You are absolutely correct. However, I fear you're running up against the basic human instinct of "my enemy's enemy is my friend.".

I also wonder how many actually support them, and how much is just a result of opinions boosted by bots?

I love the idea of this. I want it to succeed.

But most of the questions I got... They weren't very good and not just because I got them wrong - I got a bunch of them right that I shouldn't have.

For example, the one about homelessness, where it ends with a guy saying our politicians would rather use the money for genocide.

I downloaded the statement for that reason, got told my vote was correct and then it came up with it was correct only because of the first part of it.

I think you're trying to import statements automatically and I fear that won't work. I also fear that you're gonna get, just crap, to be honest. And your social network doesn't deserve that.

I think your best bet is to look at the kind of questions asked on the LSAT, and just do a bunch of essentially IQ and general-knowledge questions. Take the input from Twitter as inspiration, use it as a template and it might work.

One thing you might consider is wanting to filter out people who can't see past their own political agenda.

You can do that by making enough questions so that you're sure to catch people, no matter what they believe on all the hot issues of the day. This probably isn't as hard as it sounds, there's only going to be seven or eight hot issues.

You pick three of them and you should be pretty certain that you will cover the entire spectrum. So for example, you could make sure to include, pro LGBT, pro abortion and pro guns. You would catch most people on that and then you should exclude them if they cannot see past their blindness.

I hope you make this work, the world needs it.

Windows is still the king for gaming. Word is better than Google Docs for anything but the absolute basics[0].

But as a professional, it has no further use.

[0]: Please tell me how I add a new paragraph style in Docs?

I don't think you can add a new paragraph style in Docs. However, 99% of people I've known to use a word processor have never used that feature. Heck, I'd bet the majority of users don't even understand what a 'style' is; people just change the font size directly.

You are right on both counts and that is a bad thing.

World has had ctrl+b for bold forever, so people can start to use it and then upgrade to styles when they run into the limitations. Alternatively someone knowledgable could set Word to only allow a selection of styles.

Open and Libreoffice has had style support since forever. Its only docs that kneecaps its users learning journey like that.

You can get that anyway, and you should because 2 is 1 and 1 is none.

Not your (drone)air-defense, not your data center I guess.

Deduplicating/validating/processing incoming bug reports?

I won’t, but it does have a couple features Codex lags, including remote SSH (huge, because the easiest way to sandbox your agent is to put it into a VM), and the ability to kicking things of on your mobile and finishing up on your desktop (again, really nice if you get a good idea out on a walk, or while talking to a colleague.

These are features I am sure Codex will soon have, of course.

Then there is the advantage of multiple models: run a top level agent with an expensive model, that then kicks of other models that are less expensive - you can do this in Claude Code already (I believe), but obviously here you are limited to something like Haiku.

You are right.

But you can use AI to improve your codebase too. Plus models are only going to get smarter from here (or stay the same).

> Plus models are only going to get smarter from here (or stay the same).

Training models on AI generated content leads to model collapse so they hardly become smarter if more and more code is from AI

That is a possibility, but even then the models won't become more stupid (you can just keep using the current ones).

Yeah, thats part of why I hate "login with SERVICE". The big benefit would be not spamming me, but they always insist on getting my email.

There was a time were you would have to select "sign me up for your newsletter" then you had to uncheck it. Then you had to check to not get an email and now you don't even get that choice.

And lately? You have to go dig through your email because you can't set a password (looking at you Claude), so you can't filter email.

Didn't they have a crash dummy in it the last time? The data from buster should be able to tell us if the parachute worked or not.