<?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://desktop.ecency.com</link><image><url>https://desktop.ecency.com/logo512.png</url><title>RSS Feed</title><link>https://desktop.ecency.com</link></image><generator>RSS for Node</generator><lastBuildDate>Mon, 16 Nov 2026 22:23:30 GMT</lastBuildDate><atom:link href="https://desktop.ecency.com/created/models/rss.xml" rel="self" type="application/rss+xml"/><item><title><![CDATA[Anthropic shipped one model with two doors, and only one of them opens for you]]></title><description><![CDATA[Hi there, A thousand AI agents built a working operating system from scratch in eight days. That is the story Anthropic told on Monday, when it released Claude Fable 5.2. The agents worked together, wrote]]></description><link>https://desktop.ecency.com/@susmi/anthropic-shipped-one-model-with</link><guid isPermaLink="true">https://desktop.ecency.com/@susmi/anthropic-shipped-one-model-with</guid><category><![CDATA[hive-167922]]></category><dc:creator><![CDATA[susmi]]></dc:creator><pubDate>Wed, 11 Nov 2026 00:38:12 GMT</pubDate><enclosure url="https://i.ecency.com/p/V9N4wevejZUdjxDounRWBciUgsEWE3HnQKenfnJLQZDh1M6fgJynmrtpVKaJVrXH2dTwuo3DDMLXG1frUMK8aJ5zp1Xo3vQpVC4PxTGkC2zZucmj5phRNiYryM2JPrc3RQgzoDTpMDepWEqQwNHgykQdDKJMMXJ2FqaucpXqt7yX9qzmbkeWdmVFF8NqRuap1XQ2JUm6mzf7ZQgkuzbV9?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[Moonshot put a 2.8 trillion parameter model on Hugging Face, and the download alone is 1.56 TB]]></title><description><![CDATA[Good day, Yesterday I wrote about a model called Small, 594 billion parameters, and you still cannot download it. Today I have the opposite story. Moonshot put Kimi K3.1 Pro on Hugging Face on November]]></description><link>https://desktop.ecency.com/@susmi/moonshot-put-a-2-8</link><guid isPermaLink="true">https://desktop.ecency.com/@susmi/moonshot-put-a-2-8</guid><category><![CDATA[hive-167922]]></category><dc:creator><![CDATA[susmi]]></dc:creator><pubDate>Mon, 09 Nov 2026 00:43:21 GMT</pubDate><enclosure url="https://i.ecency.com/p/2r8F9rTBenJQoT6WvCTR8RVMxew81GYxwACEH9qvNc6ktifkToHmffqS5i7xqceBbxMpCaSSY7Sub56s3izN615KbPbW2Yefn2K4RsjtxzapGseJrcMkfrLQsQEK2tJm4?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[A model called Small holds 594 billion parameters, and you still cannot download it]]></title><description><![CDATA[Cover image: AI-generated Hey, A model called Small holds 594 billion parameters. That is the name Thinking Machines Lab gave its new model, Inkling 2 Small. It came out on November 5. Small is the second]]></description><link>https://desktop.ecency.com/@susmi/a-model-called-small-holds</link><guid isPermaLink="true">https://desktop.ecency.com/@susmi/a-model-called-small-holds</guid><category><![CDATA[hive-167922]]></category><dc:creator><![CDATA[susmi]]></dc:creator><pubDate>Sun, 08 Nov 2026 00:40:42 GMT</pubDate><enclosure url="https://i.ecency.com/p/Kz4AvTzHkfLstLhmA7JT35RHJV6mCpRM1XGJ73xCVaswDqEeKcUVkuwcPdNfjbzPcEuN2x5omeQoqQYr2v1oax5hyxNscAGrhHQGSaN65hp3cqxHPF2j9abzK96DDi6UxDG6CCFhVGaVZk8m9HcxJXa3PX8K3Wt3a5Gcz61PPwsrgbj8LnU8Nozzxtj6B1UyRZyUrzBWtPExZYRRY?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[Building Kickback Decepticon Insecticon Blokees Transformer Model]]></title><description><![CDATA[These Blokees figures have definitely grown on me over the years. At first, I was completely against them, who wants a Transformer that doesn't TRANSFORM? Apparenytly I do. This is my first Decepticon]]></description><link>https://desktop.ecency.com/@triverse/building-kickback-deceptico-443</link><guid isPermaLink="true">https://desktop.ecency.com/@triverse/building-kickback-deceptico-443</guid><category><![CDATA[hive-181335]]></category><dc:creator><![CDATA[triverse]]></dc:creator><pubDate>Sat, 07 Nov 2026 12:44:18 GMT</pubDate><enclosure url="https://i.ecency.com/p/GTCx6Xsvc3wLoGm99qTzKqZu2XxCq2QjPFXAUsNtcxNx6PpfxJxv?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[Kakao built a model that refuses to talk, and that is why it is fast]]></title><description><![CDATA[Cover image: AI-generated Good morning, Kakao built a model that refuses to talk. Most models answer you in sentences. This one does not. Kanana-2-v-decide, released on November 6, gives you a number,]]></description><link>https://desktop.ecency.com/@susmi/kakao-built-a-model-that-refuses-to-talk-and-that-is-why-it-is-fast</link><guid isPermaLink="true">https://desktop.ecency.com/@susmi/kakao-built-a-model-that-refuses-to-talk-and-that-is-why-it-is-fast</guid><category><![CDATA[hive-167922]]></category><dc:creator><![CDATA[susmi]]></dc:creator><pubDate>Sat, 07 Nov 2026 00:52:45 GMT</pubDate><enclosure url="https://i.ecency.com/p/cyxkEVqiiLy5WLCfVNWsFwbsPrCojjxgYFsJnuNtFGGEfcjn1j6BWFRw3q9jMAA5DatK4jfrM9bFF3pnvuzCAdjvfojr3QtGG4WKCDQpE7Tfgr8ix7vmidNvoyEbUB9fVEN?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[Baidu released a giant model you cannot talk to yet, and that is the whole point]]></title><description><![CDATA[Cover image: AI-generated Hello there, A giant model you cannot talk to yet. That sounds wrong at first. Baidu released ERNIE 5.5 Flash Base on November 5, and the weights are out there to download. So]]></description><link>https://desktop.ecency.com/@susmi/baidu-released-a-giant-model</link><guid isPermaLink="true">https://desktop.ecency.com/@susmi/baidu-released-a-giant-model</guid><category><![CDATA[hive-167922]]></category><dc:creator><![CDATA[susmi]]></dc:creator><pubDate>Fri, 06 Nov 2026 01:22:33 GMT</pubDate><enclosure url="https://i.ecency.com/p/8SzwQc8j2KJa4cS5mWK9qGuYn7uNSJprgvXqAj6DQLxqMdJ3EQkoCQQ9ungGQZFf7aNQZfty1F4YoQCQcqrC3TokPejBYMJZL4Rw5A8kdaFxqTjyucA?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[Tencent's new Hy4 can see a screen and use a computer, but its open part is still to come]]></title><description><![CDATA[Cover image: AI-generated Hi everyone, Yesterday, Tencent released the full version of its Hy4 model, and the new part is easy to say in plain words. It can now see images, and it can use a computer. The]]></description><link>https://desktop.ecency.com/@susmi/tencent-s-new-hy4-can</link><guid isPermaLink="true">https://desktop.ecency.com/@susmi/tencent-s-new-hy4-can</guid><category><![CDATA[hive-167922]]></category><dc:creator><![CDATA[susmi]]></dc:creator><pubDate>Thu, 05 Nov 2026 01:16:33 GMT</pubDate><enclosure url="https://i.ecency.com/p/PB8ro82ZpZP31VVaPTn6pYcK3aHihgs7qv34LuRqnb1HzkqdXuFezNXLi5eiVkBRmzTosiaYE4EnfpJB2HohAda3uJebt3tVEFTBPakhsEFtiYZt?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[IDW's Megatron Blokees Build a Figure]]></title><description><![CDATA[Fans of Transformers know who Megatron is. This is specifically the IDW Comics version of the famous Decepticon leader. I am not personally familiar with IDW's Transformers comics, I became a fan and stopped]]></description><link>https://desktop.ecency.com/@triverse/idws-megatron-blokees-build-523</link><guid isPermaLink="true">https://desktop.ecency.com/@triverse/idws-megatron-blokees-build-523</guid><category><![CDATA[hive-181335]]></category><dc:creator><![CDATA[triverse]]></dc:creator><pubDate>Wed, 28 Oct 2026 02:27:09 GMT</pubDate><enclosure url="https://i.ecency.com/p/GTCx6Xsvc3wLoGm99qTzKqZu2XxCq2QjPFXAUsNtcxNx6PpfxJxv?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[What is the Model Context Protocol and how does it work?]]></title><description><![CDATA[AI systems become much more useful when they can work with external tools, data sources, and business systems. The challenge is that every new connection can add another custom integration that needs to]]></description><link>https://desktop.ecency.com/@softwareco/what-is-the-model-context</link><guid isPermaLink="true">https://desktop.ecency.com/@softwareco/what-is-the-model-context</guid><category><![CDATA[connecting]]></category><dc:creator><![CDATA[softwareco]]></dc:creator><pubDate>Wed, 30 Sep 2026 14:01:27 GMT</pubDate></item><item><title><![CDATA[Can you run Qwen3.8-Omni-Flash locally? GGUF availability explained]]></title><description><![CDATA[Can Qwen3.8-Omni-Flash actually run locally as a GGUF? The answer isn’t as obvious as the model name makes it sound. Here’s what local AI users need to know. Read the full article on Popular AI]]></description><link>https://desktop.ecency.com/@popularai/can-you-run-qwen38-omni-flash-locally-gguf-availability-explained</link><guid isPermaLink="true">https://desktop.ecency.com/@popularai/can-you-run-qwen38-omni-flash-locally-gguf-availability-explained</guid><category><![CDATA[qwen]]></category><dc:creator><![CDATA[popularai]]></dc:creator><pubDate>Sat, 26 Sep 2026 00:17:00 GMT</pubDate><enclosure url="https://i.ecency.com/p/NTy4GV6ooFRmaCXZ8UYgPhoud1kjiNX8QokLEZtbBKLuLWQ9yt7K3o4S896uvt8XBr4hwpAMa2aBE2UKB7Niudpys82JffosfQbnVUyaAdGktC4LdT3t3CpD4qV2t8951NswAi5xrBVSn94w2svcQFvQqa9pV4mWZBJVQzqC?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[GPT-6 Sol vs. Claude Opus 5.5 for coding]]></title><description><![CDATA[GPT-6 Sol vs. Claude Opus 5.5 looks like a simple coding showdown. It isn't. We compared the tradeoffs that benchmarks alone don't reveal. Read the full article on Popular AI]]></description><link>https://desktop.ecency.com/@popularai/gpt-6-sol-vs-claude-opus-55-for-coding</link><guid isPermaLink="true">https://desktop.ecency.com/@popularai/gpt-6-sol-vs-claude-opus-55-for-coding</guid><category><![CDATA[sol]]></category><dc:creator><![CDATA[popularai]]></dc:creator><pubDate>Fri, 25 Sep 2026 12:01:57 GMT</pubDate><enclosure url="https://i.ecency.com/p/NTy4GV6ooFRmaCXZ8UYgPhoud1kjiNX8QokLEZtbBKLuLWQ9yt7K3o4S896uvt8XBr4hwp9jX1QdMVrFFwfzpULLKpGVKTJW7NynCohGCUwdXY8KV19uQtnZMUmsq2fzBmiAja8cUDnWn9w4jcMBso4vwy9kEhqbj9x7Lr4W?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[DeepSeek reversed its V4 Pro shutdown. Should API users switch to V4.1 Flash?]]></title><description><![CDATA[DeepSeek just reversed its V4 Pro shutdown, but that doesn't make the upgrade decision obvious. V4.1 Flash is cheaper and faster in key workloads, yet the benchmark story has a catch. Read the full article]]></description><link>https://desktop.ecency.com/@popularai/deepseek-reversed-its-v4-pro-shutdown-should-api-users-switch-to-v41-flash</link><guid isPermaLink="true">https://desktop.ecency.com/@popularai/deepseek-reversed-its-v4-pro-shutdown-should-api-users-switch-to-v41-flash</guid><category><![CDATA[deepseek]]></category><dc:creator><![CDATA[popularai]]></dc:creator><pubDate>Sat, 19 Sep 2026 11:29:24 GMT</pubDate><enclosure url="https://i.ecency.com/p/NTy4GV6ooFRmaCXZ8UYgPhoud1kjiNX8QokLEZtbBKLuLWQ9yt7K3o4S896uvt8XBr4hwp9iw5gLgcy1Nf6SCjojTayS56fdMLEsSraqAeQ4MoHVwh7719QsfUTj5PefYRPKunMNa9pUKSpioKes4dZV63YWyVJfg4UubhvN?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[SWE-2 vs Fable 5.1: don’t switch your coding agent yet]]></title><description><![CDATA[SWE-2 is cheaper and suddenly close enough to make premium coding agents uncomfortable. Then one benchmark flips the comparison. Should you switch your coding stack? Read the full article on Popular AI]]></description><link>https://desktop.ecency.com/@popularai/swe-2-vs-fable-51-dont-switch-your-coding-agent-yet</link><guid isPermaLink="true">https://desktop.ecency.com/@popularai/swe-2-vs-fable-51-dont-switch-your-coding-agent-yet</guid><category><![CDATA[fable]]></category><dc:creator><![CDATA[popularai]]></dc:creator><pubDate>Thu, 17 Sep 2026 10:37:18 GMT</pubDate><enclosure url="https://i.ecency.com/p/NTy4GV6ooFRmaCXZ8UYgPhoud1kjiNX8QokLEZtbBKLuLWQ9yt7K3o4S896uvt8XBr4hwp9iKZppmov1gL2fYgkYrzv6HbR3jccvzTmS5QDi78xWY5q3DFje7WeXyWTiyYuhrtmDsuToYE26Q8V44pNbxWf39DQgmXJfqpWz?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[GPT-6 Astra vs GPT-5.6 Sol: when is Astra worth it?]]></title><description><![CDATA[GPT-6 Astra promises more, but the upgrade is not equally valuable for every workload. See where Astra earns the premium, and where GPT-5.6 Sol still makes more sense. Read the full article on Popular]]></description><link>https://desktop.ecency.com/@popularai/gpt-6-astra-vs-gpt-56-sol-when-is-astra-worth-it</link><guid isPermaLink="true">https://desktop.ecency.com/@popularai/gpt-6-astra-vs-gpt-56-sol-when-is-astra-worth-it</guid><category><![CDATA[astra]]></category><dc:creator><![CDATA[popularai]]></dc:creator><pubDate>Mon, 07 Sep 2026 21:41:57 GMT</pubDate><enclosure url="https://i.ecency.com/p/NTy4GV6ooFRmaCXZ8UYgPhoud1kjiNX8QokLEZtbBKLuLWQ9yt7K3o4S896uvt8XBr4hwpAMbAkyg7tfeY5AmbAnJCaxjheNR6NEZHLfsZuUW1noKaJSvqBFdym9CaQ6Be4tDJQrRJ6fkHVWo8yBeqLdo9SKeVpxu2khGVxA?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[NVIDIA is buying Hugging Face. Your local models should not depend on one download button]]></title><description><![CDATA[NVIDIA is buying Hugging Face. Should local AI users start mirroring their models now? The real risk is bigger than one company or one GPU brand. Read the full article on Popular AI]]></description><link>https://desktop.ecency.com/@popularai/nvidia-is-buying-hugging-face-your-local-models-should-not-depend-on-one-download-button</link><guid isPermaLink="true">https://desktop.ecency.com/@popularai/nvidia-is-buying-hugging-face-your-local-models-should-not-depend-on-one-download-button</guid><category><![CDATA[nvidia]]></category><dc:creator><![CDATA[popularai]]></dc:creator><pubDate>Fri, 04 Sep 2026 21:16:15 GMT</pubDate><enclosure url="https://i.ecency.com/p/NTy4GV6ooFRmaCXZ8UYgPhoud1kjiNX8QokLEZtbBKLuLWQ9yt7K3o4S896uvt8XBr4hwp9iw3KVCzRgPRWH8PWnLwh1h4eCWojrxqpT1m9dr9R1Fg7zY1VNZJ4aNXFyLbDtz9tK8o1G46nn9Z5fD5cko8Kf6xcuGCx1mAtN?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[GLM-5.3 weights are still on hold. Should you wait or use GLM-5.2?]]></title><description><![CDATA[GLM-5.3 looks stronger at coding, but its weights are still missing. Should local AI users wait, keep GLM-5.2, or buy hardware now? One key question remains unanswered. Read the full article on Popular]]></description><link>https://desktop.ecency.com/@popularai/glm-53-weights-are-still-on-hold-should-you-wait-or-use-glm-52</link><guid isPermaLink="true">https://desktop.ecency.com/@popularai/glm-53-weights-are-still-on-hold-should-you-wait-or-use-glm-52</guid><category><![CDATA[local]]></category><dc:creator><![CDATA[popularai]]></dc:creator><pubDate>Wed, 26 Aug 2026 23:17:00 GMT</pubDate><enclosure url="https://i.ecency.com/p/NTy4GV6ooFRmaCXZ8UYgPhoud1kjiNX8QokLEZtbBKLuLWQ9yt7K3o4S896uvt8XBr4hwp9j5UWUb1r2Dh2CFTjs8fp5y8JZ1rwKa4WiKPfFf8A2AtAZKrxZXudxmciWfAACid5cGijyLGirmhk52FDyJ6P4PXgEqKK72xnr?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[Meta Muse Glimmer: what one GPU really means for local AI]]></title><description><![CDATA[Meta Muse Glimmer puts a provocative question in front of local AI users: what does “one GPU” actually buy you? The answer comes with a catch. Read the full article on Popular AI]]></description><link>https://desktop.ecency.com/@popularai/meta-muse-glimmer-what-one-gpu-really-means-for-local-ai</link><guid isPermaLink="true">https://desktop.ecency.com/@popularai/meta-muse-glimmer-what-one-gpu-really-means-for-local-ai</guid><category><![CDATA[meta]]></category><dc:creator><![CDATA[popularai]]></dc:creator><pubDate>Fri, 14 Aug 2026 12:08:48 GMT</pubDate><enclosure url="https://i.ecency.com/p/NTy4GV6ooFRmaCXZ8UYgPhoud1kjiNX8QokLEZtbBKLuLWQ9yt7K3o4S896uvt8XBr4hwpAMMCjduAmDRXFcZXj8wD2kqSK38Z9dNehTFyyRaW4XNaf2bGuLUCqDmjN6RySsi9xqBrA6j4mR64xkDd2sRHfUYPXtZYZXJ3pr?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[Qwen3.8-Max is live with great capabilities for coding]]></title><description><![CDATA[These days I hear a lot about so many models that are coming up with great features. I guess in the future because of the competition between different AI companies, the end users will end up getting some]]></description><link>https://desktop.ecency.com/@bala41288/qwen3-8-max-is-live</link><guid isPermaLink="true">https://desktop.ecency.com/@bala41288/qwen3-8-max-is-live</guid><category><![CDATA[hive-197685]]></category><dc:creator><![CDATA[bala41288]]></dc:creator><pubDate>Wed, 05 Aug 2026 19:02:54 GMT</pubDate><enclosure url="https://i.ecency.com/p/4PYjjVwJ1UdtK8eF6rs5argWKHu1x4LBcCvCQuw7D7ovzjeGVVVSYYH5hNWgXAYhaywF9SqyXLaiZ17oGWMW4gSY3VXmfWE5FT2VJ6JQjR8?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[Data privacy during our AI interactions]]></title><description><![CDATA[AI world is very competitive. Once upon a time, ChatGPT was the only AI that was very popular. Even today, that is the case, and there are still people who go to ChatGPT for their first need. But things]]></description><link>https://desktop.ecency.com/@bala41288/data-privacy-during-our-ai</link><guid isPermaLink="true">https://desktop.ecency.com/@bala41288/data-privacy-during-our-ai</guid><category><![CDATA[hive-197685]]></category><dc:creator><![CDATA[bala41288]]></dc:creator><pubDate>Mon, 03 Aug 2026 20:18:33 GMT</pubDate><enclosure url="https://i.ecency.com/p/4PYjjVwJ1UdtK8eF6rs5argWKHu1x4LBcBnXWHTEX25WfMhWFgEGybomxjbgcUvZdMqTUJDXFobiKgaQCyxhRURfYVWhYxBbVtuk56QYmnW?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[Why specialized AI models still beat benchmark kings]]></title><description><![CDATA[AI benchmark leaders look unbeatable. In real workflows, smaller specialized models can still win. The reason exposes what public leaderboards fail to measure. #AI]]></description><link>https://desktop.ecency.com/@popularai/why-specialized-ai-models-still-beat-benchmark-kings</link><guid isPermaLink="true">https://desktop.ecency.com/@popularai/why-specialized-ai-models-still-beat-benchmark-kings</guid><category><![CDATA[specialized]]></category><dc:creator><![CDATA[popularai]]></dc:creator><pubDate>Wed, 15 Jul 2026 15:28:36 GMT</pubDate><enclosure url="https://i.ecency.com/p/NTy4GV6ooFRmaCXZ8UYgPhoud1kjiNX8QokLEZtbBKLuLWQ9yt7K3o4S896uvt8XBr4hwp9jhLJa9fVZG6njUE7TMzr87QGmmd9Yv3kTaGob1rWHy7nLV5gztDESxSbzf5RCzjSyZLmLZZyjweENbFDEQxsuTLWCrNaDFkTg?format=match&amp;mode=fit" length="0" type="false"/></item></channel></rss>