Skip to main content

ai.engineer summit nyc

· One min read
Nick Lange
Nick Lange
Someone at 5L Labs

To be updated​

The AI Engineering Summit was a definite eye-opener to the speed with which IT is transforming mundane "busy" work, and the startup cost for exploring new ideas.

Take aways for a private agent:​

  • Do Agents need to be local to be private?
  • Locally on a macbookpro
  • Hosted in a secure enclave on AWS / Azure / GCP
  • Or can some sort of formal proof be done to leave a multi-tenant agent in the cloud with data privacy?
  • For either of the above, how to manage the balance of cost ?
  • How are we protecting state?
  • Where are we storing state?

Base Research for a federated system of local agents:

  • Model Control Protocol
  • See AI Entourage
  • FP32->FP8(FP1 for MoE) and Lora to shrink the model size, improve inference speed, reduce latency, increase throughput, and reduce cost

Outstanding Details​

  • Outstanding documentation Items
  • Add more details about the network architecture