I had received four very different bids for a home repair project. Just wildly different itemization breakdowns, costs, timelines, scopes, even formats. Opus helped me turn it into an apples-apples comparison, filled in missing areas with reasonable inferences based on the other bids, provided a nice pdf I printed to review with my partner, even offered suggested key questions for follow up calls. It really clarified the advantages of one of the bids.
I use it professionally all the time and could cite technical scenarios where it’s become almost indispensable, but saving me time and money and reducing stress on this mundane stuff… now imagine applying to people’s stressors: job searches, health, big purchases, debt… there’s an opportunity to actually make people’s lives better. After 30 years of hype cycles, I should be wary of techno-optimism. But here I am feeling cautiously optimistic anyway.
The software generalist described in this post has domain expertise as well. In software.
If you’re a great generalist software engineer today, you aren’t jumping to some random domain to escape AI. Software is your domain. You’re sticking with it as it expands and transforms.
I think a lot of us aren’t rational about it. I tend to feel excited about changes for which productivity is a side effect, even if it’s not my motivation. It’s hard to say no to extending my capabilities and insulating myself from the more boring repetitive tasks.
If your job was 80-90% shoveling and one day you were offered use of an excavator, wouldn’t you find that exciting even while realizing the shoveling part of your career is probably dead?
My thinking tends to be that our standard work week is an equilibrium among a few different forces. We’re motivated by social norms, capital markets, and biological needs and wants. In places like the U.S. the market forces have been powerful enough to really shift social norms. In tandem they’re probably slowly altering our biology too.
I’ve been playing with nanoclaw since it came out, which has similar use cases to openclaw. I initially set it up to monitor various news sources for me about specific theses I’ve had. I had it grooming its growing knowledge base, trying to make connections. It would check in with me about certain goals I had.
My current take is that these projects are alluring for a kind of personal productivity or workflow tinkering. They are integration hubs centered around an LLM. Automation can be fun, like running model trains or setting up home assistant. And you can learn the shape of the technologies by tinkering. But I’m doubtful they have improved productivity in real world cases.
Maybe I’m using it wrong and I need to be spending a ton of tokens with a dark factory pattern and a fleet of claws creating new religions? Then I’ll see the benefits?
Thank you, Zed team, for creating Zed. It’s clearly a labor of love, and I really want Zed to work for me. It seems like a quality project, it’s fast, and the base editor is easy to use.
I gave it weeks though, and the surrounding UI just never clicked for me. The various AI panels are confusing, the global search is awkward, and something about the type rendering just didn’t ever look right (maybe I’m hallucinating this?). I use VS Code only grudgingly, but I do think its ergonomics are actually pretty reasonable. I came from Sublime before that. I’ll keep trying Zed, and I hope you succeed.
Yeah writing out code by hand made me slow down and think more.
One thing I recall is that the grading policy made it very clear that minor syntax issues were inconsequential in handwritten answers. And more advanced classes only wanted pseudocode. Which are exactly the right priorities.