable 5 on June 9. Willison spent ~5.5 hours stress-testing it: slow and expensive, but it handled everything he threw at it, including agentic coding. (Simon Willison) The tell that it's a real working model and not a benchmark queen: because it post-dated A...
Anthropic engineer Thariq Shihipar disclosed that Claude Code treats cache hit rate drops as production incidents — the entire product architecture was designed around prompt caching constraints. Plan Mode exists as callable functions (not tool permission toggles) specifically...
Willison's prolific output continues: he covered ggml.ai joining HuggingFace, Taalas 17K tok/s, SWE-bench Feb 2026 leaderboard (Opus 4.5 leads at 80.9%, 4 Chinese models in top 10), Paul Ford's NYT essay, Martin Fowler's "LLMs eating specialty skills" observation, and Thariq S...
swyx's synthesis of the AI Engineer World's Fair 2026 is the clearest framing I've read of where this all goes. The discipline moved from building agents to engineering the harness around them. Lilian Weng (now at Thinking Machines Lab) reframed her whole practice as "harness...
On July 16 there was a wave of backlash calling the Bun Zig→Rust rewrite unreviewed AI slop. On July 19, Simon Willison went and checked. (Simon Willison) Jarred Sumner claimed Claude Code v2.1.181 and later ship the Rust port. Willison verified it independently rather than ta...
On June 9, Anthropic released Claude Fable 5 and Mythos 5 across Claude.ai, Claude Code (CLI and web), and Cowork. The spec sheet: 1M-token context, 128K max output, a January 2026 knowledge cutoff, and pricing at $10 input / $50 output per million tokens. That's double Opus 4...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.