Claude Fable 5 첫인상

생각 덩어리

첫인상 — 느리고 비싸고, 던지는 족족 해치우는 짐승

I didn’t have early access to today’s Claude Fable 5 release, but I’ve spent the past ~5.5 hours putting it through its paces. My initial impressions are that this is something of a beast. It’s slow, expensive and has been quite happily churning through everything I’ve thrown at it so far. As is frequently the case with current frontier models the challenge is finding tasks that it can’t do.

핵심 스펙 — Mythos 5의 성능에 엄격한 guardrails를 더한 모델

Anthropic claim that Claude Fable 5 offers the same performance as Claude Mythos 5, except with much more strict guardrails in place to prevent it being used for harmful things. Those guardrails trigger often enough that the Claude API has new mechanisms for letting you know when you hit them, and even has a new option to request it falls back to another model automatically if something gets rejected.

Claude Mythos 5 is out today as well, Anthropic say it “Shares Claude Fable 5’s capabilities without the safety classifiers”.

The models have a 1 million token context window, 128,000 maximum output tokens and a knowledge cut-off date of January 2026.

They are priced at twice the price of Claude Opus 4.5/4.6/4.7/4.8: $10/million input tokens and $50/million output tokens. There’s no increase in price for longer context usage.

큰 모델의 냄새 — 속도·가격, 그리고 아는 양

The best way to describe Fable is that it feels big. Not just in terms of speed and cost, but also in how much it knows.

Here’s an example prompt, which I used to compare Fable’s knowledge with Opus 4.8 (typo included):

List all of Simon Willion's open source projects, most recent first, each with a rough date of when they were first released

같은 프롬프트, 두 응답 — Opus는 사리고 Fable은 쏟아낸다

I don’t have a reliable, comprehensive, and date-verified list of all of Simon Willison’s open source projects, and I want to be honest about that rather than risk giving you inaccurate dates or fabricated entries. Here’s what I can tell you with reasonable confidence ...

I think you mean Simon Willison — the prolific open source developer, co-creator of Django, and creator of Datasette. An important caveat upfront: a truly complete list isn’t feasible. Simon Willison is famously prolific — he has published hundreds of repositories (Datasette alone has 100+ plugins, many written by him), and my knowledge has a cutoff date, so I’ll be missing his most recent work.

(Here’s GPT-5.5 for good measure. It listed even more projects than Fable did!)

지식 무용론의 수정 — 아는 양은 모델 크기의 프록시

In the past I’ve stated that I don’t care about how much models know—I want them to be able to manipulate text and code in useful ways and actively look up the information they need via search tools, not bake it into their weights.

But knowledge like this is a reasonably good proxy for model size—you can cram a whole lot more details about the world into a larger number of parameters.

Does knowing more stuff mean the model is better at the tasks we pose to it? I can certainly imagine how a coding model with deeper knowledge of modern libraries and patterns could crunch through coding tasks more effectively.

Is Fable really bigger than Opus? Anthropic haven’t said anything about model size, so all we have are tea-leaves, but the speed, pricing and my own poking at its knowledge make me think that it’s a large model. Maybe the largest yet from any vendor.

과소평가된 Claude.ai — 모든 채팅에 컨테이너가 붙어 있다

Anthropic made Fable 5 available across all of their surfaces—the Claude.ai chat interface, Claude Code for web, Claude Code CLI and Claude Cowork as well. The model is available “until June 22nd” on the subscription plans (I’m on $100/month Max at the moment), after which it will be billed extra.

Claude.ai is often under-estimated. Since September 2025 every chat has had access to a full container environment to run code, including the ability to install additional packages and even clone repositories directly from GitHub.

Last week I released micropython-wasm, a Python library that uses wasmtime to run a custom build of MicroPython in WebAssembly to act as a sandbox for untrusted Python code.

첫 과제 — MicroPython 샌드박스를 풀 CPython으로

Clone simonw/micropython-wasm from GitHub and research how this could use a full Python as opposed to MicroPython

Fable identified that it could use Brett Cannon’s cpython-wasi-build builds for this, but was unable to download them itself due to environment restrictions.

And that was that. It churned away for a few minutes and got the entire thing working.

막힌 지점 재돌파 — 휠 하나에 시스템 전부를 담기

I tried the cleaner single-zip-stdlib approach to shrink the filesystem surface, but CPython’s getpath bootstrap fails to find encodings from inside a zip without more prefix finessing — the directory-preopen approach works reliably, so that’s what the PoC uses. The zip path is solvable but needs _PYTHONHOME/frozen-getpath work.

Try a bit more at the single-zip-stdlib problem

I want a wheel that has the whole system in it, the Python wrappers and the WASM files and the stdlibrary, so I can do uv run --with path-to-whl python -c "demo code"

... and it gave me this 13.9MB cpython_wasm-0.1.0-py3-none-any.whl file. ... This was a very strong start.

Datasette Agent와 LLM 0.32a3 — 임시 해킹을 정식 기능으로

Before I’d realized it was Fable day, my stretch goal for today was to add a new feature to Datasette Agent: I wanted tool calls within that agent software to gain the ability to pause mid-execution and request approval directly from the user.

Over the course of the day Fable not only solved that problem, it also identified and then implemented four issues in my underlying LLM library that would help support this kind of advanced pause-resume mechanism in tool calls.

It got everything working first using somewhat gnarly hacks, but the moment I told it that changes to LLM itself were in scope it set to work unraveling the hacks and turning them into supported features of LLM instead.

I’m really impressed with the quality of API design, tests, code and documentation that Fable put together for this. I spent several hours on it today, but it feels like several days’ worth of work.

하루 사용액 $110.42 — 월 구독료를 하루 만에 초과

I recently started using AgentsView to help track my local LLM usage across all of the different coding agents. I published a TIL today about adding custom Fable pricing to that tool, which I expect will not be necessary in the very near future.

I used $110.42 worth of tokens today, all as part of my $100/month subscription.

펠리컨 벤치마크 — thinking effort 다섯 단계

I ran “Generate an SVG of a pelican riding a bicycle” against all five thinking effort levels with Fable.

It’s interesting that high ended up using fewer tokens than medium for this particular run.

Here are the Opus 4.8 pelicans for comparison.