Cursor IDE support hallucinates lockout policy, causes user cancellations

Post by ToValueFunfetti » Wed, Apr 16, 2025, 8:19 PM UTC

gitremote wrote: post #578

ToValueFunfetti wrote: post #533

Earlier quoted context omitted.

Yes, so in my first example in the GP, this happens first. Humans do the work. The calculator double checks and gives me a list of all errors plus 5% of the non-errors, and I only need to double check that list. In my third example, the calculator does the hard work of dividing, and humans can validate by the simpler task of multiplication, only having to do extra work 5% of the time. (In my second, the unreliablity…

In your first example, you appear to assume that for calculations where "each mistake could cost $millions or lives", engineers who calculated by hand typically didn't double-check by redoing the calculation, so a second check with a 95% accuracy tool is better than nothing. This assumption is false. I suggest you watch the 2016 film Hidden Figures to understand the level of safety at NASA when calculations were done…

Post by kazinator » Wed, Apr 16, 2025, 8:45 PM UTC

jimbokun wrote: post #531

nkoren wrote: post #458

Earlier quoted context omitted.

I've been doing AI-assisted coding for several months now, and have found a good balance that works for me. I'm working in Typescript and React, neither of which I know particularly well (although I know ES6 very well). In most cases, AI is excellent at tasks which involve writing quasi-custom boilerplate (eg. tests which require a lot of mocking), and at answering questions of how I should do _X_ in TS/React. For th…

> AI is excellent at tasks which involve writing quasi-custom boilerplate (eg. tests which require a lot of mocking) I wonder if anyone has compared how well the AI auto-generating approach works compared to meta programming approaches (like Lisp macros) meant to address the same kind of issues with repetitive code.

Post by cachvico » Wed, Apr 16, 2025, 9:05 PM UTC

tptacek wrote: post #238

ericwood wrote: post #223

Earlier quoted context omitted.

I naively bought into the idea of a future where the computers do the stuff we’re bad at and we get to focus on the cool human stuff we enjoy. If these LLMs were truly incredible at doing my job I’d pack it up and find something else to do, but for now I’m wholly unimpressed, despite what management seems to see in it.

Well, I've spent my entire career writing software, starting in C in the 1990s, and what I'm seeing on my dev laptop is basically science fiction as far as I'm concerned.

Post by Azeralthefallen » Wed, Apr 16, 2025, 9:53 PM UTC

mntruell wrote: post #272

(Cursor cofounder) Apologies - something very clearly went wrong here. We’ve already begun investigating, and some very early results: * Any AI responses used for email support are now clearly labeled as such. We use AI-assisted responses as the first filter for email support. * We’ve made sure this user is completely refunded - least we can do for the trouble. For context, this user’s complaint was the result of a r…

Post by nyrikki » Wed, Apr 16, 2025, 11:38 PM UTC

cachvico wrote: post #586

xvector wrote: post #325

Earlier quoted context omitted.

> Do you double check that the LLM hasn't magically recreated someone else's copyrighted code? I frankly do not care, and I expect LLMs to become such ubiquitous table-stakes that I don't think anyone will really care in the long run.

That's really a non-issue. Anything copyrightable is non-trivial in length and complexity to the point that an LLM is not going to verbatim output that.

    >>> Please write a hello world app in java
    ```java
    public class HelloWorld {

        public static void main(String[] args) {
            System.out.println("Hello, World!");
        }
    }
    ```