Dhir

248 posts

Dhir banner
Dhir

Dhir

@dhirrr_k

building @veclabss typing my way through the matrix @oregonstate

Katılım Ekim 2024
528 Takip Edilen68 Takipçiler
Sabitlenmiş Tweet
Dhir
Dhir@dhirrr_k·
The bridges I burn, will light my way!
English
0
0
0
428
Dhir
Dhir@dhirrr_k·
here today
Dhir tweet media
English
0
0
1
32
Dhir retweetledi
Can Vardar
Can Vardar@icanvardar·
if you don’t hold your macbook like this you’re not agentmaxxing enough
Can Vardar tweet media
English
137
56
1K
299.3K
Dhir retweetledi
veclabs
veclabs@veclabss·
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
English
0
1
2
44
Dhir
Dhir@dhirrr_k·
this weekend i will write an api that handles over 100M requests per month
English
1
0
3
21
Arlan
Arlan@arlanr·
welcome to @nozomioai hq the first startup frat house
English
46
10
425
45.5K
Dhir
Dhir@dhirrr_k·
Threads are for working in parallel, async is for waiting in parallel.
English
0
0
0
82
Kat McGuire
Kat McGuire@katmcguir3·
guys i designed these !!
Kat McGuire tweet media
English
132
30
1.5K
48.3K
Icedcortado
Icedcortado@agrawalnishii·
Back to my nerdy interests (started reading againnnn)
English
2
0
7
247
Dhir
Dhir@dhirrr_k·
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
English
1
0
0
45
Dhir
Dhir@dhirrr_k·
project idea with veclabs : a App where users get personalized, hallucination-resistant recommendations powered by your vector tech + Solana data.
English
0
0
1
37
Dhir
Dhir@dhirrr_k·
excited for this. hfo. @veclabss
Dhir tweet media
English
0
0
2
97
Dhir
Dhir@dhirrr_k·
writing a new webservice in rust using actix-web, start of system design principles
English
0
0
1
30
Dhir
Dhir@dhirrr_k·
hold on, whattttttttttty
Dhir tweet media
English
1
0
1
108
Dhir retweetledi
veclabs
veclabs@veclabss·
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.
English
0
1
2
47