<?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>LLM on 3rd layer</title><link>https://3rdlayer.uk/tags/llm/</link><description>Recent content in LLM on 3rd layer</description><generator>Hugo -- 0.154.5</generator><language>en-US</language><lastBuildDate>Sat, 24 Jan 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://3rdlayer.uk/tags/llm/index.xml" rel="self" type="application/rss+xml"/><item><title>Do LLMs Have Thinking Styles? REI-40 Experiment on 5 Frontier Models</title><link>https://3rdlayer.uk/posts/llm-rei-experiment/</link><pubDate>Sat, 24 Jan 2026 00:00:00 +0000</pubDate><guid>https://3rdlayer.uk/posts/llm-rei-experiment/</guid><description>We administered the REI-40 dual-processing personality inventory to 5 frontier LLMs. The results reveal distinct &amp;rsquo;thinking style&amp;rsquo; profiles — from neutral responders to rational enthusiasts.</description></item><item><title>psyctl — An LLM Personality Steering Tool</title><link>https://3rdlayer.uk/posts/psyctl-intro/</link><pubDate>Sat, 24 Jan 2026 00:00:00 +0000</pubDate><guid>https://3rdlayer.uk/posts/psyctl-intro/</guid><description>Building an open-source tool that controls LLM personality using Steering Vectors.</description></item><item><title>Sentence Reranking Using LLM Attention Maps</title><link>https://3rdlayer.uk/posts/attention-reranking/</link><pubDate>Sun, 07 Sep 2025 00:00:00 +0000</pubDate><guid>https://3rdlayer.uk/posts/attention-reranking/</guid><description>Leveraging what the LLM already knows. An experiment extracting document relevance signals from Attention Maps to rerank sentences, along with a survey of related papers.</description></item></channel></rss>