I love reading Werner's blog because of how he is able to break things down to their essence. In his use of Kiro Crew he picked out patterns in its memory architecture around how it decides what to keep, what to compress, and what to prune. While the team did this for practical reasons, he notices similarities to how the brain works. Specifically he compares Kiro Crew's memory architecture of distinct memory types, background consolidation, and decay to what Hawkins describes in A Thousand Brains. Memory is what lets an agent earn the autonomy to work unattended. You review less over time not because you check less, but because it remembers your rules. That memory architecture is core to the personal Kiro Crew system I have described in recent tweets. You should try it.

It's pre-invent/re:Invent time, which means that I am putting my Twitter break on a hold for a few weeks.

I have always enjoyed my conversations with the smart folks at @insitro. In this post, @mattrasmus talks about their data science workflows that run on AWS Batch. aws.amazon.com/blogs/hpc/dat…