PwnallthethingsSo these AI chats are pretty cool.
One thing that's gonna cause some problems tho is that they sound really really convincing while sometimes being extremely extremely wrong
A zillion ways this revolution is going to be great.
One way that's going to suck tho is in places where human interactions are a *useful* friction / proof-of-work. When it's not, those systems will get really overloaded
Few examples:
1. Online troll bots & fake personalities
It's going to get a *lot* harder to distinguish bots from people and much easier to create entirely fictitious credible online personalities to troll/harass/do crime
2. Persuasive letters by e.g. constituents to regulators.
Volume of (~sensible, unique) letters was a valid indication of sentiment. Soon won't be.
3. Ransomware victim communications & negotiations
Used to be one of the few costly areas in scale. Not for long
4. Places where writing is assessed for cash or credit
Going to be much easier for e.g. students to fake/plagiarize essays or other homework for-credit
Combatting that will probably eventually force schools and universities towards towards more heavy focus on proctored work (exams, supervised essay writing) (ugh)
Going to be much easier to create fake-news clickbait farms too for ~ the same reason
What worries me a bit here is that in trying to preserve some of these systems, there'll probably be a lot of folks pushing tech designed to *prove* humanness to combat it. And politicos and regulators are less likely to hear that and think "guess they should use creative CAPTCHAs" and more likely to think "oh, people should upload passports", and that's gonna be a whole new shitshow
Also excited for the new era of "who is liable when the AI tells you to cook the frozen Turkey in the deep-fryer" / "can you maliciously interact as user A with the AI, such that the AI interacts with user B and advises them to do X" wars
Anyway. New world. New cool stuff. New unforeseen challenges. Gonna be weird.
Gonna add one point to this, since it's easy to focus on the downsides. There's some great stuff too.
One way AI is going to be *fantastic* is for accessibility. Imagine, for example, tools that summarize pictures as the default text for alt-text fields, making it faster and easier to make apps and sites accessible by default.
Another is making cool learning technologies, especially for beginners. Turning text into example code and vice-versa is a great learning tool!
IsWackyI asked of openai playground bot the following request:
Ralph Nader said, "Republicans stab you in the front." The implication is that Democrats stab you, the voter, in the back. Please show examples of republicans stabbing you in the front.
It puzzled out the Q and gave a good answer!
(Cont'd)
Examples of Republicans stabbing you in the front include:
1. Attempting to pass legislation that would cut taxes for the wealthy and big corporations while cutting government assistance programs for the middle and lower classes.
2. Attempting to pass legislation that would roll back regulations on corporations, while leaving individuals and small businesses unprotected.
(Cont'd)
(Cont'd)
3. Refusing to pass meaningful gun control legislation, instead choosing to make it easier for dangerous individuals to obtain firearms.
4. Pushing for deregulation of the banking and financial industries, leading to the 2008 financial crisis.
5. Supporting policies that would weaken labor unions and make it harder for workers to get fair wages and benefits.