✨ solving all disease @isomorphiclabs
London
Joined January 2016
- Tweets13.9K
- Following1.3K
- Followers3.7K
- Likes1K
bilal retweeted
HAPPY HALLOWEEN FROM T̴͇̜͇̀͐̈͌H̵̛̲͔͈̘̺̯̹͉̘̆͂͛̉͛͑͝Ę̶͕͓̺͇̳̲͒̐̀͜͠ ̴͈̼̻̺͎̞͎̠̩̈͛̄̏͑͐͘͠ͅB̷̨̞͓̰̦̥̹͉̼̀̅̉̉̈̍͐̈͊͘L̷͙̀̒̎̾́̒A̴̧̡̢̛̟̗͈̘͉͛͋ͅC̷̮̰̗̬͈͚̭̖͍͛̓̈́͊̈̅̑̀̓K̶̡̦̤̱̰̮̰͚̂̂͛̈́̍͂ ̸̳̗̮͆́̔̑Ḽ̶̣͔̃͜͜Ȍ̶̡͚͇̱̹͕̺͉̲̂͆́̓̂̇̋͜͝D̸̛͉̦̠̝̏̒̑̉̈́̅̒̽̚G̵̛̬̏̑̋̽̐̽̕E̷̱̦͔͔̤̼̅͗͋̋
looks like a good chip
Huawei Ascend 950PR Deep dive & µbenchmarks,
DSv4.1 Flash Analysis, DeepSeek support for Ascend,
AICPU, Tilelang Ascend
newsletter.semianalysis.com/…
bilal retweeted
Digital minimalism
vitalik.eth.limo/general/202…
bilal retweeted
introducing tiny.london/world
after tiny.london & isometric.nyc went viral, dozens people did same maps for their cities. i put all of them in one place
from tashkent to goiânia check how similar but different they are!
Introducing tiny.london
A massive isometric pixel map of London, based on amazing NYC demo by @_coenen from 9 months ago
My agent created the dataset, finetuned qwen image LoRA adapter, did a multiday inference run and built an efficient tile viewer!
bilal retweeted
Our second product is called Blindsight and it will, as the name suggests, enable even those who are completely blind or have never seen to see.
It is ready from an engineering standpoint. Just waiting on regulatory approval.
piccadilly arc
Entire London Underground line will be shut over Halloween weekend
mylondon.news/news/transport…
bilal retweeted
one thing @_albertgu won't tell you is how well hnet tokenizes bad apple vs bpe.
suspicious! what else is he hiding???
Our opening animation and blog didn't fully show the interesting dynamics for languages like CJK that have multi-byte characters.
In Chinese most characters take up 3 bytes, and when learning end-to-end from bytes it's not even trivial to get the model to chunk these into characters. Early in training this H-Net incorrectly sub-divides characters, but it eventually figures it out. Actually this was a prominent issue in the original H-Net - and even BPE doesn't get it right on rare characters. The blog has some examples!
