Comment by sarchertech
2 hours ago
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.
I've found that Gemini with Google maps integration does this pretty well.
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
> LLMs aren't mapping applications, they're reasoners.
No they aren't. They're statistical token generators. They do not understand concepts such as "distance from a given location or coordinate point". If you're lucky you might ask it something likely to appear nearly verbatim in its training data, like "Chinese restaurants in Midtown Manhattan", and get back a reasonably accurate list, but it does not understand what a "Chinese restaurant" is, or what "Midtown Manhattan" is, or that one relates to the other in any way other than both appearing statistically associated with another set of tokens when they appear near each other.
I wasn’t asking it to pull it from its training data, I was asking it to search.
Also reasoners that can’t recall facts is not how people are using them. No one is asking “from first principles derive this equation”.
GPT 5.5 Pro is worth the increased price of the higher subscription.
I have it. Got the same issues with xhigh and pro.