Air Canada is responsible for chatbot's mistake: B.C. tribunal • Hacker News Board

Re: Air Canada is responsible for chatbot's mistake: B.C. tribunal

#431

Post by mmh0000 » Wed, Feb 21, 2024, 8:01 PM UTC

itsoktocry wrote: post #326

wongarsu wrote: post #308

Earlier quoted context omitted.

It's not like human call center staff has never given anyone wrong information, or cost companies money in fines and lawsuits. The bar LLMs have to clear to beat the average front line support operations isn't that high, as your own experience shows. And compared to a large force of badly paid humans with high turnover, LLMs are pretty consistent and easy to train to an adequate level. They won't beat great costumer…

> It's not like human call center staff has never given anyone wrong information, or cost companies money in fines and lawsuit A human will be more likely to say "I don't know" or pass you along, rather than outright lie.

Maybe... Over two decades ago (holy crap, I'm old), I used to work in the call center for a major airline. I was the guy you got when you complained to the 1st level rep that you wanted their manager, then you got sent to the 2nd level rep and wanted their manager. And that was me.

90% of my job was undoing and compensating passengers for the incorrect information either the phone agent or gate agent gave them. The other 10% was dealing with workarounds to technical issues in our booking software.

Re: Air Canada is responsible for chatbot's mistake: B.C. tribunal

#432

Post by citizenpaul » Thu, Feb 22, 2024, 5:16 AM UTC

eru wrote: post #424

citizenpaul wrote: post #418

Earlier quoted context omitted.

Yeah they pass those cost saving right onto record corporate profits for the last 20 years...

Huh? Airlines are notorious for being bad for investors. (And even without looking up any data, I find your 'record profits for the last 20 years' hard to square with my memories of covid.) EDIT: I tried to find some indices for airlines. The closest I found was https://finance.yahoo.com/quote/JETS/performance/ which didn't exactly have a stellar performance. So I'm not sure where you get your claim from?

I wasn't referring to airlines specifically. I see how I was unclear now. We are in a decade+ era of record corporate profits yet incomes are stagnate and costs are rising.

Airlines are weird. I think warren buffet said something about airlines being the most complicated way to guarantee losing money as a business or something like that once.

Re: Air Canada is responsible for chatbot's mistake: B.C. tribunal

#433

Post by fennecfoxy » Fri, Feb 23, 2024, 3:13 PM UTC

steveBK123 wrote: post #389

wongarsu wrote: post #308

Earlier quoted context omitted.

It's not like human call center staff has never given anyone wrong information, or cost companies money in fines and lawsuits. The bar LLMs have to clear to beat the average front line support operations isn't that high, as your own experience shows. And compared to a large force of badly paid humans with high turnover, LLMs are pretty consistent and easy to train to an adequate level. They won't beat great costumer…

It's still way too easy to send LLMs into a complete tangent of rambling incoherently, opening yourself up to the LLM making written statements to customers you really don't want. I recently asked some LLMs "How many gallons in a mile?" and got some very verbose answers, which turned into feats of short story short stories when I refined to "How many gallons of milk in a mile?"

Only because the models have seemingly only been trained on generating text that matches a prompt, ie prompt completion. Rather than knowledge retrieval/parsing/organisation.

If part of the training was to only use knowledge sourced from a vector db and that it is allowed to use its trained knowledge only for grammar rules, phrasing or rewriting information then I think it would do a lot better.

Doesn't seem like many models are trained on prompts like "Question Q"->"[no data] I'm sorry but I don't know that" = accepted during training.

This would help immensely for not just for chatbots but for personal use too. I don't want my LLM assistant to invent a trip to Mars when I ask it "what do I have to do today" and my calendar happens to be empty.

Re: Air Canada is responsible for chatbot's mistake: B.C. tribunal

#434

Post by eszed » Sat, Feb 24, 2024, 7:01 PM UTC

pintxo wrote: post #425

eszed wrote: post #204

Earlier quoted context omitted.

I did not know that! Thanks. Indeed, "family run", depending on where they are in the internal-to-the-family management-transition cycle, is more encouraging to me than "publicly held". ("Private equity" is always and everywhere a huge red flag.) It's depressing to me that we have to think about those things. I mean, "buyer beware" has always been the case, but it seems like we have to be more wary (or more wary of m…

It might be just the normal process of capitalism in which you see take-over after take-over leading to ever bigger companies?

"Capitalism" is very much in the eye of the beholder, and different regulatory models create market economies with different incentives. What you're talking about is "normal" in certain places.

I didn't mean that, though, and I don't think it's what the other people in this thread did, either. I was thinking of the practice whereby private equity funds purchase companies and exploit the "brand equity" they've built up over the long term, whilst deliberately enshittifying them, in order to make a short-term profit for the new owners. That's been normalized, in some places, but I wish it were not, and would prefer that financial markets be regulated in ways that make it un-profitable.