An army of assistants working while you sleep
Obviously Jack Clark (Anthropic co-founder) has a vested interest in promoting this but I’m increasingly convinced we’re seeing the most significant shift in LLM-use taking place in quite some time with the rise of Claude Code. There are very intense cultures of use emerging in which people are finding the system transformative at the level of lifestyle, rather than just work narrowly construed:
I sleep in the back of an Uber, going down to give a talk at Stanford. Before I get in the car I set my agents to work, so while I sleep, they work. And when we get to the campus I stop the car early so I can walk and look at the eucalyptus trees – a massive and dangerous invasive species which irrevocably changed the forest ecology of California. And as I walk through these great organic machines I look at my phone and study the analysis my agents did while I slept.
The next day, I sit in a library with two laptops open. On one, I make notes for this essay. On the other, I ask Claude Cowork to do a task I’ve been asking Claude to do for several years – scrape my newsletter archives at jack-clark.net and help me implement a local vector search system, so I can more easily access my now vast archive of almost a decade of writing. And while I write this essay, Claude does it. I watch it occasionally as it chains together things that it could do as discrete skills last year, but wasn’t able to do together. This is a task I’ve tried to get Claude to help me with for years but every time I’ve run into some friction or ‘ugh-factor’ that means I put it down and spend my time elsewhere. But this time, in the space of under an hour, it does it all. Maps and scrapes my site. Downloads all the software. Creates embeddings. Implements a vector search system. Builds me a nice GUI I can run on my own machine. And then I am staring at a new interface to my own brain, built for me by my agent, while I write this essay and try to capture the weirdness of what is happening.
My agents are working for me. Every day, I am trying to come up with more ways for them to work for me. Next, I will likely build some lieutenant agents to task out work while I sleep, ensuring I waste no time. And pretty soon in the pace of a normal workday, I will be surrounded by digital djinn, working increasingly of their own free will, guided by some ever higher level impression of my personality and goals, working on my behalf for my ends and theirs.
I’ve been up and running on Claude Code for a few weeks. But I lack the technical imagination to work how to really leverage this, beyond asking them to work on isolated projects. I can totally see how there’s something intoxicating though about setting the agent to work and coming back a few hours later to admire the end result. There’s something very big taking place here, I think, which is largely opaque to non-developers.
See also Casey Newton on Claude Code for Writers.
#agents #ClaudeCode #JackClark #LLMs #productivity
sayzard
The Bad Place
Mark Carrigan
Andreas Becker
Ars Technica News
SESH.sx
Phil Edwards