What can we learn from microservices when applied to AI agents?
Introducing MicroAgents!
Check out this Semantic Kernel blogpost that my colleague Chris and I wrote exploring patterns for getting agents to use reliably use a large number of tools.
Charles Packer is a current 5th-year PhD student at UC Berkeley and author of MemGPT an open-source project teaching large language models to manage their own memory for unbounded context! Charles is also a core member of the Berkeley Artificial Intelligence Research (BAIR) Lab and Real-Time Intelligent Secure Explainable Systems (RISE) Lab where his work has spanned reinforcement learning and autonomous driving.
Aayush Mudgal is a Senior Machine Learning Engineer at Pinterest, currently leading the efforts around Privacy Aware Conversion Modelling. Ayush has expertise in large-scale recommendation systems, personalization, and ads marketplaces, and in the past has conducted research on intelligent tutoring systems, developing data-driven feedback to aid students in learning computer programming.
A great episode with Adam Steinle, founder and CEO of hona.ai, a customizable, HIPAA-Compliant AI that searches and converts 1000s of health records into one simple patient overview!
Adam started out as a biomedical engineer, and after stints at Goldman Sachs and Meta, he returned to his roots to help medical systems communicate so that providers can learn about their patients more effectively.
Definitely give the episode a listen to hear Adam's story!
And if you want to share your story on the Humans of AI Podcast or want to partner in any way, please reach out!
An amazing conversation with Shishir Patil the creator of the Gorilla LLM, a large language model specifically trained to use APIs!
Shishir is currently a 5th year PhD student at the University of California, Berkeley whose work broadly covers ML-Systems, LLMs, Edge-ML, and Sky computing.
Definitely give the episode a listen to hear Shishir's story.
And to read more about #GorillaLLM, check out the project page!
Chun Jiang is the founder of Monterey AI, an AI startup looking to be your copilot for product insights. Coming from a background of urban design and architecture, Chun has built design-centric AI products across industries like self-driving cars and geospatial data platforms.
This is a big week for the Semantic Kernel as we're making a big push for plugins! Plugins are at the heart of unlocking more potential with your Semantic Kernel applications.
They allow you to connect to external data sources and give large language models tools to be able to interact with native functions and API services.
To show our commitment to plugins, we're kicking off a weeklong hackathon open globally for people to submit their best plugins.
We'll have great prizes with more to be announced!
So, make sure to sign up for the event on Partiful and join our Discord channel to share and get help on the plugins you want to build.
An amazing podcast session with Evan Mays, founder of Rootbeer Computer!
In this episode, we cover Evan's inspiration to get into AI from the original Iron Man films and Halo video games to his journey to winning the Scale AI hackathon with an innovative idea that GPT is all you need for backend.
We also touch on an in-depth conversation on the merits and pitfalls of current approaches to building with LLMs from vector databases and agents.
And if you want a refresher on the details of GraphRAG, check out our walkthrough video: https://youtu.be/r09tJfON6kE?si=yP6nvp-wOoOL4fB5