News for hackers. Stuff that matters.

A comment on Even GPT-5.2 Can't Count to Five: Zero-Error Horizons in Trustworthy LLMs. Parent comment

Re:Even GPT-5.2 Can't Count to Five: Zero-Error Horizons in ... by kenjackson on Thursday April 02, 2026 @02:30PM (#47618313)
Weird. I tried in chatGPT auto and it worked perfectly. I tried like 10 variations. I also did the letters in words. Got all of them right.

The one thing I did trip it up on was "Is there the sh sound in the word transportation". It said no. And then realized I asked for "sound" not letters. It then subsequently got the rest of the "sounds-like" tests I did.

Clearly, my ChatGPT is just better than yours.

[ Parent | on HN ]
Re:Even GPT-5.2 Can't Count to Five: Zero-Error Horizons in ... by revachol on Thursday April 02, 2026 @02:41PM (#47618460)
heh, interesting that. I just tried it twice more with ChatGPT "Instant" (disabling "Auto-switch to Thinking") and it got it wrong both times. Does yours get it right without thinking or tool calls? If so, maybe it does like you better than me.
[ Parent | on HN ]
Re:Even GPT-5.2 Can't Count to Five: Zero-Error Horizons in ... by kenjackson on Thursday April 02, 2026 @04:22PM (#47619681)
OK, I didn't think to disable switch to thinking (didn't know this was a mode). When I did that then it did get it wrong -- oddly it took about the same amount of time, so thinking mode wasn't taking longer, but it was more accurate.
[ Parent | on HN ]
Re:Even GPT-5.2 Can't Count to Five: Zero-Error Horizons in ... by revachol on Thursday April 02, 2026 @06:45PM (#47621171)
Right, though I didn't explicitly disable thinking for my first attempt either. I'd guess my prompt was less detailed than yours and so ChatGPT (in "Auto" mode) decided to allocate thinking tokens for your questions but not mine.
[ Parent | on HN ]