I don’t really know what constitutes a conspiracy theory. Diamonds in wedding rings are essentially worthless, yet people still pay exorbitant amounts for them. So, I guess I’ll leave it to personal judgment.
I don’t really know what constitutes a conspiracy theory. Diamonds in wedding rings are essentially worthless, yet people still pay exorbitant amounts for them. So, I guess I’ll leave it to personal judgment.
Today I learned that the owner of the WTC had it insured against terrorism just six weeks before its collapse and made $4.55 billion. I had a chat with an AI about probabilities, and it doesn’t paint a good picture.
If only ai didn’t get its information from people like us casually chatting on the internet, then passes off everything we say as fact.
It had been the target of less permanent terrorism multiple times before that.
Discussing conspiracies is basically the worst case for LLMs. They’re both extremely sycophantic (they try to figure out and tell you what you want to hear), and not grounded in real references.
If you must, use something like z.ai’s deep research mode, with a single even, neutral question. It’s way better than ChatGPT.
So is z ai an ai which uses more critical thinking patterns to make it better?
It’s GLM 4.6 underneath, which is a good model and has a really helpful “default” tone without a system prompt. And it’s open weights! I host it locally, sometimes.
But no. In of itself it does nothing different from other “thinking” LLMs.
What really sets the website apart is its “deep research” tool, specifically. It’s just good at scouring the web for references… it sucks that you can’t change the temperature/sampling, but for a free web portal, it’s not bad.
The guy set up the insurance for the building he just purchased that had a terrorist attack in 1993. Of course he got insurance for terrorism for a building he just purchased that was a target for terrorists.