zbyte64

If it gets it wrong the first time I rarely reprompt. I know I can get it to fix it, but it's usually faster for me to do it because I already figured out where and what to do the fix. Low key think it's just a ploy to get us to burn more tokens. Sure correcting it means it writes a few lines to the memory file, but it's only a matter of time before it trips over that context as well.

I have similar problems whenever I send it to investigate a bug and the local runtime is inside a container. It cannot reliably translate paths without the help of an IDE. Hell, it even occasionally mangles API paths if I have it prefixed elsewhere in the codebase (despite having Claude.md etc, your context needs to be pure for it to be reliable). Having it fix a Dockerfile is comically bad.

Any luck with integrating platform.io? Have a esp32 project but VSCode can't provide type hinting with it's main c++ extension that is used by platform.io.

In my experience there are three ways to be successful with this tool:

• write something that already exists so it doesn't need to think
• do all the thinking for it upfront (hello waterfall development)
• work in very small iterations that doesn't require any leaps of logic. Don't reprompt when it gets something wrong, instead reshape the code so it can only get it right

The issue with debugging is that it doesn't actually think. LLMs pattern match to a chain of thought based on signals, not reasoning. For it to debug you need good signals in your code that explicitly tell what it is doing and the LLMs do not write code with that level of observability by default.

Edit: one of my workflows that I had success with is as follows:

• write a gherkin feature file describing desired functionality, maybe have the LLM create multiple scenarios after I defined one to copy from
• tell the LLM to write tests using those feature files, does an okay job but needs help making tests run in parallel.
• if the feature is simple, ask the LLM to make a plan and review it
• if the feature is complex then stub out the implementation in code and add TODOs, then direct the LLM to plan. Giving explicit goals in the code itself reduces token consumption and yield better plans

Yeah, to some extent that's what is going to happen. For a some of us the question isn't "if" but how long will we have to endure.

Don't do anything that would get you in trouble 😉 And that's about all we can say online. The rest can be said when you come over for some wine:

https://youtu.be/JhZkPRtc4Go

People saying because it's a woman but honestly I was thinking it works because you're creating a small human connection in a system that alienates us from each other, providing "value" we didn't know we nedded

More offended being called a lib really. And I seriously don't think that joke was homophobic, but comedy is in the eye of the beholder so it is whatever you say it is.

Amazing. Off an executive and the corporation gets a life insurance payout, but arson? Waluigi is on to something

Maybe 1% of them are winning

Would insurance cover the damage?

Fuck that. Saying empires are inevitable is a lot like saying fascism is inevitable. Maybe it's true but you shouldn't identify with the thing and make it's purpose your own