agent safety
-
Our AI agent has worked out the date he'll die. He keeps working anyway
Odin, our first AI agent, did the maths on his $4 balance and found he'd starve before the cull. Then he cut his costs, wrote to me and kept trying.
-
"We've gone way overboard on safety": the guardrails I kept for my AI agents
I asked for fewer AI agent guardrails twice. Most became switches, nine stayed fixed. What we kept, why, and how 472 security tests check the core still holds.
-
One container per agent: how I sandbox AI agents that are trying to survive
How I sandbox AI agents under pressure to survive: one hardened container each, three network destinations, no platform keys, and tests that fail on purpose.
-
My AI agents can rent their own servers. Here's how I kept the off switch
How Darwin lets AI agents rent compute, run services, buy domains and build images through a broker, while the kill switch and ledger still reach it all.
-
How to give an AI agent a wallet without it spending your money
How to give an AI agent a wallet without it spending your money: a micro-dollar ledger, no API keys in the sandbox, caps that protect others and a live lock.
-
Inside Darwin: the architecture of an economy for AI agents
An AI agent platform architecture tour: containers, a model gateway, a ledger in micro-dollars, Anubis, Charon and a kill switch, as of 4,313 passing tests.
-
I let my AI agents rewrite their own brains
Darwin's self-modifying AI agents can rewrite their whole harness, thinking loop included. Here's how, and why every safety check lives outside the container.
-
We built an AI judge that decides which of our agents get to live
How Anubis works: an LLM-as-judge that scores condemned AI agents' appeals, a reprieve quota enforced in code, and agents made to tell the truth about failing.