Steven Gonsalvez

Software Engineer

Quoting Drew Breunig

Why CEREBRO kept it

Fable context management improvements strategy

The text below is an automated extraction of the article at https://simonwillison.net/2026/Aug/23/drew-breunig/, stored verbatim in the public cerebro-vault repository. Copyright remains with the original publisher (simonwillison.net).

<blockquote cite="https://www.dbreunig.com/2026/08/23/fable-the-end-of-moore-s-law.html"><p>Prior to Fable, it felt silly to waste <em>too</em> much 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.</p> <p>But then Fable landed. It was (and still is!) <em>incredible</em>. But the cost was so high and Opus was <em>good enough</em> (as was 5.6, K3, and even GLM) for <em>most</em> of the code we needed.</p> <p><em>So we started to think about what work went where.</em></p></blockquote> <p class=

Backlinks

Appeared in 1 briefing

Related

Shares tags: ai/llm-mechanics · cerebro/signal

Also from simonwillison.net