Prior to Fable, it felt silly to waste
toomuch time improving your coding harness or context strategies. A new model would arrive at the same price (or cheaper!) and paper over most of your problems.But then Fable landed. It was (and still is!)
incredible. But the cost was so high and Opus wasgood enough(as was 5.6, K3, and even GLM) formostof the code we needed.
So we started to think about what work went where.
— [Drew Breunig](https://www.dbreunig.com/2026/08/23/fable-the-end-of-moore-s-law.html), Fable & The End of the Free Lunch
Tags: [drew-breunig](https://simonwillison.net/tags/drew-breunig), [anthropic](https://simonwillison.net/tags/anthropic), [claude](https://simonwillison.net/tags/claude), [llm-pricing](https://simonwillison.net/tags/llm-pricing), [ai](https://simonwillison.net/tags/ai), [llms](https://simonwillison.net/tags/llms), [generative-ai](https://simonwillison.net/tags/generative-ai), [claude-mythos-fable](https://simonwillison.net/tags/claude-mythos-fable)
source & further reading
simonwillison.net — original article
Software Engineering in the Agentic Era
llm 0.33
More than just code review