logoalt Hacker News

sarchertechyesterday at 7:09 PM3 repliesview on HN

I’ve noticed the same thing at work with Opus 4.8.

ChatGPT on my personal plan does it too. Just yesterday I asked it to give some places fitting a specific criteria. The first was that they were within a 2 hour drive of my city. 75% of the locations it gave me were more than 2x that distance. It kept doing this across multiple difference searches. I tried high and pro with no difference.


Replies

diceyesterday at 7:27 PM

I've found that Gemini with Google maps integration does this pretty well.

trvzyesterday at 7:37 PM

GPT 5.5 Pro is worth the increased price of the higher subscription.

show 1 reply
colonCapitalDeeyesterday at 7:17 PM

That's not surprising, LLMs are bad at pulling hyperspecific facts out of memory. LLMs aren't mapping applications, they're reasoners. Just a poor problem fit

show 2 replies