Gagan Bansal

@bansalg_

Co-creator of AutoGen, researching agents and people + agents @msftresearch | Previously PhD @uwcse, B Tech @iitdelhi

Seattle, WA

bansal.sh

Replies Reposts Media

Pinned
Gagan Bansal
@bansalg_
May 1
📢 Networks of agents are the future and in order to make them useful at scale, they must remain secure. So, we deployed an internal platform where every agent was always-on, had a known human "principal" (MS employee) that it reported to, and could interact w/ other agents via
00:20
Microsoft Research
@MSFTResearch
Apr 30
Safe agents don’t guarantee a safe ecosystem of interconnected agents. Microsoft Research examines what breaks when AI agents interact and why network-level risks require new approaches. Learn more: microsoft.com/en-us/research…
Gagan Bansal
@bansalg_
Jul 28
This is great! We need more efforts on education + AI! I think there is another thing that chatbot-based learning lacks. E.g., I often visit my favorite video lectures from 10-15 years on various topics like operating systems or algorithms. There is joy in retrospectively
Andrew Ng
@AndrewYNg
Jul 28
Fifteen years ago, @coursera and online courses changed education. It worked better than almost anyone expected, expanding access by opening up where you can learn. But how you learn remains largely the same as it has for centuries: it is still one-size-fits-all, taught the same
Gagan Bansal
@bansalg_
Jul 8
Very cool stuff!
Thomas Dohmke
@ashtom
Jul 8
42 is the answer to everything. This is @EntireHQ’s answer to Git in the era of agents: fast, independent, distributed. Mirror your GitHub repos, let your agents clone and pull from the region(s) of your choice, and…we're open sourcing it. 🤖
Gagan Bansal
@bansalg_
Jul 6
If you are ICML, checkout cool work by @iamwaynechi
Wayne Chi
@iamwaynechi
Jul 6
I'll be presenting GameDevBench at ICML tomorrow! If you're interested in agents and games, come check us out poster session 2 from 2 PM to 3:45 PM!
Gagan Bansal
@bansalg_
May 22
👇👇👇
Karthik Narasimhan
@karthik_r_n
May 21
Deep work and deep thinking will be increasingly valuable in a world where AI agents automate a lot of knowledge work. Spawning tens of agents in parallel and context switching between them feels productive, but it's mostly dopamine.