Aneesh Sathe ☀️ pfp

Aneesh Sathe ☀️

@ars

254 Following
137 Followers


Aneesh Sathe ☀️ pfp
Aneesh Sathe ☀️
@ars
Do protocols dream of Directed Acyclic Graphs?
0 reply
0 recast
3 reactions

Aneesh Sathe ☀️ pfp
Aneesh Sathe ☀️
@ars
0 reply
0 recast
0 reaction

Aneesh Sathe ☀️ pfp
Aneesh Sathe ☀️
@ars
0 reply
0 recast
0 reaction

Aneesh Sathe ☀️ pfp
Aneesh Sathe ☀️
@ars
Delving (hehe) into AI agents more today. These two wrote code for logistic regression (on a toy problem) and then wrote a blog post about it. https://ai.aneeshsathe.com/Two%20Agent%20Task%20Decomposition/Task%20Decomposition%20Using%20Two%20Agents.html
0 reply
0 recast
0 reaction

Aneesh Sathe ☀️ pfp
Aneesh Sathe ☀️
@ars
Does everyone have a screenshots folder??
0 reply
0 recast
0 reaction

Aneesh Sathe ☀️ pfp
Aneesh Sathe ☀️
@ars
Does everyone have a screenshots directory??
0 reply
0 recast
0 reaction

Aneesh Sathe ☀️ pfp
Aneesh Sathe ☀️
@ars
High information density makes time feel shorter https://www.nature.com/articles/d41586-024-01169-3
0 reply
0 recast
0 reaction

Aneesh Sathe ☀️ pfp
Aneesh Sathe ☀️
@ars
Looks like I’ll be playing with agents enough to warrant making a little online space https://ai.aneeshsathe.com/intro.html
0 reply
0 recast
2 reactions

Aneesh Sathe ☀️ pfp
Aneesh Sathe ☀️
@ars
LxM agents are expressive skeuomorphisms
1 reply
0 recast
1 reaction

Aneesh Sathe ☀️ pfp
Aneesh Sathe ☀️
@ars
Two days of setting up environments and joining all the pipes… But, got the AI agents working! Automated logistic regression through group chat as a toy problem. Llama3 just happened to release at a convenient time. Sleeping happy. Fun stuff starts Monday. Going to avocado 🥑 festival tomorrow lol.
0 reply
0 recast
0 reaction

Aneesh Sathe ☀️ pfp
Aneesh Sathe ☀️
@ars
0 reply
0 recast
0 reaction

Aneesh Sathe ☀️ pfp
Aneesh Sathe ☀️
@ars
1 reply
0 recast
0 reaction

Aneesh Sathe ☀️ pfp
Aneesh Sathe ☀️
@ars
In the context of AI agents, thinking about how people’s resumes are essentially a prompt for who they are. In a reverse UNO move thinking of implementing RAG (with resumes) AI agents who can call on experts automatically to seek advice on difficult topics. Combine with token payments & it could be new Quora
1 reply
1 recast
1 reaction

Aneesh Sathe ☀️ pfp
Aneesh Sathe ☀️
@ars
I don’t play but the /sop folks are cool
0 reply
0 recast
1 reaction

Aneesh Sathe ☀️ pfp
Aneesh Sathe ☀️
@ars
😍 https://www.abc.net.au/news/2024-04-18/bonorong-wildlife-sanctuary-george-cockatoo-raphael-lorikeet/103732066
1 reply
0 recast
0 reaction

Aneesh Sathe ☀️ pfp
Aneesh Sathe ☀️
@ars
I keep trying to build agents but then I find agents who can build agents but then I find agents who can build agents who can build agents but then I find…
1 reply
0 recast
1 reaction

Aneesh Sathe ☀️ pfp
Aneesh Sathe ☀️
@ars
Generation gap is actually protocol jealousy.
0 reply
0 recast
2 reactions

Aneesh Sathe ☀️ pfp
Aneesh Sathe ☀️
@ars
Fast becoming my favorite thing to check on everyday: https://bsky.app/profile/willquinnart.bsky.social/post/3kqhfj6tpok2i
0 reply
0 recast
0 reaction

Aneesh Sathe ☀️ pfp
Aneesh Sathe ☀️
@ars
Docker containers with LLMs should be called magic lamps 🪔
0 reply
0 recast
0 reaction

Aneesh Sathe ☀️ pfp
Aneesh Sathe ☀️
@ars
Hair changes signal trauma for sure… the best that I’ve managed is shaved head and then beard to “compensate” that was a spicy year
0 reply
0 recast
0 reaction