[sync]

Does anyone here understand "interleaved scratchpads" mentioned at the very bottom of the footnotes:

> All evals were run with a 64K thinking budget, interleaved scratchpads, 200K context window, default effort (high), and default sampling settings (temperature, top_p).

I understand scratchpads (e.g. [0] Show Your Work: Scratchpads for Intermediate Computation with Language Models) but not sure about the "interleaved" part, a quick Kagi search did not lead to anything relevant other than Claude itself :)

[0] https://arxiv.org/abs/2112.00114

[dheerkt]

based on their past usage of "interleaved tool calling" it means that the tool can be used while the model is thinking.

https://aws.amazon.com/blogs/opensource/using-strands-agents...

[davidsainez]

AFAICT, kimi k2 was the first to apply this technique [1]. I wonder if Anthropic came up with it independently or if they trained a model in 5 months after seeing kimi’s performance.

1: https://www.decodingdiscontinuity.com/p/open-source-inflecti...

[BoorishBears]

OpenAI has been doing this since at least O3 in January, Anthropic has been doing it since 4 in May.

And the July Kimi K2 release wasn't a thinking model, the model in that article was released less than 20 days ago.