October 23, 2026

Personal agents need a new kind of harness

I’ve been working on building a personal agent that is both useful and secure and have come to the conclusion that it needs a new kind of harness, specifically one without a shell. A personal agent comes with the lethal trifecta by default — in order to be useful, it needs access to your data and the internet, which is full of untrusted content and ways to exfiltrate information. […14 min read]

post#agent-tools#ai-agents#ai-safety#coding-agents#lethal-trifecta#llms#personal-agents#security

October 7, 2026

A useful personal agent

I started building a useful personal agent. What makes it useful is that it runs on my computer, but this immediately raises concerns about data exfiltration. I use Apple reminders (among other things) to organise my life so I had it write a little script to be able to interact with those, which works great. One of the main things I want help with is getting a handle on my chaotic piles of todos. They are scattered all over the place and all mixed up. […2 min read]

post#ai#ai-agents#ai-assistants#data-security#lethal-trifecta#llms#parenting#personal-agents#personal-knowledge-management#privacy#productivity