New on LowEndTalk? Please Register and read our Community Rules.
All new Registrations are manually reviewed and approved, so a short delay after registration may occur before your account becomes active.
All new Registrations are manually reviewed and approved, so a short delay after registration may occur before your account becomes active.
Comments
In a multi-AI consult, even DeepSeek V4 brings unique findings to the table from my experience picking up issues even SOTA models didn't (confirmed by SOTA models). My multi-AI consults on average surface 50% to 200% more findings than standalone Claude Fable 5 or GPT-5.6 Sold can find!
I mainly use the multi-AI consults at planning or post-implementation verification phase so relatively they don't use as much tokens but ensure you start with an accurate plan to begin with = saving you tokens and time - preventing you from going down the wrong path.
Yes but reasoning is expentional the more models, 3 is intensive, 4 is very intensive, 8+ is stupid, or they aren't all reasoning with each-other and it's selective which is just as random as not having that many.
"Unique Findings" no was just that particular prompts which founds some of that particular billions of parameters at that time, all other models capable.
I assure you this is a waste of reasoning and LLM compute, it's beyond useless to have more than 4 models consult.
**4 models create 6 pairwise relationships; 8 create 28. **
Simply put, if it doesn't over-comptue that they aren't all reasoning with eachother anyways.
Well I don't use all the LLM models all the time, I said up to 8 LLM models supported. I usually only use 2-4 of them, Claude, GPT-5.6 Sol, GLM-5.3 are the main 3 right now.
I recall @layer7 has one of the best practice when responding to ticket
Too bad image that @sillycat post already expired
I think part of the “getting old” feeling is noticing other people behaving in ways you wouldn’t have considered acceptable yourself.
And I swear it’s not just me becoming a grumpy old man, staring at a wall of AI-generated text and muttering that the young whippersnappers should go back to actually debugging things (yet)
how do you feel about unboxing videos?
Hi,
the general practice with any kind of non technical what ever bla bla blob ( no matter if its coming from the internet / forum / blog or AI ) is that the longer the text is, the less brain activity will be done and more and more frequently whole lines of bla bla will just be skipped by my eyes and the brain will filter more and more the rest.
When i reached the buttom of this and did not understand it, i ask for clarification and more technical details :-)
EDIT:
But to contribute something more real here:
@SplitIce yes. The future is agents handling things. If they cant, the senior level agent handles ( Token will be more expensive ). And that goes up until some human will read it.... maybe
I probably would have gone another 10-15 years in ignorant bliss if it wasn't for this!
If I worked in support, I'd be the guy reminding people they need some admin skills and to get managed services instead.
At least people haven't started calling you "granny" yet
Huh? Is your daughter already pregnant or something? Or your nephews kid?
She's only got one son, but he's struggling with a drug addiction.
Oof. There's so much drug in NL. Can't go hiking or picnic or sitting on a park bench without smelling pot.
What's being unboxed?
That reminds me of university days when one of our friends was called "Grandma $SURNAME" by almost everyone because she was a year older than everyone else.
It's simple. You feed that ticket into your AI along with your findings and ask it to frame a response that is relevant. AI problems require AI solutions.
Aluy has you click a check-box where you confirm that the message was written by a human. Presumably not selecting it lowers the priority or prompts you to turn off your clanker and try again.
I was tempted, to not check it a couple times, to see what happens 🤣
Oh me too.
It's wnba player
I have few services that do this, always respect it, and it's always fucking fixed correctly.
30 is old now .
Is it just on high priority tickets? I feel that maybe a checkbox that says "I confirm that I have done basic troubleshooting and included technical readouts" might actually be fair for high priority tickets.
Pretty much all the notes examples of these ai generated tickets were opened as high priority (even if they were sales / capability questions)
Yes. 30 years old boomer
'Alledgely'
AI slop is the worst
Nope... old feels like saying "meeh! fuck it!" about anything anytime.
Got to market and all regular human-op registers are empty and just self-pay registers?! You say: "Meh, fuck it!" and just leave the cart there and leave.
Your car makes weird noise and the service is quoting you a 5h+ bill?
"Meh! Fuck it!" - you just turn up the music and stop hearing that noise.
You should take out the trash but you just stare at it for a while and go: "Meh! Fuck it!".
This can be mixed up with laziness but ... meh... fuck it! Who cares?!
I agree, it’s not fun at all when reviewing tickets. It’s doesn’t help when many types of businesses are incentivised to use it.
Even when clients publicly state they ignore AI responses to tickets from the vendor for example. It just continues because why not.
The countless times I’ve read clients getting mad about slop from the vendor, only for it to continue as normal is concerning.
The joys of being in the service business.