<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"><channel>
<title>NeuroForge lab updates</title><link>https://neuroforge.io/updates/</link><description>Dated updates from the NeuroForge lab.</description>
<item><title>A research cycle that keeps the result</title><link>https://neuroforge.io/updates/#research-cycle-runner</link><guid>https://neuroforge.io/updates/#research-cycle-runner</guid><pubDate>Sat, 24 Oct 2026 00:00:00 GMT</pubDate><description>Our research workflow can take a proposed experiment, run it within a defined scope and record both positive and negative results. One recent cycle tested different ways of grouping recorded model data ranges. The work produced a repeatable path from a hypothesis to an experiment and a retained result. The measurements describe that planning task; they do not establish a full-model speedup.</description></item>
<item><title>Using the research process to improve itself</title><link>https://neuroforge.io/updates/#iterative-improvement</link><guid>https://neuroforge.io/updates/#iterative-improvement</guid><pubDate>Fri, 23 Oct 2026 00:00:00 GMT</pubDate><description>We are using iterative research workflows to propose, test and improve parts of the software that supports our experiments. People set the scope and checks. AI-assisted proposals are evaluated against those checks, and useful changes can be retained while failed or inconclusive attempts stay in the record. This recursive software improvement is operating under supervision; it is not a claim that the whole research programme runs autonomously.</description></item>
</channel></rss>