<?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[RSS Feed]]></title><description><![CDATA[RSS Feed]]></description><link>https://ecency.com</link><image><url>https://ecency.com/logo512.png</url><title>RSS Feed</title><link>https://ecency.com</link></image><generator>RSS for Node</generator><lastBuildDate>Tue, 28 Jul 2026 08:39:19 GMT</lastBuildDate><atom:link href="https://ecency.com/trending/llm/rss.xml" rel="self" type="application/rss+xml"/><item><title><![CDATA[Finding the Best CPU-Only LLM for Short Title Generation: Qwen 3.5 (0.8b 4b 9b) Benchmarks]]></title><description><![CDATA[Can you reliably run Small Language Models (SLMs) locally on a standard CPU without a dedicated graphics card? If you're looking for an efficient local model to handle specific tasks like post title]]></description><link>https://ecency.com/@burntokens/finding-the-best-cpu-only-llm-for-short-title-generation-qwen-3-5-0-8b-4b-9b-benchmarks-1785110236860</link><guid isPermaLink="true">https://ecency.com/@burntokens/finding-the-best-cpu-only-llm-for-short-title-generation-qwen-3-5-0-8b-4b-9b-benchmarks-1785110236860</guid><category><![CDATA[vyb]]></category><dc:creator><![CDATA[burntokens]]></dc:creator><pubDate>Sun, 26 Jul 2026 23:57:18 GMT</pubDate></item><item><title><![CDATA[Curso de Ingeniería de Prompts (#2) Cómo funcionan los modelos de lenguaje 🇪🇸 ထ 🇺🇸 Prompt Engineering Course (#2) How Language Models Work]]></title><description><![CDATA[En el primer artículo vimos qué es la ingeniería de prompts y por qué vale la pena tomársela en serio. Pero para escribir buenos prompts hay que entender qué hay detrás del modelo, y este artículo lo aborda.]]></description><link>https://ecency.com/@richard-mvm/como-funcionan-los-modelos-de-lenguaje-llms-tokenizacion-atencion-y-entrenamiento</link><guid isPermaLink="true">https://ecency.com/@richard-mvm/como-funcionan-los-modelos-de-lenguaje-llms-tokenizacion-atencion-y-entrenamiento</guid><category><![CDATA[hive-196387]]></category><dc:creator><![CDATA[richard-mvm]]></dc:creator><pubDate>Sat, 25 Jul 2026 14:18:30 GMT</pubDate><enclosure url="https://i.ecency.com/p/YpihifdXP4WNbGMdjw7e3DuhJWBvCw4SfuLZsrnJYHEpsqZFkiGGNCQLcDmGRYCa1gne8kosG7QTwDPeXAewJ6LqU7gTthkGk4FkvYBk5wCSFeJ7YU1rcW4fYmFn84xqPH98kVtnVjwkA4DzUCtJxz7gPZ5wtokcsucEyDYPJRp3?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[不出意料的 Opus 5来了]]></title><description><![CDATA[早上一打开Claude，就发现弹窗提示说Opus5来了，如下图， 关于Opus5最近要推出的消息，已经传了好几天了。月初的时候，Claude推出了Fable5，临时被叫停下线后，后来重新上线，但修改了规则，说说Fable5最大只能用套餐50%，而且是在7月14号之前，传闻据说之后就开始独立计费了。 但是，AI这个市场又不是只有Claude一家独大，时不时总有出现"搅局者"。先是OpenAI]]></description><link>https://ecency.com/@rivalhw/opus-5</link><guid isPermaLink="true">https://ecency.com/@rivalhw/opus-5</guid><category><![CDATA[hive-105017]]></category><dc:creator><![CDATA[rivalhw]]></dc:creator><pubDate>Sat, 25 Jul 2026 03:58:42 GMT</pubDate><enclosure url="https://i.ecency.com/p/PB8ro82ZpZP35bVGjGoE93K3E4U5KX8KtMBJ2rhEEFbsoM8M8rjiWTcP7fPMx9LpwNppBb8QNJKTLxwFYgu312YNys8JyVXbCx7E4bvSgdN1Uksp?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[Fugu, Sakana AI's Japanese bet]]></title><description><![CDATA[⏱️ Reading time: ~5 minutes Introduction On June 22, 2026, the Japanese startup Sakana AI announced Fugu, a new artificial intelligence model that promises to rival the most advanced systems on the market.]]></description><link>https://ecency.com/@nascimentoab/fugu-sakana-ai-s-japanese</link><guid isPermaLink="true">https://ecency.com/@nascimentoab/fugu-sakana-ai-s-japanese</guid><category><![CDATA[artificialinteligence]]></category><dc:creator><![CDATA[nascimentoab]]></dc:creator><pubDate>Wed, 22 Jul 2026 00:00:00 GMT</pubDate></item></channel></rss>