x.com
x.com/I_loves_deep... follow kim!
01.12.2024 08:38 โ ๐ 0 ๐ 0 ๐ฌ 0 ๐ 0
wait it works now
25.11.2024 03:02 โ ๐ 1 ๐ 0 ๐ฌ 0 ๐ 0
omg, mute doesn't work yet , ughh
25.11.2024 02:59 โ ๐ 0 ๐ 0 ๐ฌ 1 ๐ 0
Unhello to u sire
24.11.2024 17:42 โ ๐ 1 ๐ 0 ๐ฌ 0 ๐ 0
24.11.2024 05:27 โ ๐ 2 ๐ 0 ๐ฌ 0 ๐ 0
yea, but a couple of missing features:
- muting
- group chats
24.11.2024 04:48 โ ๐ 2 ๐ 0 ๐ฌ 0 ๐ 0
feels so weird to reply on bsky lol
24.11.2024 04:43 โ ๐ 2 ๐ 0 ๐ฌ 1 ๐ 0
๐
22.11.2024 13:50 โ ๐ 1 ๐ 0 ๐ฌ 0 ๐ 0
Musings on typicality
A summary of my current thoughts on typicality, and its relevance to likelihood-based generative models.
Here's another oldie from 2020: an entire blog post about the weirdness of high-dimensional probability distributions.
With generative modelling having taken off as it has, understanding typicality and its implications is all the more important, but it still isn't talked about much in ML circles!
22.11.2024 00:25 โ ๐ 39 ๐ 6 ๐ฌ 3 ๐ 0
building the future
research at midjourney, deepmind. slinging ai hot takes ๐ฅat artfintel.com
a boy and his gpu vs the world. cofounder/directing research at
@leonardoai_. (now at @canva) trying to feel the magic.
www.ethansmith2000.com
Coming to a representation space near you.
hot takes, linear Algebra, JAX apologist, Raconteur
๊ฎ surfed on by the information superhighway
๊ฎ ๐ @linneaisaac.bsky.social
๊ฎ she/they ๐ณ๏ธโโง๏ธ
๊ฎ blog posts and games @ https://vgel.me
forget this i didnโt know you can share block lists here. call me when you fixed this
software engineering - systems/infrastructure - llms - information retrieval - long term memory - brain/mind - writing - talking - thinking (too much)
ML, Psychology, Art, Materials Informatics, Espresso, Cushbrooch
he/him
teaching computers how to see
synthesis-focused entity.
art ๐ @ http://instagram.com/surea.i
aspiring independent researcher exploring the loss landscape โข 24 โข interested in reasoning, creativity, intelligence
stochasm.blog
Bs CS&EE , AI/ML Engineer in Automotive
i am a bridge between the known and the unknown.
post training, datasets and inference.