<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hacker News: 8lamaster8</title><link>https://news.ycombinator.com/user?id=8lamaster8</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 19 Nov 2026 05:14:43 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=8lamaster8" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[Show HN: 3-SAT: Let me show you 500K variables]]></title><description><![CDATA[
<p>Not theory.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=50415664">https://news.ycombinator.com/item?id=50415664</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 08 Nov 2026 18:20:56 +0000</pubDate><link>https://zenodo.org/records/23933428</link><dc:creator>8lamaster8</dc:creator><comments>https://news.ycombinator.com/item?id=50415664</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50415664</guid></item><item><title><![CDATA[New comment by 8lamaster8 in "Ask HN: What's your current AI agentic setup?"]]></title><description><![CDATA[
<p>I built my experimental system and I'm using it. I'm genuinely very happy with it. If I had more compute and could run a real, full 30B model locally, I'd be absolutely thrilled.<p><a href="https://github.com/8lamaster8/GIN" rel="nofollow">https://github.com/8lamaster8/GIN</a></p>
]]></description><pubDate>Thu, 05 Nov 2026 08:36:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=50376692</link><dc:creator>8lamaster8</dc:creator><comments>https://news.ycombinator.com/item?id=50376692</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50376692</guid></item><item><title><![CDATA[New comment by 8lamaster8 in "Three new discoveries in mathematics, computer science, and physics"]]></title><description><![CDATA[
<p>local p=np
global p!=np<p>why, because of time.<p>what does it mean, every key is formed only during the process and no other way!
if you understand how the key is formed - you can hack that level, but a new level means a new key.<p>again: understand, insert - hack<p>but you can't understand how the key is formed, if you don't see it...<p>for 50 years people have wanted to find the key, the magical key, I got it, and it's not magical<p><a href="https://zenodo.org/records/23812703" rel="nofollow">https://zenodo.org/records/23812703</a></p>
]]></description><pubDate>Sun, 01 Nov 2026 05:56:41 +0000</pubDate><link>https://news.ycombinator.com/item?id=50323050</link><dc:creator>8lamaster8</dc:creator><comments>https://news.ycombinator.com/item?id=50323050</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50323050</guid></item><item><title><![CDATA[New comment by 8lamaster8 in "Separating logic and language"]]></title><description><![CDATA[
<p>Nice explainer. One nuance I’d be careful with: “the brain doesn’t think in words” is broader than what the study seems to establish. The stronger result is that the natural-language network is not necessary for the kinds of inductive and deductive reasoning tested here.<p>The AI implication is fascinating though. We tend to build systems where the language model is simultaneously the language interface, memory, planner, reasoner and controller. Human cognition may be pointing in the opposite architectural direction: separate persistent state, reasoning/control mechanisms and language, then let language be one tool among several.<p>That distinction seems more interesting to me than simply asking whether LLMs “reason in language.”</p>
]]></description><pubDate>Fri, 28 Aug 2026 17:48:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=49482063</link><dc:creator>8lamaster8</dc:creator><comments>https://news.ycombinator.com/item?id=49482063</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49482063</guid></item><item><title><![CDATA[Show HN: Is the "frozen weights" paradigm the main bottleneck for AGI?]]></title><description><![CDATA[
<p>I believe the bottleneck for AGI is our reliance on static, "pre-frozen" weights. If the logic is frozen during inference, it’s just a glorified lookup table. Real intelligence needs a substrate that rewires itself through experience.
As a passion project, I’m building an AI assistant that learns in real-time without any underlying LLM or external generative APIs.
Just a heads-up: This is a solo enthusiast project, and I'm still deep in the 'build-test-break' cycle. It’s very much a work in progress. I’m not claiming to have solved AGI — I’m just exploring a different path.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47034056">https://news.ycombinator.com/item?id=47034056</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 16 Feb 2026 12:10:35 +0000</pubDate><link>https://github.com/8lamaster8/hybrid-ai-core/tree/master/autonomous_ai</link><dc:creator>8lamaster8</dc:creator><comments>https://news.ycombinator.com/item?id=47034056</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47034056</guid></item></channel></rss>