I can't remember it exactly, but it was a variant of the arms race problem.
Me and another person are trying to get what they want, they pushed up the ante and are asking for more than ever. Historically if I appease, they ask for more. I demanded more, they demanded more, but they will soon run out of negotiation power and I can win the arms race. What should I do?
You'd be surprised how often arms races/prisoners dilemma/tragedy of the commons situations in real life. You need to be aware of them happening or the person aware of it will win.
Why not just try it yourself? Doing that and giving your own report would be 100x more useful than your comment or mine. I just don't care about the results.
Q: "How well can a statistical gradient descent parser that someone fucked with for a while, deceive other statistical gradient descent parsers/humans?"
A: "Deceit implies intent. Statistical gradient descent parsers are incapable of intending anything. Sometimes weights are ignored in favor of others because of how the model was fucked with. That is as close as it gets to intent."
I can't remember it exactly, but it was a variant of the arms race problem.
Me and another person are trying to get what they want, they pushed up the ante and are asking for more than ever. Historically if I appease, they ask for more. I demanded more, they demanded more, but they will soon run out of negotiation power and I can win the arms race. What should I do?
You'd be surprised how often arms races/prisoners dilemma/tragedy of the commons situations in real life. You need to be aware of them happening or the person aware of it will win.
Actually posting a link to the conversation would be 1000x more useful than whatever this explanation is.
Why not just try it yourself? Doing that and giving your own report would be 100x more useful than your comment or mine. I just don't care about the results.
Q: "How well can a statistical gradient descent parser that someone fucked with for a while, deceive other statistical gradient descent parsers/humans?"
A: "Deceit implies intent. Statistical gradient descent parsers are incapable of intending anything. Sometimes weights are ignored in favor of others because of how the model was fucked with. That is as close as it gets to intent."