<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>PxA Labs Blog</title><description>PxA Labs is a multi-disciplinary research collective building high-fidelity intelligent systems across speech, AI safety, bioinformatics, multi-agent systems and signal processing.</description><link>https://pxa-labs.pxalabs.workers.dev</link><item><title>Introducing the PxA Labs website</title><link>https://pxa-labs.pxalabs.workers.dev/blog/hello-world</link><guid isPermaLink="true">https://pxa-labs.pxalabs.workers.dev/blog/hello-world</guid><description>A single home for our projects, research write-ups and demo videos — and how we intend to use it.</description><pubDate>Fri, 13 Nov 2026 00:00:00 GMT</pubDate></item><item><title>SafetyPulse: catching safety drift before it ships</title><link>https://pxa-labs.pxalabs.workers.dev/blog/safetypulse-safety-drift</link><guid isPermaLink="true">https://pxa-labs.pxalabs.workers.dev/blog/safetypulse-safety-drift</guid><description>Fine-tuning on harmless data can quietly weaken a model&apos;s refusals. SafetyPulse reads the refusal circuit at every checkpoint and gates it.</description><pubDate>Thu, 12 Nov 2026 00:00:00 GMT</pubDate></item></channel></rss>