Skip to main content

AI Agent

Agent architecture, trust & behavior

Archive17 posts

When the Harness Gets Messy, Start Over

Building an inference engine from scratch with an agent, the project unraveled and model performance visibly degraded. The fix: pause, redefine the goal, start fresh in a new repo. Same model, different entity. Microsoft simulated 200k conversations: once a model goes off track, it won't recover.

5 min read

Subscribe to Updates

Get notified when I publish new posts. No spam, ever.

Only used for blog update notifications. Unsubscribe anytime.