darepublic

When I'm looking for info that requires careful parsing of a source site, then LLM is faster. If it's something like looking up the hours of a business googling that local business is better imo. Result is fast you get to see the business picture etc

Yes that's right

I enjoy a monopoly variant where every property landed on causes an auction regardless of who landed on it.

Whenever anthropic / AI guru talks about loving humanity and how they're scared about the future I can't help but think of the childhold meme where one child bullies the other by striking the other with their own arms. Stop hitting yourself, stop hitting yourself, stop hitting yourself!

The fast feedback loop is.. sometimes not feeling so fast. Codex regularly takes a couple of minutes on tasks I give it.. sometimes considerably more.this takes me out if the zone. Still faster than what I could do still enables working in an exhausted state where I would otherwise be unable to produce code. But there are problems in the UX to be fixed I feel

It could be logically valid but irrelevant? Allowing for the atrophying of all our skills is dangerous? While simultaneously building ever more complicated edifices that control our lives? Not a doomer but you really just want to shrug and say it ain't no thing?

> I tried asking Claude fron the android app if it could sign me up for the waitlist and it said that it couldn't.

I assume this is because it would require account editing tools available to Claude. And it opens the possibility perhaps of user tricking the llm into doing something inappropriate with the account. Seems like if properly designed that should not be possible however ..

Tbf jev should also be required to use vision on the UI to decide where to click to proceed with the quiz

Nice site. I assume vibecoded but it was tasteful and performant on mobile. Thanks for open sourcing it

I've been practicing leet code recently because.. reasons. But I actually have been enjoying it a lot more than in the past because I get that now scarce hands on experience

Silly math puzzle is reductionist. If it was considered a worthwhile life long pursuit how is it dumb to be upset that the rug was pulled on it

Gate the refund with llms I guess

I did also notice that in the abyss mode I gave some answers that "should" be popular but weren't and I'm wondering if it's simply because of small sample size.

I figured any hire at openai would know that at least