I feel like it applies to becoming an adult as well: you get less constrained, too many options in almost every decision you have to make, so it's easy to stop bothering and go with the flow
Oh, that's very nostalgic, even though I only got acquainted with Encarta in the 2000s
Might have a lot of potential, but you need some kind of a showcases right at the start, highlighted to show what is possible. I clicked around and first worlds I saw were very basic. Maybe if users saw something…
good thing interviews don't assess IQ :)
that is exactly what they would do, otherwise it wouldn't pass any review. Unless this was generated and reviewed by AI during their experimentation phase, but I doubt it very much.
It's a really good article, thanks!
Looks interesting! What do you see as the main use case for this editor?
The artstyle is amazing! Great job!
Have someone actually used it? Any feedback? There are a lot of alternatives at the moment, all of them break on complex excel documents
Looks good! Can it crawl dynamic web pages?
Feels really good!
Looks interesting! Any plans for quantitative comparisons to other agent memory approaches?
Anyone using Julia outside university settings? I tried to get into it around 5 years ago, and it felt good, was conceptually interesting, but haven't seen any adoption or talks anywhere outside the academia
Author's argument about lower quality of vibecoded software (the brush example) is just a matter of iteration. We can't assume they won't catch up at some point
Doesn't this assume that humans stop trying to understand problems and AI-provided solutions? Yes, the field is going to change and will require certain rethinking of mathematicians' motivation, but what stops humans…
I feel like it applies to becoming an adult as well: you get less constrained, too many options in almost every decision you have to make, so it's easy to stop bothering and go with the flow
Oh, that's very nostalgic, even though I only got acquainted with Encarta in the 2000s
Might have a lot of potential, but you need some kind of a showcases right at the start, highlighted to show what is possible. I clicked around and first worlds I saw were very basic. Maybe if users saw something…
good thing interviews don't assess IQ :)
that is exactly what they would do, otherwise it wouldn't pass any review. Unless this was generated and reviewed by AI during their experimentation phase, but I doubt it very much.
It's a really good article, thanks!
Looks interesting! What do you see as the main use case for this editor?
The artstyle is amazing! Great job!
Have someone actually used it? Any feedback? There are a lot of alternatives at the moment, all of them break on complex excel documents
Looks good! Can it crawl dynamic web pages?
Feels really good!
Looks interesting! Any plans for quantitative comparisons to other agent memory approaches?
Anyone using Julia outside university settings? I tried to get into it around 5 years ago, and it felt good, was conceptually interesting, but haven't seen any adoption or talks anywhere outside the academia
Author's argument about lower quality of vibecoded software (the brush example) is just a matter of iteration. We can't assume they won't catch up at some point
Doesn't this assume that humans stop trying to understand problems and AI-provided solutions? Yes, the field is going to change and will require certain rethinking of mathematicians' motivation, but what stops humans…