Archive - Inference Notes

The cheapest line item in my AI app is the AI

When you ship a consumer app that leans on a large language model, the standard cost warning is always the same: watch your inference bill.

May 29 • Sathish J

Three things that surprised me running a personal AI agent in production

For the last few months I’ve run a small agent system on a server in my house.

May 26 • Sathish J

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts