cowoder

Training the LLM on logs might make little sense, but that doesn't mean the LLM can't get access to those logs outside of training. Companies have been gobbling up your data left and right, why wouldn't these companies do the same and then feed it to their LLM for a specific use case?

Isn't it the other way around, nobody writes React by hand they all use JSX?

Won't it generate tests that prove the correctness of the code instead of the correctness of the application? As in: if my code is doing something wrong and I ask it to write tests for it, it will supply tests that pass on the wrong code instead of finding the problem in my code?

My pipeline and hosting solutions are:

Static: Github Actions to build and deploy to BunnyCDN

Non-static: selfhosted Dokku on Hetzner

Neither is free, if you're looking for free, Github Pages or Cloudflare for static sites. Free non-static, I'm not sure there are solutions that don't have the same problem Netlify has.

That's a tracking script, might be failing due to your adblocker or other privacy tool. Learn page appears to work fine for me, while blocking plausible.

What would make correlation research worthless? Wouldn't that just be a first step to see if researching causation is even worth it?

You can use vite for that