https://starship-whisperer.com/tags/ai/Recent content in AI on Starship WhispererHugoen-usSat, 24 Oct 2026 10:10:00 +0100https://starship-whisperer.com/posts/quantumpizzapanel/Sat, 24 Oct 2026 10:10:00 +0100https://starship-whisperer.com/posts/quantumpizzapanel/My &#39;lonely spinor neuron&#39; from last November wasn&#39;t actually a spinor. Claude worked out why, three other models had a go blind, and then we finally ran the experiment the file had been promising.https://starship-whisperer.com/posts/hybridagentprobe/Fri, 23 Oct 2026 20:30:00 +0100https://starship-whisperer.com/posts/hybridagentprobe/I ran Stanford/Together&#39;s HybridAgent on trick questions and read its &#39;latent thoughts&#39; back as text. What the readout shows, and what it hides.https://starship-whisperer.com/posts/kansnthings/Sun, 30 Nov 2025 16:56:45 +0000https://starship-whisperer.com/posts/kansnthings/<h2 id="exploring-kans-pins-and-other-ramblings">Exploring KANS, PINS and other ramblings</h2> <p>Warning, this is a fairly non systematic wondering, blogged for future reference. Anything useful is probably accidental!</p> <p>We were reading about Kolmogorov-Arnold Networks — again — because sometimes you have to circle back to things before they click. And this time, something clicked.</p> <p>We ended up spending an evening bouncing between Claude and Gemini, following threads, and accidentally walking into research directions that apparently people are actually working on. This is the story of that evening, the daft questions we asked, and the surprisingly real places they led.</p>