Using ldgr we tightened a published bound on the Riemann zeta function
The useful part is how often we were wrong.
Read postBlog
Writing on long-running agent work, provenance, and the systems we build with both.
The useful part is how often we were wrong.
Read postThe reasoning that produced yesterday's code is gone by morning. On the four kinds of record a resumed agent session actually needs, and the tool we built to keep them.
Read postThere is a sentence we keep deleting from our research notes. On null controls, ablations, and why we publish the regime where our own effect reverses.
Read post