Eugene Yan
Person on 4 sites
Member of technical staff at Anthropic; previously led ML/AI teams at Amazon, Alibaba and Lazada, and writes about LLMs, RecSys and engineering at…
-
4 facts on wiqqi (opens wiqqi.app)
Who people, organisations and podcasts are, and how they connect, with sources.
Updated 2026-11-01 -
4 channels on ppll (opens ppll.app)
Where public figures publish, and what they are on record saying.
Updated 2026-09-01 -
15 beliefs on korrents (opens korrents.com)
-
The surrounding system framework and scaffolding matter more for AI agent capability than the underlying model. (opens korrents.com)
“The experiments showed that the system framework matters far more than the underlying model.”
-
The practices that make someone effective at working with an AI model are the same practices that make someone effective at onboarding any new human collaborator. (opens korrents.com)
“none of this is specific to AI. It's simply how you onboard and work with any new collaborator.”
-
Delegating a task to an AI agent only works if the output can be verified, which requires defining success criteria first. (opens korrents.com)
“You can't delegate what you can't verify, so this requires first defining success criteria and metrics.”
-
The surrounding system framework and scaffolding matter more for AI agent capability than the underlying model. (opens korrents.com)
-
11 recommendations on rcmnd (opens rcmnd.app)
-
Warp (opens rcmnd.app)
“Trying Warp instead of my usual iTerm”
-
Fish (opens rcmnd.app)
“Trying Fish instead of my usual Oh My Zsh”
-
Rectangle (opens rcmnd.app)
“While Raycast already has window management, Rectangle lets you hit the hotkey again”
-
Warp (opens rcmnd.app)