Hacker News Reader

Comment by concinds | Hacker News Reader

For decades people tried to correlate gait to personality and behavior. Then, DNA, with IQ and all sorts of things. Now they're trying it with barely-noticeable facial features, again with personality traits. But the research is still crap bordering on woo, and barely predictive at all.

It's at least plausible that we are sufficiently complex that, even with tons of NSA and corporate data and extremely sophisticated models, you still wouldn't be able to predict someone's behavior with much accuracy.

View on HN

There doesn't need to be a correlation between some data structure and its effects for people to implement some sort of feature. There only need to be enough stupid people in powerful positions that believe in some sort of correlational trend AND also for the data gathering task to be trivially cheap enough for them to implement said things. And there's no shortage of that going around. That's why these technologies are dangerous. Stupid people with powerful and cheap tools to weald them. Kind of like what we saw with the first wave of Facebook algorithms being used against its users to maximize the attention at the detriment of everything else.

Yes, exactly. “Well, the AI said to go arrest that guy, and I’ve been hearing for years that AI is super smart, so that must be the right thing to do.”

Any tech for predicting people's behavior will likely be sooner mature in predicting the behavior of crowds of people than one individual. (They seem like related problems where the latter is much harder.) The easier one is where the $$$ incentives lie, e.g. if you correctly predict how masses of people are going to buy stocks, you're rich.

It’s not predicting more about controlling and shutting down who doesn’t agree with you. We already know majority of governments spying and sabotaging activists. Now imagine you can query for “extreme environmentalists who lives in X” and whatever the further filtering is needed.

Reply on news.ycombinator.com