DrawTR

Interesting how malware is essentially allowed on GitHub, seeing as the top result here has ~500 stars and has features advertised to steal much more than Discord accounts. I have a recollection of downloading a program from GitHub (which has 1.4k stars right now) whose installer had an opt-out malware bundled -- I reported the repo three times, and they didn't take any action. Chocolatey team did step in and remove it on their platform, but I wonder why GitHub didn't take any action

Makes me think of this one: https://youtu.be/WqnXp6Saa8Y

Ah, gotcha! I didn't know that the few-shot thing was applicable to the newer models, that's very interesting

For what it's worth, not all of these examples are consistent: https://chat.openai.com/share/29e1c2bd-ef7b-4475-b5a9-9287d1...

I know exactly what you mean by this! I can always tell if it was taken on an iPhone -- not that it looks bad, or anything, but there's always a few little cues that make it obvious. As you mentioned, I think the motion is a large part of it.

> i just... want to see a stupid letter threatening me which i can laugh off.

Are you familiar with the UK's TV licensing notices? Those are really funny

I agree -- in some regards, it's like he's separating conscious thought? Not sure if that makes sense. Like, if it were that easy to just will yourself out of it I'm sure everyone would have quit horrible addictions. The entire point is that the dopamine drives your behavior to a point where it's integrated in everything you do. Sure, with enough effort you can build routines that replace that with more intrinsically beneficial stuff, but I don't think it's just a matter of "simply getting rid of bad things"

A little jarring how clicking on any of the hyperlinked 'channels' on the left navigation bar will send you 20 years into the future in terms of web design. Quite a stark contrast.

Yep, Numworks is really great. Love the updates

This is definitely cool, but it seems to 'forget' about the prompt after a few back and forths. Is this because the prompt is placed before the conversation in its memory? It doesn't seem to be continuously reminded of it.

I think this is true when examining the inherent length of a body of text -- you'll look at some generated jargon that's paragraphs long and instinctually be impressed -- but the most horrifying part of this technology (at least for me) is that with only a tiny bit of effort, you can get an output that sounds well. With the right prompts, you can get a result that isn't just impressive upon first glance, but one that holds up to a decent amount of scrutiny. The latter is what scares me the most.