Angehefteter Tweet
Adesh Gupta
321 posts

Adesh Gupta
@a4dex
20, developer @sdslabs , maths ug @iitroorkee, ml & systems
Beigetreten Temmuz 2024
459 Folgt160 Follower


New blog!
I’ve been working on this for the past couple of days & explored a large part of the landscape around community detection, modularity, Louvain, Leiden, CPM & how all of this connects back to GraphRAG!
Covers:
• modularity + random graph baselines
• Louvain & its disconnected-community bug
• how Leiden Algo fixes it through refinement
• CPM, resolution limits & hierarchical Leiden + CPM in graphRAG
Also made a bunch of visual walkthroughs + modularity examples to make the intuition behind Leiden easier to see, not just memorise.If you're into GraphRAG, network science, or graph algorithms, you might enjoy this one!
Link below, please check it out and RT/QT appreciated :)



English

@atulit_gaur people at my uni do use matiks, half of college might be exaggeration but it is not completely made up as well
English

who tf uses matiks, bro just saying random shit to get fulltime
Sudhanshu | Matiks@cortisoul_
day made <<<3
English
Adesh Gupta retweetet

This is the the quote I've been citing a lot recently.
kache@yacineMTB
you can outsource your thinking but you cannot outsource your understanding
English
Adesh Gupta retweetet

Claude code source code has been leaked via a map file in their npm registry!
Code: …a8527898604c1bbb12468b1581d95e.r2.dev/src.zip

English

I trained models across MacBooks using Apple's AirDrop protocol.
grove is a distributed training library for Apple Silicon. Devices discover each other over AWDL, a direct radio link. If there's a shared WiFi network it upgrades to that for speed, otherwise everything goes over the direct link. No router, no cloud, no setup.
grove start








