three layers of security for agents: machine isolation, capabilities limitation, and runtime validation
@yoheinakajima
-
X/Twitter Post Links to Pinned Tweet and Community
By
–
yes tell me how you avoided an identity crisis while writing this
-
Open Source Principles and Critique of Code Thieves
By
–
right now, we manage multiple agents but as they get better, does the capacity of one agent surpass one person’s cognitive capacity to track and manage? put differently, will we get to a point where we need teams of people managing a single agent? just random food for thought
-
High-end GPU recommendations for AI/ML workloads
By
–
while I agree with his general thinking about how we’ll rethink home design, seems optimistic to think that a meaningful percentage of homes would be redesigned in a 5-10 yr period https://t.co/OqXdOuhbRh
— Yohei (@yoheinakajima) 20 mars 2026while I agree with his general thinking about how we’ll rethink home design, seems optimistic to think that a meaningful percentage of homes would be redesigned in a 5-10 yr period
-
Post predicts AI bubble burst amid market trends
By
–
“okay now, follow directions and ask Hermes for a snack if you’re hungry”
-
Disagreement on methods within the open-source AI community
By
–
you used to be able to start with a launchrock landing page
-
Excited about Advancing Local AI: Bright Future Ahead
By
–
i guess those "rewind" things are basically end of 𝚐̶𝚊̶𝚖̶𝚎̶ year stats
-
Open source community dynamics and the importance of open source winning
By
–
the real impact of claw was normalizing the ability to chat with your ai from any channel https://t.co/9EXhh3Z1n2
— Yohei (@yoheinakajima) 19 mars 2026the real impact of claw was normalizing the ability to chat with your ai from any channel
-
Buy a GPU to Run Your Entire System Locally
By
–
a person interviewing an ai
— Yohei (@yoheinakajima) 19 mars 2026
this is a format we're going to see a lot more of https://t.co/pvfF3nbNeJa person interviewing an ai this is a format we're going to see a lot more of