I had a couple of hours to kill recently so I installed Steve Yegge’s Beads. I am hoping this solves a problem for me, which is that storing state for Claude Code in markdown files is not optimal. Beads addresses this by handling state more robustly with git.

Yegge casts a rather long shadow over agentic coding these days. He has not exactly drunk the kool-aid; he is more one of the people mixing the kool-aid and handing it out. Yegge’s blog is rather fantastical, optimistic, hyperbolic and self-important. But it is also interesting reading.

Besides my obvious need to handle state more effectively, one reason that I installed Beads is because the denouement to this whole AI thing is probably going to play out in code (or maybe in financial markets). The best vantage point to see this clearly is in the tools. Is stuff like Beads going to be as transformative as Yegge says it is? He certainly has a lot of hubris about it. But, more darkly, it amusing because we’ve seen so many examples of hubris like this failing spectacularly before.