> Gnomon is a PostgreSQL extension that gives your database branches, history, merges and undo. Give an agent its own branch of your real database, as nothing more than a connection string. See every field it changed, merge it into main when it's right, and undo it if it wasn't.
I don't know if I like the idea of handing an agent direct access to db migrations when db migrations already exist through code in most applications (which are then managed by git). What would the use case be for this that isn't already handled through migration code in git?
I'm fine with people using LLMs to generate code, but I am so, so tired of reading README.md files written by AI. If you want me to take any interest in your idea, please spend the hour or two it takes to explain what you did (or made your agent do) and why, using your own words.
LLMs will make anything sound like a good idea on the surface, and I as a reader have to dig in and spend mental capacity to separate the fluff from what is actually a good idea. I'm not going to do that, I'm just going to close the tab. What I want to read in the README.md is an actual human expressing an actual need and an actual idea for how to address it.
Sure, use an LLM to get feedback on your writing, maybe even let it help you develop good examples. But if you can't even write a single coherent sentence on your own, keep your project to yourself and stop wasting the time and attention of others.
I wonder if the prompt was "Make a HN front page project complete with post, docs, repo, and tutorial. Make it seem like it's been around for a while. Pick two popular concepts and go with it"
I don't know if I like the idea of handing an agent direct access to db migrations when db migrations already exist through code in most applications (which are then managed by git). What would the use case be for this that isn't already handled through migration code in git?
LLMs will make anything sound like a good idea on the surface, and I as a reader have to dig in and spend mental capacity to separate the fluff from what is actually a good idea. I'm not going to do that, I'm just going to close the tab. What I want to read in the README.md is an actual human expressing an actual need and an actual idea for how to address it.
Sure, use an LLM to get feedback on your writing, maybe even let it help you develop good examples. But if you can't even write a single coherent sentence on your own, keep your project to yourself and stop wasting the time and attention of others.
just get feedback from actual readers who will tell you and may even submit a PR. That's what open source is for...