<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title><![CDATA[Hermes can be used with the DeepSeek V4 Pro model]]></title><description><![CDATA[<p>Hermes can be used with the DeepSeek V4 Pro model</p><p>If you set a /goal, it will come up with a multi agent strategy to look for solutions similar to Karpathy's /autoresearch </p><p><a href="https://hermes-agent.nousresearch.com/docs/user-guide/tui" rel="nofollow noopener"><span>https://</span><span>hermes-agent.nousresearch.com/</span><span>docs/user-guide/tui</span></a></p><p><a href="https://hermes-agent.nousresearch.com/docs/user-guide/features/goals#commands" rel="nofollow noopener"><span>https://</span><span>hermes-agent.nousresearch.com/</span><span>docs/user-guide/features/goals#commands</span></a></p><p>I think for coding you are better off with AntiGravity (or claude).</p><p>But for RnD or data science, things that require a hypothesis, this is cool.</p><p><a href="https://infosec.exchange/tags/hermes" rel="tag">#<span>hermes</span></a> <a href="https://infosec.exchange/tags/deepseek" rel="tag">#<span>deepseek</span></a> <a href="https://infosec.exchange/tags/research" rel="tag">#<span>research</span></a> <a href="https://infosec.exchange/tags/autoresearch" rel="tag">#<span>autoresearch</span></a> <a href="https://infosec.exchange/tags/karpathy" rel="tag">#<span>karpathy</span></a></p>]]></description><link>https://board.circlewithadot.net/topic/ec619474-5354-45af-abac-5c8d6af0d445/hermes-can-be-used-with-the-deepseek-v4-pro-model</link><generator>RSS for Node</generator><lastBuildDate>Fri, 15 May 2026 02:44:21 GMT</lastBuildDate><atom:link href="https://board.circlewithadot.net/topic/ec619474-5354-45af-abac-5c8d6af0d445.rss" rel="self" type="application/rss+xml"/><pubDate>Mon, 11 May 2026 14:00:47 GMT</pubDate><ttl>60</ttl><item><title><![CDATA[Reply to Hermes can be used with the DeepSeek V4 Pro model on Mon, 11 May 2026 14:49:05 GMT]]></title><description><![CDATA[<p><a href="https://hermes-agent.nousresearch.com/docs/user-guide/features/rl-training" rel="nofollow noopener"><span>https://</span><span>hermes-agent.nousresearch.com/</span><span>docs/user-guide/features/rl-training</span></a></p><p>Hermes is an evolutionary approach. Compared the DSPy agent model, which is programmatic / declarative. </p><p>DSPy for many of the use cases, is a lot of work (fine-tuning, debugging). DSPy excels at finance tasks or data analytics where you know all the details. But that is phase 2. Phase 1 is getting these details, and getting them fast. That is imho where Hermes comes in. </p><p>I can see myself using Hermes for </p><p>* Content tooling: auto-briefing, strategic foresight assessments.<br />* Intelligence analysis: method approaches to trend analysis or signals<br />* Individualization of content. OSINT, social media scraping, trend analysis.<br />* Data sensing, estimation on datasets, start simple<br />* Autoresearch (later), for example, for optimization solutions or performance debugging</p><p><a href="https://infosec.exchange/tags/dspy" rel="tag">#<span>dspy</span></a> <a href="https://infosec.exchange/tags/hermes" rel="tag">#<span>hermes</span></a> <a href="https://infosec.exchange/tags/declarative" rel="tag">#<span>declarative</span></a> <a href="https://infosec.exchange/tags/evolutionary" rel="tag">#<span>evolutionary</span></a> <a href="https://infosec.exchange/tags/ai" rel="tag">#<span>ai</span></a></p>]]></description><link>https://board.circlewithadot.net/post/https://infosec.exchange/users/windsheep/statuses/116556493335734088</link><guid isPermaLink="true">https://board.circlewithadot.net/post/https://infosec.exchange/users/windsheep/statuses/116556493335734088</guid><dc:creator><![CDATA[windsheep@infosec.exchange]]></dc:creator><pubDate>Mon, 11 May 2026 14:49:05 GMT</pubDate></item></channel></rss>