<?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[Could someone make 'Norbu AI for Marx and Engels'?]]></title><description><![CDATA[<p dir="auto"><a href="https://norbu-ai.org/" target="_blank" rel="noopener noreferrer nofollow ugc">https://norbu-ai.org/</a> is an LLM with expertise focused specifically on the Pali Canon. It's supposed to have narrow expertise and be used for a single purpose.</p>
<p dir="auto">Norbu is useful for searching through the canon and say, "Where does the Buddha talk about alcohol?" "Where does the idea of the seven factors of awakening come from?"</p>
<p dir="auto">Norbu allows you to get from concepts you've heard about back to primary sources. It does have some advantages over just searching <a href="http://suttacentral.net" target="_blank" rel="noopener noreferrer nofollow ugc">suttacentral.net</a> or <a href="http://accesstoinsight.org" target="_blank" rel="noopener noreferrer nofollow ugc">accesstoinsight.org</a>: you don't have to know the keywords you're looking for, you can look for things you're only starting to understand when you don't know the jargon.</p>
<p dir="auto">The works of Marx and Engels are about the same size as the Pali Canon. Imagine a narrowly-expert LLM, a fine-tuned open-source model, and baby leftists asking it things like –</p>
<ul>
<li>Where is the tendency of the rate  of profit to fall discussed?</li>
<li>What was Marx's understanding of international trade? (and it wouldn't just tell you what it was but what chapter and verse it's citing)</li>
<li>Did Marx ever consider there wouldn't be gold-backed money?</li>
</ul>
<p dir="auto">and the LLM gives answers grounded in the primary sources.</p>
<p dir="auto">What do you think of my idea?</p>
]]></description><link>https://citiverse.it/topic/99ffe449-c39c-4778-95a0-5e76c30fba37/could-someone-make-norbu-ai-for-marx-and-engels</link><generator>RSS for Node</generator><lastBuildDate>Tue, 18 Aug 2026 10:30:43 GMT</lastBuildDate><atom:link href="https://citiverse.it/topic/99ffe449-c39c-4778-95a0-5e76c30fba37.rss" rel="self" type="application/rss+xml"/><pubDate>Sat, 25 Jul 2026 11:22:08 GMT</pubDate><ttl>60</ttl><item><title><![CDATA[Reply to Could someone make 'Norbu AI for Marx and Engels'? on Sun, 09 Aug 2026 11:05:52 GMT]]></title><description><![CDATA[<p dir="auto">Thanks for letting me know! I'll have a look.</p>
]]></description><link>https://citiverse.it/post/https://lemmy.world/comment/25201470</link><guid isPermaLink="true">https://citiverse.it/post/https://lemmy.world/comment/25201470</guid><dc:creator><![CDATA[bademantel@lemmy.world]]></dc:creator><pubDate>Sun, 09 Aug 2026 11:05:52 GMT</pubDate></item><item><title><![CDATA[Reply to Could someone make 'Norbu AI for Marx and Engels'? on Sat, 08 Aug 2026 21:13:49 GMT]]></title><description><![CDATA[<p dir="auto">Oh boy oh boy oh boy this is very exciting.....</p>
<p dir="auto">Days after I posted this I hear about a serious plan to do exactly what I said: <a href="https://lemmy.ml/post/51088047" target="_blank" rel="noopener noreferrer nofollow ugc">https://lemmy.ml/post/51088047</a></p>
<p dir="auto">and I said "<em>“no hallucinations” isn’t a thing within the LLM paradigm</em>" – and they're using knowledge-graphs (a different paradigm) so it can fulfill your "no hallucinations" requirement</p>
]]></description><link>https://citiverse.it/post/https://lemmy.ml/comment/27146410</link><guid isPermaLink="true">https://citiverse.it/post/https://lemmy.ml/comment/27146410</guid><dc:creator><![CDATA[frightful_hobgoblin@lemmy.ml]]></dc:creator><pubDate>Sat, 08 Aug 2026 21:13:49 GMT</pubDate></item><item><title><![CDATA[Reply to Could someone make 'Norbu AI for Marx and Engels'? on Wed, 29 Jul 2026 11:33:29 GMT]]></title><description><![CDATA[<p dir="auto">"no hallucinations" isn't a thing within the LLM paradigm</p>
<p dir="auto">Norbu always says "I may be mistaken, please verify"</p>
]]></description><link>https://citiverse.it/post/https://lemmy.ml/comment/26959080</link><guid isPermaLink="true">https://citiverse.it/post/https://lemmy.ml/comment/26959080</guid><dc:creator><![CDATA[frightful_hobgoblin@lemmy.ml]]></dc:creator><pubDate>Wed, 29 Jul 2026 11:33:29 GMT</pubDate></item><item><title><![CDATA[Reply to Could someone make 'Norbu AI for Marx and Engels'? on Sun, 26 Jul 2026 01:50:41 GMT]]></title><description><![CDATA[<p dir="auto">i like it. that'd be actually great for referencing works, and finding stuff by asking it questions.</p>
<p dir="auto">i don't think it'd be that hard if you meet the steep hardware requirements for doing it.</p>
<p dir="auto">one could probably do something like that if enough people are interested.</p>
]]></description><link>https://citiverse.it/post/https://lemmy.ml/comment/26898180</link><guid isPermaLink="true">https://citiverse.it/post/https://lemmy.ml/comment/26898180</guid><dc:creator><![CDATA[umbrella@lemmy.ml]]></dc:creator><pubDate>Sun, 26 Jul 2026 01:50:41 GMT</pubDate></item><item><title><![CDATA[Reply to Could someone make 'Norbu AI for Marx and Engels'? on Sat, 25 Jul 2026 16:39:07 GMT]]></title><description><![CDATA[<p dir="auto">it's definitely doable, you can install a local model and train it on marxist literature, you probably just need like 64gb of ram lol. maybe 32 will do tho. but yeah, it's not a cheap project i guess.</p>
]]></description><link>https://citiverse.it/post/https://lemmy.ml/comment/26891001</link><guid isPermaLink="true">https://citiverse.it/post/https://lemmy.ml/comment/26891001</guid><dc:creator><![CDATA[gary_host_laptop@lemmy.ml]]></dc:creator><pubDate>Sat, 25 Jul 2026 16:39:07 GMT</pubDate></item><item><title><![CDATA[Reply to Could someone make 'Norbu AI for Marx and Engels'? on Sat, 25 Jul 2026 12:40:02 GMT]]></title><description><![CDATA[<p dir="auto">I'd like it. Making the literature more accessable is a good thing imo. Important to me would be the trustworthiness you mentioned. This includes showing the specific source material but even more important: no hallucinations. Just tell me if there's nothing there, don't make shit up.</p>
]]></description><link>https://citiverse.it/post/https://lemmy.world/comment/24946074</link><guid isPermaLink="true">https://citiverse.it/post/https://lemmy.world/comment/24946074</guid><dc:creator><![CDATA[bademantel@lemmy.world]]></dc:creator><pubDate>Sat, 25 Jul 2026 12:40:02 GMT</pubDate></item></channel></rss>