Pash explains that Anthropic already promotes an 'advisor' architecture where Sonnet/Haiku handle routine work and escalate to Fable only when needed, effectively enterprise-taught model routing. ✦ AI generated
Pash · The Cognitive Revolution · 2026-07-02 · original ↗
starts at this moment · 27:29
So the Frontier Lab can always do this kind of advisor strategies where you have um you know sonnet 5 as the core model which then pulls in fable as an adviser for uh various tasks and in fact on the API that is actually what the product team at anthropic has been promoting.
verbatim transcript · starts at 27:29
27:29serve that $100 million worth of uh, you know, revenue not using our let's say Fable, but let's say using Sonnet 5 and how would we structure that so that we could hit the capability uh, that is required and also hit the cost and so the Frontier Lab can always do this kind of advisor strategies where you have um you know sonnet 5 as the core model which then pulls in fable as
28:00an adviser for uh various tasks and in fact on the API that is actually what the product team at anthropic has been promoting. They've been promoting to people if you're going to use Sonnet and Haiku use Sonnet and Haiku in your kind of classification systems for your customer service but when things get too difficult pull in a fable. And so this is basically model routing but model
28:25routing driven by the you know enterprise customer themselves teaching them how to model route effectively using a smaller model. But you can also model it out using a uh using a better model and that is part of this kind of uh split tasks into to-do lists and then send out independent agents. Uh some people have been on fable right now on in in claude code if you set it to ultra
28:53code right now you actually get this experience. uh but they don't Fable doesn't use like uh sub agents or you don't know whether they're using sub aents which are of lower models. They won't tell you but you can explicitly ask Fable to use sonnet sub aents and it will use those sonnet sub aents and check their work and so you can start like streaming a lot of this work
29:15actually to other agents even using the existing model and then cut down. I hit my fable limit yesterday, the the five hour limit. I hit my fable limit and I went online and um you know I saw one of the other uh you know uh software engineers, influencers online and he said he had done 16 pull requests since Fable was out hadn't hit his limit at all but he had a structured strategy of