IT’S HERE ✨ The 10th edition of the Human Era Calendar: https://shop.kgs.link/12026Join us in 12,026 to celebrate humanity’s connection to the stars with a y...
Maybe not that interesting for everyone here, but I found no better community for this.
Then other day I was trying to find out how to get just one AD account not to sync through to Azure without disabling it. And the AI came up with this complicated instruction set that didn’t work and was totally made up from nowhere. Now what on earth was the point in doing that?
At one point it told me I had to triple click on something. Because that’s totally a thing.
It’s so fun when it’s so specific about some detail with casual confidence that is based on absolutely nothing at all. I know ultimately it’s architecture is more akin to a predictive word generator, but it seems so much better.
Saw a clear demonstration and it is wild that the output is consistent, but at least in the model I saw being run, every word is generated without it having considered what the word after would be or what the general concept it is going for. For a human one has to already know the concept before he/she starts putting words to it, but at least the models I’ve seen explained with detail, it manages to assemble it word by word without knowing where it is trying to go in advance.
You might try setting Google’s Web subsearch as your main search engine, or else put your searches through https://udm14.com/, which does the same thing.
Google still does its psychotic summarys though.
Then other day I was trying to find out how to get just one AD account not to sync through to Azure without disabling it. And the AI came up with this complicated instruction set that didn’t work and was totally made up from nowhere. Now what on earth was the point in doing that?
At one point it told me I had to triple click on something. Because that’s totally a thing.
It’s so fun when it’s so specific about some detail with casual confidence that is based on absolutely nothing at all. I know ultimately it’s architecture is more akin to a predictive word generator, but it seems so much better.
Saw a clear demonstration and it is wild that the output is consistent, but at least in the model I saw being run, every word is generated without it having considered what the word after would be or what the general concept it is going for. For a human one has to already know the concept before he/she starts putting words to it, but at least the models I’ve seen explained with detail, it manages to assemble it word by word without knowing where it is trying to go in advance.
Yeah, after seeing it hallucinate on things I actually know, I’ve decided to never trust it.
You might try setting Google’s Web subsearch as your main search engine, or else put your searches through https://udm14.com/, which does the same thing.