Research, essays, and lab notes from SAIPAL — an independent lab studying safe and aligned intelligence.https://saipal.net/https://saipal.net/research/two-hundred-studies-later/https://saipal.net/research/two-hundred-studies-later/Behind our circuit-discovery paper is a registry of about two hundred pre-registered studies, most of which failed. This post walks through that record — what we tried, what broke, and how a question about tool-use agents turned into a result about two eigenvectors of the same graph.Sun, 19 Jul 2026 00:00:00 GMTinterpretabilitymech-interpresearch-noteshttps://saipal.net/blog/welcome/https://saipal.net/blog/welcome/What this blog is, what's coming first, and how to follow along.Thu, 07 May 2026 00:00:00 GMTmetahttps://saipal.net/blog/why-saipal/https://saipal.net/blog/why-saipal/The honest version: I want humanity to prosper, I want less suffering than there would otherwise be, and I think somebody without a product to sell should be checking the numbers.Fri, 01 May 2026 00:00:00 GMTessay