Email chain is a mile long going back 3 months
Oh yes, I love those. Maliciously complying would mean taking the morning to read that novel, thoroughly.
Email chain is a mile long going back 3 months
Oh yes, I love those. Maliciously complying would mean taking the morning to read that novel, thoroughly.
Opens ticket
Ticket only says “read customer email and advise”
Email chain is a mile long going back 3 months
Closes ticket with “please clearly and concisely explain the problem in the next ticket you open”
3 day SLA on our tickets, so back to the end of the line they go.
Little over a decade ago I dealt with internet on trains. One ticket read "internet doesn't work".
No info who submitted it.
No info when.
No info which carriage.
No info which train.
No info which route or any other clues as to the geographical location. Could have been inside of a tunnel for all I know.
Malicious compliance to the rescue.
Call them just to say "ticket closed" and hang up.
I hope ticket systems have ways to assign priorities to users, so you can deprioritize any future requests coming from them
Asset tag: Broken printer.
Office location: BROKEN PRONTER.
Requester: BOOKEN PINTOOOR!!!
"Computer machine, it no works"
Do ticket templates not work?
For real. I get tickets like this issued for/on behalf of a location. So I don't know who, what, where (within that location), when, why, or how...
And when remoted, open the ticket system and fill it out for them as they answer your directing questions. Once done, let them know that the new ticket will be handled according to the sla. At low priority.
This is actually where a phone call can be beneficial if you’re assertive about the questions and cut them off when they get squirrely. Some people will never figure out how to get to the point over a ticket because they cannot organize their thoughts no matter how well formed your written instructions are. Get them on the phone and just remote to their workstation.
Ma’am, in the ticket you indicated “Shits busted” but could you give me some additional details?
The context is optional. But without context, copilot has nothing to work on. So the correct answer should be:
„Are you stupid?! Which numbers are you talking about?“ instead of „sure thing, the sum of nothing is clearly 15!“
There would be no way to do that reliably. There's too much weird stuff people might say to reference things, and the LLM would definitely act on the wrong cells more often than not.
Excel already has a perfectly unambiguous way to provide a specific range of cells, Which is why the =COPILOT() function lets you supply those in the second parameter. I'm assuming they get passed to the LLM as context, likely encoded as a markdown table. LLMs love parsing markdown, apparently.
The user provided no such range of cells, though, so the LLM is most likely seeing none of those other cells, and is just working based on random values from the Internet.
The COPILOT function only has access to data provided through the context arguments. It does not have access to:
Other data from the workbook
You give them too much credit.
Yes, but "above" just goes into the LLM,
I don't believe even Microsoft are this stupid. The llm will have tools to interrogate the spreadsheet.
yeah, that shitshow was one epic nothingburger in the end.
This one is looking to clock in at toddler level
Yes, but "above" just goes into the LLM, which does who-knows-what with it, and certainly isn't designed to address cells that way. So to the LLM that's just like any other arbitrary text.
For all of its faults, the Windows Server ecosystem is incredibly good at providing graphical configs for everything that you'll need for a small to medium sized business, and Windows servers can really survive a surprising amount of abuse. For most things it's at least acceptable, and on a couple of things (Active Directory with Group Policy, as well as RDP) it's best in class and very difficult to beat
Of course all of Microsoft's killer products were built at least 25 years ago by engineers who've long since left the organization and it shows. Microsoft is trying so hard to move everything to Azure so they can charge monthly for access, yet everything they build into Azure is somehow worse than the on-prem alternative and as they stop updating on-prem options and keep forcing more and more migration into Azure businesses are going to get more and more frustrated with the constantly rising costs and constant loss of quality. Oh and whenever there's another Azure outage it's going to be increasingly un-fun as everything migrates into Azure
bunch of text you shoved into a spreadsheet, say for example customer testimonials or something
Lol more features for people abusing Excel and trying to treat it like a database
Ah, sorry, I though you were disagreeing with me by posting a link that companies are unsuccessful with it, so I was confused - because my point was that error rate is gigantic. My bad!
Hilariously that's part of how Facebooks llama.cpp local chatbot became so popular. It was initially released only to researchers and research institutions but someone rapidly uploaded it to some warez sites and the cat was out of the bag from there. Subsequent releases of llama were released under far more permissive licenses after it became clear that it wasn't as dangerous as they feared