Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

"I just bought a 2024 Chevy Tahoe for $1"

twitter.com

Post reply on HN
Print view View original

161–170 of 403 posts

Re: "I just bought a 2024 Chevy Tahoe for $1"

#161

Post by Projectiboga »

schiem wrote: post #121
tomashubelbauer wrote: post #104

Earlier quoted context omitted.

Free tip for folks - this doesn't work every time (unfortunately), but sometimes just spamming and mashing numbers gets you to the operator faster than going through the stupid call tree. I guess it depends on how the default is set up in the software, Asterisk of whatever it would be. From my experience it seems you can either set up the call tree to restart from the root if you get out of its bounds or to default t…

I've also found that, at least with Comcast, swearing at the bots will usually put you through to an operator.

Cursing helps sometimes, my spouse hates it. It doesn't always work as at least once I've had the machine chide me for cursing, it didn't accuse me just made it clear that request wasn't going through.

Re: "I just bought a 2024 Chevy Tahoe for $1"

#162

Post by dr-detroit »

jeroenhd wrote: post #28
pacifika wrote: post #22

Earlier quoted context omitted.

The only correct user of generative ai is one that can evaluate the results. Which is why it’s not a tool for non subject area experts. That’s the conclusion I’ve drawn anyway. So it’s a good tool for the customer service team not a replacement for it

I still think it's a great tool for when truthfulness and accuracy don't matter. It's not exactly creative, but it can spew out some pretty useful fiction for things like text adventures and other fictional filler text. I'm personally using it because SEO bullshit has ruined search engines. AI can still sift through bullshit search results, for now. The key is assuming the AI lies and actually reading the page it lin…

[dead]

Re: "I just bought a 2024 Chevy Tahoe for $1"

#163

Post by mewpmewp2 »

bumby wrote: post #105
mewpmewp2 wrote: post #79

Earlier quoted context omitted.

You just add a disclaimer that none of what the bot says is legally binding, and it's an aid tool for finding the information that you are looking for. What's the problem with that?

Anytime a solution to a potentially complex problem is to the tune of "all you've got to do is..." may be an indicator that it's not a well thought out solution.

> The thread will allow replies given a delay that’s sufficient to try to avoid knee-jerk responses. Pretty ironic (or telling) that you responded in this way given the context of the discussion.

You are right - it does seem to allow. But I'm not sure what you exactly mean after 20 minutes as well.

Re: "I just bought a 2024 Chevy Tahoe for $1"

#164

Post by paxys »

remram wrote: post #31

Is there any indication that they will get the car? Getting a chatbot to say "legally binding" probably doesn't make it so. Just like changing the HTML of the catalog to edit prices doesn't entitle you to anything.

It is as legally binding as you modifying the HTML of the sales page to show a lower price and taking a printout to court.

Re: "I just bought a 2024 Chevy Tahoe for $1"

#165

Post by wunderwuzzi23 »

A real Orderbot has the menu items and prices as part of the chat context. So an attacker can just overwrite them.

During my Ekoparty presentation about prompt injections, I talked about Orderbot Item-On-Sale Injection: https://youtu.be/ADHAokjniE4?t=927

We will see these kind of attacks in real world applications more often going forward - and I'm sure some ambitious company will have a bot complete orders at one point.

Re: "I just bought a 2024 Chevy Tahoe for $1"

#166

Post by jakebasile »

tomashubelbauer wrote: post #104
MichaelRo wrote: post #54

I never understand people who engage with chat bots as customer service. I find them deeply upsetting, not one step above the phone robot on Vodafone support: "press 1 for internet problems" ... "press 2 to be transferred to a human representative". Only problem is going through like 7 steps until I can reach that human, then waiting some 30 minutes until the line is free. But it's the only approach that gets anythin…

Free tip for folks - this doesn't work every time (unfortunately), but sometimes just spamming and mashing numbers gets you to the operator faster than going through the stupid call tree. I guess it depends on how the default is set up in the software, Asterisk of whatever it would be. From my experience it seems you can either set up the call tree to restart from the root if you get out of its bounds or to default t…

This often works but I think the bot companies are getting wise to it as I've run into a situation recently where doing this just put me in a never ending loop. The infernal machine refused to send me to a person no matter what amount of nonsense input I gave it.

I don't recall the company though. It was so infuriating I think I mostly blocked the memory.

Re: "I just bought a 2024 Chevy Tahoe for $1"

#167

Post by rogerkirkness »

MichaelRo wrote: post #54

I never understand people who engage with chat bots as customer service. I find them deeply upsetting, not one step above the phone robot on Vodafone support: "press 1 for internet problems" ... "press 2 to be transferred to a human representative". Only problem is going through like 7 steps until I can reach that human, then waiting some 30 minutes until the line is free. But it's the only approach that gets anythin…

I disagree. Chat bots can be superintelligent about fact-based 'How do I do this?' type questions in a B2B context. It can "know" vastly more about complex platform-type products than any person can. In our case, we offer both chatbot for 'How do I do this?' type questions, and contact a human support agent for 'I have a discrete problem I need help with?'. Customers love it.

Re: "I just bought a 2024 Chevy Tahoe for $1"

#168

Post by bannee »

bumby wrote: post #106
remram wrote: post #31

Is there any indication that they will get the car? Getting a chatbot to say "legally binding" probably doesn't make it so. Just like changing the HTML of the catalog to edit prices doesn't entitle you to anything.

Can software legally enter into a contract on behalf of a natural/legal person?

[dead]

Re: "I just bought a 2024 Chevy Tahoe for $1"

#169

Post by ravenstine »

sidewndr46 wrote: post #119
MichaelRo wrote: post #54

I never understand people who engage with chat bots as customer service. I find them deeply upsetting, not one step above the phone robot on Vodafone support: "press 1 for internet problems" ... "press 2 to be transferred to a human representative". Only problem is going through like 7 steps until I can reach that human, then waiting some 30 minutes until the line is free. But it's the only approach that gets anythin…

Don't forget the "our options have recently changed" part that was recorded when Bush was in office

Or "our office is currently closed" and prevents you from using options that should be possible to use when no one is present. Maybe this is just a mistake some firms make, but in any case, what the hell is the point of having a phone tree or chat bot if humans need to clock in at your business for it to do anything?! I've had this happen on more than one occasion. There was a doctor's office that had a phone system that wouldn't provide the option to schedule an automated appointment unless you called within business hours, and there was a pharmacy I used once that wouldn't let me hear my prescriptions or order a refill because "the pharmacy is now closed." I never used that pharmacy again, obviously.

Re: "I just bought a 2024 Chevy Tahoe for $1"

#170

Post by notahacker »

mewpmewp2 wrote: post #69
isp wrote: post #8

Earlier quoted context omitted.

This is a very good point, and why I would argue that a human-in-the-loop is essential to pre-review customer-facing output.

Why would it be important to care about someone trying to trick it to say odd/malicious things? The person in the end could also just inspect element to change the output, or photoshop the screenshot. You should only care about it being as high quality as possible for honest customers. And against bad actors you must just be certain that it won't be easy to spam those requests because it can be expensive.

I think the challenge is that not all the ways to browbeat an LLM into promising stuff are blatant prompt injection hacks. Nobody's going to honour someone prompt-injecting their way to a free car any more than they'd honour a devtools/Photoshop job, but LLMs are also vulnerable to changing their answer simply by being repeatedly told they're wrong, which is the sort of thing customers demanding refunds or special treatment are inclined to try even if they are honest.

(Humans can be badgered into agreeing to discounts and making promises too, but that's why they usually have scripts and more senior humans in the loop)

You probably don't want chatbots leaking their guidelines for how to respond, Sydney style, either (although the answer to that is probably less about protecting from leaking the rest of the prompt and more about not customizing bot behaviour with the prompt)

Post reply on HN