Is it naive to imagine AI-based anti-propaganda would also be significant? E.g. “we generated AI propaganda for 1000 true and 1000 false claims and trained a neural net to distinguish between the two, and this text looks much more like propaganda for a false claim”.
What does GDP growth look like in this world?
Another reason the hype fades is that a stereotype develops of the naive basement-dweller whose only friend is a chatbot and who thinks it’s conscious and intelligent.
Things like this go somewhat against my prior for how long it takes for culture to change. I can imagine it becoming an important effect over 10 years more easily than over 1 year. Splitting the internet into different territories also sounds to me like a longer term thing.
Propaganda usually isn’t false, at least not false in a nonpartisan-verifiable way. It’s more about what facts you choose to emphasize and how you present them. So yeah, each ideology/faction will be training “anti-propaganda AIs” that will filter out the propaganda and the “propaganda” produced by other ideologies/factions.
In my vignette so far, nothing interesting has happened to GDP growth yet.
I think stereotypes can develop quickly. I’m not saying it’s super widespread and culturally significant, just that it blunts the hype a bit. But you might be right, maybe these things take more time.
Re splitting the internet into different territories: Currently, the internet is split into two territories: One controlled by the CCP and one (loosely) controlled by western tech companies, or by no one, depending on who you ask. Within the second one, there is already a sort of “alternate universe” of right-wing news media, social networks, etc. beginning to develop. I think what I’m proposing is very much a continuation of trends already happening. You are right that maybe five years is not enough time for e.g. the “christian coalition” bubble/stack to be built. But it’s enough time for it to get started, at least.
But yeah, I think it’s probably too bold to predict a complete right-wing stack by 2024 or so. Probably most of the Western Right will still be using facebook etc. I should think more about this.
Misinformation is false, but not created or shared with the intention of causing harm.
Disinformation is deliberately created to mislead, harm, or manipulate a person, social group, organization, or country.
Malinformation is based on fact, but used out of context to mislead, harm, or manipulate.
(got this example from Zvi’s covid post today)
Also, the recent events with GoFundMe and GiveSendGo is an instance of the trend I predicted with separate tech stacks being developed. (GoFundMe froze and/or confiscated funds donated to the canadian trucker’s protest, so people switched to using GiveSendGo, which is apparently built and run by Christians)
This trend is definitely continuing today with things like Truth Social and already people are talking about how ChatGPT is “woke AI” and there “needs to be a right-wing ChatGPT!”
As a sort-of example, sleuths against scientific fraud are already using tools to detect fake papers generated by GPT. already using GPT-detecting AI tools to detect AI-generated or -translated papers, even if the generating tool wasn’t GPT.
Is it naive to imagine AI-based anti-propaganda would also be significant? E.g. “we generated AI propaganda for 1000 true and 1000 false claims and trained a neural net to distinguish between the two, and this text looks much more like propaganda for a false claim”.
What does GDP growth look like in this world?
Things like this go somewhat against my prior for how long it takes for culture to change. I can imagine it becoming an important effect over 10 years more easily than over 1 year. Splitting the internet into different territories also sounds to me like a longer term thing.
Thanks for the critique!
Propaganda usually isn’t false, at least not false in a nonpartisan-verifiable way. It’s more about what facts you choose to emphasize and how you present them. So yeah, each ideology/faction will be training “anti-propaganda AIs” that will filter out the propaganda and the “propaganda” produced by other ideologies/factions.
In my vignette so far, nothing interesting has happened to GDP growth yet.
I think stereotypes can develop quickly. I’m not saying it’s super widespread and culturally significant, just that it blunts the hype a bit. But you might be right, maybe these things take more time.
Re splitting the internet into different territories: Currently, the internet is split into two territories: One controlled by the CCP and one (loosely) controlled by western tech companies, or by no one, depending on who you ask. Within the second one, there is already a sort of “alternate universe” of right-wing news media, social networks, etc. beginning to develop. I think what I’m proposing is very much a continuation of trends already happening. You are right that maybe five years is not enough time for e.g. the “christian coalition” bubble/stack to be built. But it’s enough time for it to get started, at least.
But yeah, I think it’s probably too bold to predict a complete right-wing stack by 2024 or so. Probably most of the Western Right will still be using facebook etc. I should think more about this.
Minor update: See e.g. this US government website definitions:
(got this example from Zvi’s covid post today)
Also, the recent events with GoFundMe and GiveSendGo is an instance of the trend I predicted with separate tech stacks being developed. (GoFundMe froze and/or confiscated funds donated to the canadian trucker’s protest, so people switched to using GiveSendGo, which is apparently built and run by Christians)
This trend is definitely continuing today with things like Truth Social and already people are talking about how ChatGPT is “woke AI” and there “needs to be a right-wing ChatGPT!”
As a sort-of example, sleuths against scientific fraud are
already using toolsto detect fake papers generated by GPT.already using GPT-detecting AI tools to detect AI-generated or -translated papers, even if the generating tool wasn’t GPT.(They very obviously weren’t generated by any GPT.)