Richard MacManus
Can a Cloud-Native Harness Make Agents Reliable Beyond the Desktop?
Kubernetes co-creators Craig McLuckie and Joe Beda aim to bring agent harnesses fully into the cloud.


Newsletter
The AI Engineer newsletter + Top technical AI podcast. How leading labs build Agents, Models, Infra, & AI for Science. See https://latent.space/about for highlights from Greg Brockman, Andrej Karpathy, George Hotz, Simon Willison, Soumith Chintala et al!
20 posts in the last 90 days · newest 7 Oct
Richard MacManus
Kubernetes co-creators Craig McLuckie and Joe Beda aim to bring agent harnesses fully into the cloud.



Richard MacManus
After leading Meta’s Llama models, Ahmad Al-Dahle is now transforming Airbnb with AI — from how its teams develop products to how it serves guests.

We catch up with RLM first author Alex Zhang, MIT PhD, on Jev, PhD masxing, and the future of harnesses.
... but you can’t try it yet unless you are “government users and trusted cyber defenders in the Fairwind Program”

Our DevDay coverage - the first pod on the DevDay lineup - dives in with the leaders of OpenAI’s CUA team and API platform.
the most confident DevDay yet.
Congrats team!

Shipping Opus/Sonnet 5.5, Mods, Plugins, Projects, Tag while Pacing the Frontier
In 2023 most people doubted that there could be more than 1 or 2 frontier model labs. Now there are dozens.... and Stripe just bought the best known one for $7B.
A quiet day lets us discuss the work behind the scenes - now open for business!

Richard MacManus
GWM Worlds 2 uses persistent context and timed actions to steer a world model generating video and audio in real time.

Adrian Sanborn
Guest Post: In science, thinking has gotten cheap but doing has not. This asymmetry is reshaping how research companies operate, largely inconspicuously.

Team Zuck is absolutely on fire.
RJ Honicky
Radical Numerics is using biological chain-of-thought and multimodal perception to keep up with the bio-defense arms race, design new genomes and gain insights into biology itself.

overshadowing more efficient GPT6 models from OpenAI
