The fact that there's a published recipe for a superhuman bot that can be trained for $150 and run on any desktop computer sounds like an existential threat to their business.
The main mitigating factor I can think of is that you'd need to also adversarially train it so it isn't distinguishable from a skilled human. But that doesn't seem like it would be too difficult.
Most people on sites like PokerStars are dumb money who just like to gamble. You are not going to win much money against the Pros anyway. If you create a bot like that yourself, then you are just one more of these Pros, basically. If you don't, then you use some published / commercial bot, and PokerStars will be able to detect it.
You know, now that we're talking about it I'm wondering if someone hasn't already come up with a better bot and has just been silently using it to win money online.
I'm sure the sites have been crawling with bots as long as they've been around, some better than others. As long as it doesn't drive away too many customers I doubt the sites care. They still take a rake on bot games. However better AI could change that as the "dumb money" slowly dries up.
Dumb money has been drying up for years. There have been bots taking millions of dollars out of games for more than a decade. Even bots from 10 years ago were sophisticated enough to win money at mid-stakes poker (up to $2000 buy in 6max no limit games)
proof? I dont' believe this. 2K buy-in has a lot of regs that are pretty good overall in cash games. Plus Pokerstars/FT has a pretty good anti-bot policy. if you get caught bye bye to the $.
There are a bunch of such threads over the years where through statistical analysis, users have identified groups of dozens of bots.
While years ago many of the pros could theoretically beat these bots, it may not have been by enough of a factor to overcome the rake. Of course if the bots are practicing any game selection they can take money out of the economy even if they can't beat pros.
Anti-bot measures is an arms race and the sites aren't always ahead of the game.
There's already loads of bots online, this is just another incremental improvement in a very long line. This isn't some unexpected sudden death-knell for online poker.
The fact that there's a published recipe for a superhuman bot that can be trained for $150 and run on any desktop computer sounds like an existential threat to their business.
The main mitigating factor I can think of is that you'd need to also adversarially train it so it isn't distinguishable from a skilled human. But that doesn't seem like it would be too difficult.