xhrpost

Are people actually running this on $10k of hardware?

Is this what is causing at least part of the massive bot traffic hosts are seeing to their sites? Many direct-to-inference users are just retrieving the site locally every time they need it, let alone sharing site content across users. The big providers like Claude and Google implement their own caching so that when an agent is doing research, if 100k different prompts need the same site content, they don't hit that site 100k times.

Why wouldn't this qualify as price discrimination? Which is already illegal.

Did not realize that Win95 can technically run on a 20Mhz 386DX.

Wow, I actually had this exact idea. I was specifically curious as to how well a given LLM could understand a DSL that hasn't changed much in a couple decades and doesn't have nearly as many examples to learn from online. Seems like it did alright, all things considered.

Would he have been better off just refusing to give a code?

I intuitively and perhaps naively thought that Claude using the LSP server would negate a lot of grep use. Is this tool solving the same problem or something else?

For a while everyone was saying sub agents is how you save tokens, use lower quality models with limited context to do simple parts of the job after a smart planning agent has put it all in place. Is that no longer true or is this just the result of sub agent being used at the wrong time?

> Any time I notice something in code review and have to get the agent to fix it.. I throw it on the list! My list is like 200 items now.

This is a gripe I've had with AI tools for a while now. Though it's gotten somewhat better in time, but we don't really know what to expect from the tool in terms of quality. Ex. I'd expect a human engineer to probably not use a brand new assertion library for a new test when there are 200 tests using an existing one. But Claude has done this to me multiple times. So I have to add yet another item to the list, like you have, and tell it to look for testing conventions before writing. But, there is plenty we don't have to tell it, like what a function is or a test should probably cover the change in the diff. But we don't really have a list of what things are on each side so we're just left to sort of hunt and peck to build a viable solution.