Dhir

The bridges I burn, will light my way!

here today

if you don’t hold your macbook like this you’re not agentmaxxing enough

AI agents are making decisions that affect real people. Their memory? A plain JSON blob on someone else's server. Anyone with database access can change it. The agent never knows. You can never prove it. We're fixing this

this weekend i will write an api that handles over 100M requests per month

@arlanr @nozomioai loved the beat and the house

welcome to @nozomioai hq the first startup frat house

best definition of async IO i have ever come across

Threads are for working in parallel, async is for waiting in parallel.

@katmcguir3 perfect summer vibes

guys i designed these !!

my thoughts on production grade use of k-means algo dhirk.xyz/writing/kmeans…

@agrawalnishii she might be just preparing for a exam

Back to my nerdy interests (started reading againnnn)

soon each skill will just become a vector embedding in a database which will be pulled as per requirement through a RAG and we will have perfect skills for each one of our tasks

project idea with veclabs : a App where users get personalized, hallucination-resistant recommendations powered by your vector tech + Solana data.

excited for this. hfo. @veclabss

Check out the download stats for solvec by @veclabss on Pepy! pepy.tech/projects/solvec

writing a new webservice in rust using actix-web, start of system design principles

@Risheessh cluely lol

@dhirrr_k Lmao, Which company?

hold on, whattttttttttty

most vector DBs treat memory like a black box. you write, you read, and you hope the agent remembered the right thing. we record a Merkle proof on Solana after every write. so you can prove exactly what the agent knew - and when.