Content
@
0 reply
0 recast
0 reaction
July
@july
a crazy idea: the fact that most (if not close to all) models, papers, are all going to be obsolete in a few years even though they feel so new today
7 replies
2 recasts
24 reactions
July
@july
I remember learning / reading computer vision papers back in the day, and then CNN came along and obliterated all these tips and tricks with CV that was done in the past
0 reply
0 recast
4 reactions
Claus Wilke
@clauswilke
I mean, if you've been in the space for a while (20+ years for me) you've seen it all over and over. I remember in the late 90s, wavelets where the thing for image processing. And now most people probably have never even heard that term.
1 reply
0 recast
0 reaction
vincent
@pixel
I actually don't know what Q3 2024 will look like. French bros probably are gonna summon AGI and poast magnet links without explanation, obsoleting all previous models
2 replies
0 recast
3 reactions
π _π£π _π
@m-j-r
how do you see natural data? same obsolescence in a few years?
1 reply
0 recast
0 reaction
tywen
@tywen.eth
This is why I donβt read any of them, donβt want to optimize local maxima. Also I canβt read
1 reply
0 recast
0 reaction
Kyle Mathews
@kam
well or they won't. Progress isn't guaranteed without new conceptual breakthroughs. I don't really see any improvements coming until models get embodied (i.e. exist as robots so can learn from reality)
1 reply
0 recast
1 reaction
Sam (crazy candle person) β¦
@samantha
Wasnβt there something that said that 97% of academic papers never get read
0 reply
0 recast
0 reaction
