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.

Everything listed should be done before ever getting into code along with business and product partners.

Ehh, it really depends on where the risk is and the problem is LLMs can’t evaluate for that unless you feed it everything. Some projects need code experiments before you settle on an architecture, but that’s only if you’re a pioneer (which frankly is where the money is at).

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

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.

Removed by mod

It’s one of those “every accusation is a confession”. People are thinking about themselves when talking about others.

It’s what Kirk would have wanted RIP

I wonder if you could prompt inject with QR codes…

It’s an analogy that illustrates that you are doing his PR work in order to serve an unrelated cause. Is that clear enough to understand or do you want to send people with butterfly nets after me?

You have two masters and one is problematic. It’s nice that your master said kind things about the other, but you still have two masters.

Edit: I don’t follow the guy, I only know that this is a good thing only IF y’all convince others PewDiePie is a good guy actually.

I think you make a better point than I did. I am responding to someone looking at a racist act and insisting it wasn’t racist but stupid.

He’s too dumb to be intentionally racist but he’s a great spoke person for your cause. 🙄

A win for who? Sounds like he will deter some people and attract others based on whether they think checks notes anti-Semitism is a deal breaker. Jesus Christ this is pathetic.

You think Xi has absolute power? Not even Mao had absolute power.

Opiate addict I talked to said your body was never meant to feel that good. That stuff wrecked my brother (a different addict).

You both are right but one is more consequential. Let’s dive in:

Bombing Iran does not have bipartisan support, many Dems are voicing their opposition. The Dems even advanced a bill where the president would need congressional review to specifically bomb Iran in this instance.

The President making unilateral military decisions like bombing Iran does have bipartisan support. The Dems have not challenged it’s constitutionality or proposed significant changes on this front and instead go for a case by case congressional veto. This policy also aides in our genocidal program of Gaza…

Pssh, mine uses a random number generator for odd numbers to return true 4% of the time to achieve higher accuracy and a bettor LLM metaphor