I imagine this type of automation existed before LLM agents came along - what do they add? Is it just the ability to evaluate the product description? Item quality is already listed as a categorical variable.
I imagine this type of automation existed before LLM agents came along - what do they add? Is it just the ability to evaluate the product description? Item quality is already listed as a categorical variable.
Ongoing tasks, arbitrage for mispriced postings in ways that aren't currently exploited that LLMs make feasible - by banning auto-buy, maybe they're attempting to delineate between human seeming behavior and automation, and giving AI permission to buy looks too much like a real person?
Seems pretty petty to me.
If I were going to automate something like this, I'd have a suite of products to watch for - common enough to be reasonably frequent but obscure enough to be mispriced, kinda the whole idea behind secondhand ocmmission / antique / estate sale shops.
I don't know how EBay is supposed to differentiate automation from real users in this scenario. To get around it, all you need is human intervention at the last act, so you could fire up your bot and have it forward the "buy now" link when all parameters are met? Maybe they just don't want AI companies to have an argument for some sort of revenue sharing or commissions.
On the other hand, when people list a steeply discounted item, there's usually a good reason why they do so - opportunities for easy arbitrage are rare because people would usually prefer not to give you free money if they can help it. Signing up to automatically buy broken items for $600 without so much as looking at their condition seems like an easy way to lose a lot of money.
I'm not sure how they would intend to stop it with this policy anyway. It at best is going to be an arms race detecting them. What it does do is prevent upfront the ham handed excuse of "I didn't bid on this, my bot did".
Just a random example:
https://www.ebay.com/itm/376783554515
It clearly says "Buyer pays return shipping."
I've seen enough by now and I know that some people will just unleash LLMs on anything without almost no oversight. We can already see people use agentic IDEs with "do all the shit" flag, they would probably easily add finances to the list of automation.
But, honestly, would you?
*OpenAI issues a micro auction to glass cleaner companies and distributors to see who will bid the highest combined commision*
"Sure thing! I ordered some Glass Clean Plus from Target for you!"
My mistake, you're completely correct, perhaps even more-correct than the wonderful flavor of Mococoa drink, with all-natural cocoa beans from the upper slopes of Mount Nicaragua. No artificial sweeteners!
So now imagine ten thousand of these jerks telling their AI of choice "hey go scrape everything you can and re-list it for 10% more". That's a lot of load on the platforms at both ends for listings that are unlikely to generate many sales.
The right way to use LLMs here is to have them write (and perhaps maintain) scraping scripts and run those.
Stuff that used to have to be laboriously scripted can now be pseudo code.
That said, I guess that's not quite the sort of "buy for me AI" that eBay is after here
Really, dealing with bullshit for you is by far the biggest promise of any agentic solutions today.
Web got infested by ads, I wonder BS will agents use.
"Buy good quality for less than market value and don't get scammed" is so far beyond AGI complete that I cannot fathom how people think it will be reliably doable by LLMs
I think it's telling though how everyone's example of how an AI agent can help you shop is "I want it to take advantage of someone else's mistake or knowledge asymmetry to make me free money".
Are you all just embarrassed used car salespeople?
An AI that shops for a blind user, for one free example of the untold and unexplored uses of new technology.