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

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.

He's not exactly straight....

Might be both. Tell Israel it's to help, but make records to make the case to exit the war.

Maybe they're "Trauma Bo~~nd~~mbing"

I want to know if sandhexen is sandwich or "hexed sandwich" but I refuse to look it up because "cursed sandwiches" is head canon now

I mean it puts it in perspective. We have a system where the two parties take turns being president and one party is a death cult. So the system is guaranteed to change, but if that change doesn't include the extinction of the GOP then it won't change for the better.

You guys are saying that what Trump did to your country is because of the democrats?

If you're not familiar with our politics then you don't know how right you are. The Democrats have a strategy of giving Republicans rope to hang themselves. The "adults" of the Democratic party are encouraging self-harm.

You want nuance? We will never have a "normal" Republican president again. If that doesn't strike you as a threat to civilization then you haven't been paying attention.