News for hackers. Stuff that matters.
Re:AI is going to hack Jira by anonymars on Friday June 20, 2025 @09:36AM (#44327629)
> Besides, even when AI hallucinates, when you interact with it again it is able to recognize its error and try to fix the mistake it made, just like a human would.

This feels beyond generous. I'm sure I'm not the only one who has led my AI assistant into a corner it couldn't get itself out of

Re:AI is going to hack Jira by mirsadm on Friday June 20, 2025 @09:53AM (#44327748)
I use LLMs all the time and if they make a mistake it's basically over. I'll start a new session because in my experience there's no recovery.
Re:AI is going to hack Jira by disgruntledphd2 on Friday June 20, 2025 @10:05AM (#44327864)
> I use LLMs all the time and if they make a mistake it's basically over. I'll start a new session because in my experience there's no recovery.

Yup, because the error becomes part of the prompt. Even if you tell them to do something different it's basically impossible for the model to recover.

Re:AI is going to hack Jira by 3D30497420 on Friday June 20, 2025 @09:41AM (#44327671)
> I'm sure I'm not the only one who has led my AI assistant into a corner it couldn't get itself out of

My team recently did a vibe coding exercise to get a sense of the boundaries of current LLMs. I kept running into a problem where the LLM would code a function that worked perfectly fine. I'd request tweak and it would sometimes create a new, independent function, and then continually update the new completely orphaned function. Naturally, the LLM was very confident that it was making the changes, but I was seeing no result. I was able to manually edit the needed files to get unstuck, but it kept happening.

Re:AI is going to hack Jira by zimzam on Friday June 20, 2025 @09:57AM (#44327788)
Yeah, the following has happened to me multiple times when I ask copoilot to fix something. It updates my code to version A, which is still broken. Then I share the error messages asking for a fix, resulting in version B, which is also broken. Then I share the error messages and copilot confidently changes things back to version A, which is still broken.

It will confidently explain version A is broken because it isn't version B, and version B is broken because it isn't version A. There's no "awareness" that this is cycle is happening and it could go on indefinitely.