I was testing the new SSMS (v22 Preview 3) with Copilot and ran into an interesting issue.
This is part of a series of experiments with AI systems.
My Query
I was working on something unrelated and tried this prompt, which should have saved me a few minutes from looking on MSLearn.
As you can see, I get a nice list of things. However, then this happened.
This kept going. I gave it a minute, then opened my screen recorder (which is close to a minute) and started recording.
After capturing this, I stopped the query. Things seem to work OK, but this is definitely something that concerns me about agents and letting them go. I don’t know if this was a stuck process, if this was consuming compute or tokens, but it was certainly an issue.


It concerns me greatly how too many are placing WAY too much trust in these things. It’s like the early days of search engines before people realized they were flawed we just assumed everything the search returned was true. That was also before we had placed as much reliance on the internet for everything as we have today and sop its more dangerous today that soo many have way too much faith and trust in these things. There was a Ziff Davis article in the last month where I believe is was Ed Bott (a long time author at ZD) who noted that the most common question he gets from readers is how to disable Copilot b/c of how bad and annoying it is. I’ve tested all that you can test for free and none are truly reliable. As I’ve said before they are improved query engines where the users doesn’t have to properly articulate their question to get the answers they need b/c the bot can better guess what the user is getting at then Google’s search can. They also are good at making things from existing things based on input/description from humans. They can’t actually create anything new per say just re-do things. There’s not enough healthy skepticism with regards to these things for my likings.
LikeLike
No different from anything else. Humans have been trusting things/people/etc for a long time without verification or rechecking.
AI is amazing. And it’s horrifying. You have to learn to work with it. Lots of people are having great success. Lots failing.
Like anything, it’s a tool.
LikeLike