News for hackers. Stuff that matters.
Re:AI Coding Assistants Are Getting Worse by nfw2 on Thursday January 08, 2026 @08:17PM (#46548936)
Latest reasoning models don't claim 2 + 2 = 55, and it's hard to find them making an sort of obviously false claims, or not admitting to being mistaken if you point out that they are
Re:AI Coding Assistants Are Getting Worse by taormina on Thursday January 08, 2026 @10:25PM (#46549719)
I can’t go a full a full conversation without obviously false claims. They will insist you are correct and that your correction is completely correct despite that also being wrong.
Re:AI Coding Assistants Are Getting Worse by nfw2 on Friday January 09, 2026 @01:45AM (#46550788)
Ironically the start of this thread was bemoaning the use of anecdotal evidence
Re:AI Coding Assistants Are Getting Worse by citizenpaul on Friday January 09, 2026 @05:09PM (#46560093)
Also that I specifically mentioned bikeshedding yet the reply bikesheds my simple example. While ignoring the big picture that LLM's still regularly generate blatantly and easily noticed false information as answers.
Re:AI Coding Assistants Are Getting Worse by citizenpaul on Friday January 09, 2026 @04:55PM (#46559937)
It was clearly a simplified example, like I said endless bikeshed.

Here is a real one. I was using the much lauded new Gemini 3? last week and wanted it to do something a slightly specific way for reasons. I told it specifically and added it to the instructions. DO NOT USE FUNCTION ABC.

It immediately used FUNCTION ABC. I asked it to read back its instructions to me. It confirmed what I put there. So I asked it again to change it to another function. It told me that FUNCTION ABC was not in the code, even though it was clearly right there in the code.

I did a bit more prodding and it adamantly insisted that the code it generated did not exist, again and again and again. Yes I tried reversing to USE FUNCTION XYZ. Still wanted to use ABC