I asked a local instance of Qwen3.5 122b: "American indie rock/pop band that formed in Ann Arbor, Michigan, in 2001 best known for their eclectic musical style, whimsical lyrics, and distinctive visual aesthetic involving matching colored ties and hats?"
Got this back "The band you are describing is Tally Hall.
Formed by friends at the University of Michigan, they became well-known in the mid-2000s internet era for their songs like "Good Day" and "Rooftops," as well as their signature look where each member wore a suit with a tie and fedora in a specific color (Red, Blue, Yellow, Green, and Black/White)."
Update: The gpt-oss-120b also got it correct on my prompt version.
Update 1: Llama 3.1 70B gets it right as well.
Update 2: Deepseek V4 Flash gets it right.
Update 3: Glm 4.5 Air gets it right as well
Can't seem to get any smaller models to get it.
So seems it could be an issue of data points on which the model can latch onto, the more the merrier, as they say. When asked the "What was that weird band from michigan from the 2000s that wore coloured ties" was not able to get it right.
It gets worse, I thought they installed such LCD display to virtually display the shuttle in real life size or something :) The importance of proper titles...
Reading this thread I realized something, I am just as annoyed with the upsells but have I e-mailed them and communicated my dissatisfaction with the family plan upsell popup instead of online ranting? No. I am wondering how many others did?
I always read about people and ads in Windows, haven't seen any ad ever (both 10 and 11), I am wondering what's going on (I don't use any of them debloaters either).
Among various reasons:
- Most people overcomplicate things, in general, not just in web dev.
- Not using the right tool for the job (I often run into sites displaying static content where they are using a bunch of frameworks and unnecessary code)
Fastest logo design in the business, ready in just a few hours, not days. All designed by human (me), no AI, no templates!