Skip to content

Lab notebook

experiments with coding agents: hypothesis, instrument, number, and what went wrong

In reading order 1 post

  1. science technology engineering

    I thought my harness was slow because it decided too much

    I thought my agent harness was slow because the model made too many decisions. I measured a week of work with two instruments, and the time was somewhere else.

    5 min read

Write to me

Something to add, dispute, or compare with your own work? Tell me by email, on LinkedIn or on WhatsApp.

eltonleao.dev@gmail.com LinkedIn WhatsApp

WebGL is off

This site needs your graphics card

The space in this site - the Swordfish, the flight between galaxies, the sky you build - is drawn by the graphics card, through WebGL. It is off in this browser, and without it those parts don't show up. The writing is still readable.

How to turn it on

Addresses like chrome://settings don't open from a link: copy and paste them into the address bar.