<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Gemma on Local First AI</title><link>https://localfirstai.eu/tags/gemma/</link><description>Recent content in Gemma on Local First AI</description><image><title>Local First AI</title><url>https://localfirstai.eu/images/og-default.png</url><link>https://localfirstai.eu/images/og-default.png</link></image><generator>Hugo</generator><language>en-us</language><lastBuildDate>Tue, 10 Nov 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://localfirstai.eu/tags/gemma/index.xml" rel="self" type="application/rss+xml"/><item><title>Prompt Injection on a Local Model: What Worked, What Did Not, and What the Fix Costs</title><link>https://localfirstai.eu/posts/2026-11-10-prompt-injection-on-a-local-model/</link><pubDate>Tue, 10 Nov 2026 00:00:00 +0000</pubDate><guid>https://localfirstai.eu/posts/2026-11-10-prompt-injection-on-a-local-model/</guid><description>Three things measured on a local model anyone can run (gemma4:26b): which kind of injected text took the model&amp;#39;s contribution to zero and which did not, why a design where the model can only add points did not protect it, and what a fix in the code around the model costs. Synthetic scam messages, six injected paragraphs, two runs on one day, everything public.</description></item><item><title>Ollama No Longer Calls Home From Our Mini, and Our Local Reader Answers Every Message: the Week of 27 October</title><link>https://localfirstai.eu/posts/2026-11-02-week-of-27-october/</link><pubDate>Mon, 02 Nov 2026 00:00:00 +0000</pubDate><guid>https://localfirstai.eu/posts/2026-11-02-week-of-27-october/</guid><description>Everything built on the Mac mini this week, with the artefact behind each line. Ollama&amp;#39;s daemon was calling ollama.com every four hours while the models sent nothing; the switch that stops it is now measured and on. The local reader&amp;#39;s 22 empty answers were repetition loops: a bigger context moved them, a retry without thinking closed them, 0.882 → 0.914. The mini throttled itself to 8 tokens a second over a half-finished OS upgrade. Ten changes: two from real inputs, seven from tests, one from reading.</description></item></channel></rss>