saurabhtwq's profile picture. ml research. inference. agents

saurabh

@saurabhtwq

ml research. inference. agents

lion only care about nanochat for next few days.

saurabhtwq's tweet image. lion only care about nanochat for next few days.

man i should get phd in ml compilers.


writing is my new addiction, and it will stay with me until my hand stops working. it has shown great improvement in my ability think clearly. I do not feel lost in noise.


i use zotero to read papers on mac and ipad, then use the obsidian scholar extension to take notes. It’s very convenient.


> it feels great to win. > i need to win more.


memory in agents(llm) become very useful when dealing with very specific tasks like coding but if you using llm for general purpose stuff then i don't think it matter that much to me. like i don't want llm to give me answer in same specific way(acc my prev memory) i want it be…


wake up babe! it’s time for vibe engineering.

Vibe coding is irresponsibly building software through dice rolls, not caring what code is produced What about when engineers at the top of their game use AI tools responsibly to accelerate their work? I propose "vibe engineering"!



the more i read about “the macroscopic quantum tunneling experiment” more it get interesting.

BREAKING NEWS The Royal Swedish Academy of Sciences has decided to award the 2025 #NobelPrize in Physics to John Clarke, Michel H. Devoret and John M. Martinis “for the discovery of macroscopic quantum mechanical tunnelling and energy quantisation in an electric circuit.”

NobelPrize's tweet image. BREAKING NEWS
The Royal Swedish Academy of Sciences has decided to award the 2025 #NobelPrize in Physics to John Clarke, Michel H. Devoret and John M. Martinis “for the discovery of macroscopic quantum mechanical tunnelling and energy quantisation in an electric circuit.”


first step to become a good content creator is read a lot and read about everything and write it down in your own words.


andrej karapathy twitter post randomly appearing in blogs like a dictionary. oh this is the definition of the term lol


time to get locked for winter arc.

saurabhtwq's tweet image. time to get locked for winter arc.

saurabh أعاد

from what i can see, DSA has no measurable degradation in performance compared to MLA (its usually better) even on very long context. The whale cooked once again


i want that “dad you can retire now” money.


this has to be agi.

Introducing Claude Sonnet 4.5—the best coding model in the world. It's the strongest model for building complex agents. It's the best model at using computers. And it shows substantial gains on tests of reasoning and math.

claudeai's tweet image. Introducing Claude Sonnet 4.5—the best coding model in the world.

It's the strongest model for building complex agents. It's the best model at using computers. And it shows substantial gains on tests of reasoning and math.


Loading...

Something went wrong.


Something went wrong.