<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: oedemis</title><link>https://news.ycombinator.com/user?id=oedemis</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sat, 02 May 2026 19:21:43 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=oedemis" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by oedemis in "2025: The Year in LLMs"]]></title><description><![CDATA[
<p>as architectures evolve, i think it can be that we learn more "side effects".. back in 2020 openai researchers said "GPT-3 is applied without any gradient updates or fine-tuning" the model emerges at a certain level of scale...</p>
]]></description><pubDate>Thu, 01 Jan 2026 15:31:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=46454851</link><dc:creator>oedemis</dc:creator><comments>https://news.ycombinator.com/item?id=46454851</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46454851</guid></item><item><title><![CDATA[New comment by oedemis in "CUDA Tile Open Sourced"]]></title><description><![CDATA[
<p>how mojo with max optimize the process?</p>
]]></description><pubDate>Fri, 26 Dec 2025 01:47:34 +0000</pubDate><link>https://news.ycombinator.com/item?id=46388472</link><dc:creator>oedemis</dc:creator><comments>https://news.ycombinator.com/item?id=46388472</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46388472</guid></item><item><title><![CDATA[New comment by oedemis in "The Illustrated Transformer"]]></title><description><![CDATA[
<p>there is also very good explanation from Luis Serrano, <a href="https://youtu.be/fkO9T027an0" rel="nofollow">https://youtu.be/fkO9T027an0</a></p>
]]></description><pubDate>Tue, 23 Dec 2025 13:36:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=46365218</link><dc:creator>oedemis</dc:creator><comments>https://news.ycombinator.com/item?id=46365218</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46365218</guid></item><item><title><![CDATA[New comment by oedemis in "Donating the Model Context Protocol and establishing the Agentic AI Foundation"]]></title><description><![CDATA[
<p>i thought skills are the new context resolver</p>
]]></description><pubDate>Tue, 09 Dec 2025 20:40:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=46210343</link><dc:creator>oedemis</dc:creator><comments>https://news.ycombinator.com/item?id=46210343</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46210343</guid></item><item><title><![CDATA[New comment by oedemis in "IBM to acquire Confluent"]]></title><description><![CDATA[
<p>Streaming, EDA can solve lot of data challenges for enterprise AI use cases</p>
]]></description><pubDate>Mon, 08 Dec 2025 15:14:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=46193136</link><dc:creator>oedemis</dc:creator><comments>https://news.ycombinator.com/item?id=46193136</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46193136</guid></item><item><title><![CDATA[New comment by oedemis in "IBM CEO says there is 'no way' spending on AI data centers will pay off"]]></title><description><![CDATA[
<p><a href="https://huggingface.co/ibm" rel="nofollow">https://huggingface.co/ibm</a> here is very interesting research going
<a href="https://huggingface.co/ibm-granite" rel="nofollow">https://huggingface.co/ibm-granite</a></p>
]]></description><pubDate>Wed, 03 Dec 2025 17:33:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=46137389</link><dc:creator>oedemis</dc:creator><comments>https://news.ycombinator.com/item?id=46137389</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46137389</guid></item><item><title><![CDATA[New comment by oedemis in "IBM CEO says there is 'no way' spending on AI data centers will pay off"]]></title><description><![CDATA[
<p>ibm developed SSMs/mamba models and also releasing trainings datasets i think, also quantum computing is strategic option..</p>
]]></description><pubDate>Wed, 03 Dec 2025 12:32:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=46133760</link><dc:creator>oedemis</dc:creator><comments>https://news.ycombinator.com/item?id=46133760</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46133760</guid></item><item><title><![CDATA[New comment by oedemis in "No clicks, no content: The unsustainable future of AI search"]]></title><description><![CDATA[
<p>the first thing when i open my browser is lookup at <a href="https://news.ycombinator.com/">https://news.ycombinator.com/</a> :)</p>
]]></description><pubDate>Sun, 31 Aug 2025 16:07:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=45084233</link><dc:creator>oedemis</dc:creator><comments>https://news.ycombinator.com/item?id=45084233</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45084233</guid></item><item><title><![CDATA[New comment by oedemis in "Simple Explanation of LLMs"]]></title><description><![CDATA[
<p>Hello, tried to explain Large Language Models with some visualizations, especially the attention mechanism.</p>
]]></description><pubDate>Tue, 04 Mar 2025 11:23:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=43253212</link><dc:creator>oedemis</dc:creator><comments>https://news.ycombinator.com/item?id=43253212</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43253212</guid></item><item><title><![CDATA[Simple Explanation of LLMs]]></title><description><![CDATA[
<p>Article URL: <a href="https://blog.oedemis.io/understanding-llms-a-simple-guide-to-large-language-models">https://blog.oedemis.io/understanding-llms-a-simple-guide-to-large-language-models</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=43253211">https://news.ycombinator.com/item?id=43253211</a></p>
<p>Points: 94</p>
<p># Comments: 31</p>
]]></description><pubDate>Tue, 04 Mar 2025 11:23:05 +0000</pubDate><link>https://blog.oedemis.io/understanding-llms-a-simple-guide-to-large-language-models</link><dc:creator>oedemis</dc:creator><comments>https://news.ycombinator.com/item?id=43253211</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43253211</guid></item><item><title><![CDATA[New comment by oedemis in "Ingesting PDFs and why Gemini 2.0 changes everything"]]></title><description><![CDATA[
<p>there is also <a href="https://ds4sd.github.io/docling/" rel="nofollow">https://ds4sd.github.io/docling/</a> from ibm research which is mit license and track bounding boxes as rich json format</p>
]]></description><pubDate>Wed, 05 Feb 2025 21:29:40 +0000</pubDate><link>https://news.ycombinator.com/item?id=42955441</link><dc:creator>oedemis</dc:creator><comments>https://news.ycombinator.com/item?id=42955441</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42955441</guid></item><item><title><![CDATA[New comment by oedemis in "GitSynth – Explore Git Commits and Diffs with GenAI (Ollama) for Deeper Insights"]]></title><description><![CDATA[
<p>mika6996, all set! Feel free to share any updates or thoughts on the idea</p>
]]></description><pubDate>Fri, 03 Jan 2025 19:50:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=42588866</link><dc:creator>oedemis</dc:creator><comments>https://news.ycombinator.com/item?id=42588866</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42588866</guid></item><item><title><![CDATA[New comment by oedemis in "GitSynth – Explore Git Commits and Diffs with GenAI (Ollama) for Deeper Insights"]]></title><description><![CDATA[
<p>GitSynth – A Git Commit Visualizer for Insightful Code Exploration diffs and commits with GenAI (ollama)<p>Hey HN!<p>I’m excited to share GitSynth, a tool designed to visualize Git repositories and generates commits and changelog.md file insightful and interactive way. here we go: <a href="https://github.com/oedemis/gitsynth">https://github.com/oedemis/gitsynth</a></p>
]]></description><pubDate>Fri, 03 Jan 2025 19:20:02 +0000</pubDate><link>https://news.ycombinator.com/item?id=42588631</link><dc:creator>oedemis</dc:creator><comments>https://news.ycombinator.com/item?id=42588631</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42588631</guid></item><item><title><![CDATA[GitSynth – Explore Git Commits and Diffs with GenAI (Ollama) for Deeper Insights]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/oedemis/gitsynth">https://github.com/oedemis/gitsynth</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=42588630">https://news.ycombinator.com/item?id=42588630</a></p>
<p>Points: 1</p>
<p># Comments: 3</p>
]]></description><pubDate>Fri, 03 Jan 2025 19:20:02 +0000</pubDate><link>https://github.com/oedemis/gitsynth</link><dc:creator>oedemis</dc:creator><comments>https://news.ycombinator.com/item?id=42588630</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42588630</guid></item><item><title><![CDATA[New comment by oedemis in "Show HN: FastGraphRAG – Better RAG using good old PageRank"]]></title><description><![CDATA[
<p>but what about the chunk size, if we have a small chunks like 1 sentence and the hyde embeddings are most of the time larger, the results are not so good</p>
]]></description><pubDate>Wed, 20 Nov 2024 01:56:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=42190145</link><dc:creator>oedemis</dc:creator><comments>https://news.ycombinator.com/item?id=42190145</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42190145</guid></item><item><title><![CDATA[New comment by oedemis in "The Cloud Computer"]]></title><description><![CDATA[
<p>sustainability considerations?</p>
]]></description><pubDate>Fri, 27 Oct 2023 00:53:22 +0000</pubDate><link>https://news.ycombinator.com/item?id=38033487</link><dc:creator>oedemis</dc:creator><comments>https://news.ycombinator.com/item?id=38033487</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=38033487</guid></item><item><title><![CDATA[New comment by oedemis in "Ask HN: What are your predictions for 2023?"]]></title><description><![CDATA[
<p>invest in decarbonization movement</p>
]]></description><pubDate>Sun, 25 Dec 2022 15:48:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=34128189</link><dc:creator>oedemis</dc:creator><comments>https://news.ycombinator.com/item?id=34128189</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=34128189</guid></item><item><title><![CDATA[New comment by oedemis in "Ask HN: Event Driven Design/Discovery?"]]></title><description><![CDATA[
<p>i also write recently something about this not eventstorming but more in architecture 
<a href="https://blog.oedemis.io/serverless-event-driven-architectures" rel="nofollow">https://blog.oedemis.io/serverless-event-driven-architecture...</a></p>
]]></description><pubDate>Tue, 06 Dec 2022 14:12:30 +0000</pubDate><link>https://news.ycombinator.com/item?id=33880043</link><dc:creator>oedemis</dc:creator><comments>https://news.ycombinator.com/item?id=33880043</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=33880043</guid></item><item><title><![CDATA[Serverless Event-Driven Architectures]]></title><description><![CDATA[
<p>Article URL: <a href="https://blog.oedemis.io/serverless-event-driven-architectures">https://blog.oedemis.io/serverless-event-driven-architectures</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=33879920">https://news.ycombinator.com/item?id=33879920</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 06 Dec 2022 14:06:10 +0000</pubDate><link>https://blog.oedemis.io/serverless-event-driven-architectures</link><dc:creator>oedemis</dc:creator><comments>https://news.ycombinator.com/item?id=33879920</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=33879920</guid></item></channel></rss>