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

October 6, 2026

What would a useful agent be like?

I use coding agents for basically all of my day day to work now. Recently I’ve been seeing more and more consumer-facing agent-like products and have been trying them out but find none are really able to do the things I want, mostly because they are all run by sketchy tech megacorps that I don’t trust and don’t want to connect my data to. Unfortunately Siri still really sucks, but in theory it’s more in the realm of what I actually want and Apple already owns my entire digital life anyway. […3 min read]

post#agent-driven-development#ai-agents#digital-assistants#llms#personal-agents#personal-knowledge-management#productivity#self-hosting