<?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" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Stories by Rubentak on Medium]]></title>
        <description><![CDATA[Stories by Rubentak on Medium]]></description>
        <link>https://medium.com/@rubentak?source=rss-5fed38c5e824------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*LO26s83qp70ip9hyrRyW1A.jpeg</url>
            <title>Stories by Rubentak on Medium</title>
            <link>https://medium.com/@rubentak?source=rss-5fed38c5e824------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Mon, 18 May 2026 03:00:33 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@rubentak/feed" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com" rel="hub"/>
        <item>
            <title><![CDATA[Chunking Methods, Fundamental Concepts for RAG Applications]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@rubentak/chunking-methods-fundamental-concepts-for-rag-applications-080c1083da05?source=rss-5fed38c5e824------2"><img src="https://cdn-images-1.medium.com/max/1832/0*MA55e7JlgZUiRwp0.png" width="1832"></a></p><p class="medium-feed-snippet">In this series of articles, I will explain fundamental concepts and best practices for RAG applications. Specifically about chunking</p><p class="medium-feed-link"><a href="https://medium.com/@rubentak/chunking-methods-fundamental-concepts-for-rag-applications-080c1083da05?source=rss-5fed38c5e824------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@rubentak/chunking-methods-fundamental-concepts-for-rag-applications-080c1083da05?source=rss-5fed38c5e824------2</link>
            <guid isPermaLink="false">https://medium.com/p/080c1083da05</guid>
            <category><![CDATA[vector-database]]></category>
            <category><![CDATA[chunking]]></category>
            <category><![CDATA[retrieval-augmented]]></category>
            <category><![CDATA[ai]]></category>
            <category><![CDATA[data-processing]]></category>
            <dc:creator><![CDATA[Rubentak]]></dc:creator>
            <pubDate>Mon, 04 Mar 2024 13:46:16 GMT</pubDate>
            <atom:updated>2024-03-04T13:46:16.838Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Talk to your files in a local RAG application using Mistral 7B, LangChain  and Chroma DB (No…]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@rubentak/talk-to-your-files-in-a-local-rag-application-using-mistral-7b-langchain-and-chroma-db-no-2b4ba77358e0?source=rss-5fed38c5e824------2"><img src="https://cdn-images-1.medium.com/max/2600/1*-0ROJw3TW0-06m7QckWlPQ.png" width="2732"></a></p><p class="medium-feed-snippet">I will show how you can use the Mistral 7B model on your local machine to talk to your personal files in a Chroma vector database</p><p class="medium-feed-link"><a href="https://medium.com/@rubentak/talk-to-your-files-in-a-local-rag-application-using-mistral-7b-langchain-and-chroma-db-no-2b4ba77358e0?source=rss-5fed38c5e824------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@rubentak/talk-to-your-files-in-a-local-rag-application-using-mistral-7b-langchain-and-chroma-db-no-2b4ba77358e0?source=rss-5fed38c5e824------2</link>
            <guid isPermaLink="false">https://medium.com/p/2b4ba77358e0</guid>
            <category><![CDATA[chromadb]]></category>
            <category><![CDATA[langchain]]></category>
            <category><![CDATA[mistral-ai]]></category>
            <category><![CDATA[llm]]></category>
            <category><![CDATA[rag-application]]></category>
            <dc:creator><![CDATA[Rubentak]]></dc:creator>
            <pubDate>Tue, 24 Oct 2023 20:24:25 GMT</pubDate>
            <atom:updated>2023-10-24T20:24:25.184Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Mistral 7B : The best 7 billion parameter LLM yet.]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@rubentak/mistral-7b-the-best-7-billion-parameter-llm-yet-8b0aa03016f9?source=rss-5fed38c5e824------2"><img src="https://cdn-images-1.medium.com/max/1600/1*RKOLVh6n57TyZeimo8FNOw.jpeg" width="1600"></a></p><p class="medium-feed-snippet">Mistral 7B is the best open-source 7B parameter LLM to date. It can be run locally and online using Ollama.</p><p class="medium-feed-link"><a href="https://medium.com/@rubentak/mistral-7b-the-best-7-billion-parameter-llm-yet-8b0aa03016f9?source=rss-5fed38c5e824------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@rubentak/mistral-7b-the-best-7-billion-parameter-llm-yet-8b0aa03016f9?source=rss-5fed38c5e824------2</link>
            <guid isPermaLink="false">https://medium.com/p/8b0aa03016f9</guid>
            <category><![CDATA[llama-2]]></category>
            <category><![CDATA[ollama]]></category>
            <category><![CDATA[langchain]]></category>
            <category><![CDATA[mistral-7b]]></category>
            <category><![CDATA[mistral-ai]]></category>
            <dc:creator><![CDATA[Rubentak]]></dc:creator>
            <pubDate>Mon, 16 Oct 2023 20:40:15 GMT</pubDate>
            <atom:updated>2023-10-17T09:09:59.860Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Employ a team of GPT-4 AI agents with ChatDev: build an application in only one prompt]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@rubentak/employ-a-team-of-gpt-4-ai-agents-with-chatdev-build-an-application-in-only-one-prompt-361b3b012fb9?source=rss-5fed38c5e824------2"><img src="https://cdn-images-1.medium.com/max/2600/1*2CA_9w1xfM7ALB_f9ZhEAQ.png" width="3675"></a></p><p class="medium-feed-snippet">How I was able with a team of AI agents to make an app using only one prompt!</p><p class="medium-feed-link"><a href="https://medium.com/@rubentak/employ-a-team-of-gpt-4-ai-agents-with-chatdev-build-an-application-in-only-one-prompt-361b3b012fb9?source=rss-5fed38c5e824------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@rubentak/employ-a-team-of-gpt-4-ai-agents-with-chatdev-build-an-application-in-only-one-prompt-361b3b012fb9?source=rss-5fed38c5e824------2</link>
            <guid isPermaLink="false">https://medium.com/p/361b3b012fb9</guid>
            <category><![CDATA[llm]]></category>
            <category><![CDATA[ai-agent]]></category>
            <category><![CDATA[gpt-4]]></category>
            <category><![CDATA[ai-tools]]></category>
            <category><![CDATA[chatdev]]></category>
            <dc:creator><![CDATA[Rubentak]]></dc:creator>
            <pubDate>Wed, 11 Oct 2023 10:53:08 GMT</pubDate>
            <atom:updated>2023-10-11T10:53:08.843Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Open Interpreter: Get GPT-4  and LLama 2 to run code on your computer ]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@rubentak/open-interpreter-get-gpt-4-and-llama-2-to-run-code-on-your-computer-c21471c5f918?source=rss-5fed38c5e824------2"><img src="https://cdn-images-1.medium.com/max/2600/1*YyEF28xpCoAfA1wMbO7eZQ.png" width="2732"></a></p><p class="medium-feed-snippet">How I made a stock price analysis using only one command in my terminal.</p><p class="medium-feed-link"><a href="https://medium.com/@rubentak/open-interpreter-get-gpt-4-and-llama-2-to-run-code-on-your-computer-c21471c5f918?source=rss-5fed38c5e824------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@rubentak/open-interpreter-get-gpt-4-and-llama-2-to-run-code-on-your-computer-c21471c5f918?source=rss-5fed38c5e824------2</link>
            <guid isPermaLink="false">https://medium.com/p/c21471c5f918</guid>
            <category><![CDATA[openai]]></category>
            <category><![CDATA[ai-tools]]></category>
            <category><![CDATA[llama-2]]></category>
            <category><![CDATA[code-llama]]></category>
            <category><![CDATA[gpt-4]]></category>
            <dc:creator><![CDATA[Rubentak]]></dc:creator>
            <pubDate>Sun, 08 Oct 2023 17:10:43 GMT</pubDate>
            <atom:updated>2023-10-08T17:10:43.810Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[A deep dive into Deep Learning: Recurrent Neural Networks]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@rubentak/a-deep-dive-into-deep-learning-recurrent-neural-networks-f5f0e38ecfe8?source=rss-5fed38c5e824------2"><img src="https://cdn-images-1.medium.com/max/2600/1*CdKCI8vwlKaOz1Tax9GDWg.png" width="2732"></a></p><p class="medium-feed-snippet">This article was co-written by Oanottage and Gabriel Renn&#xF3;.</p><p class="medium-feed-link"><a href="https://medium.com/@rubentak/a-deep-dive-into-deep-learning-recurrent-neural-networks-f5f0e38ecfe8?source=rss-5fed38c5e824------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@rubentak/a-deep-dive-into-deep-learning-recurrent-neural-networks-f5f0e38ecfe8?source=rss-5fed38c5e824------2</link>
            <guid isPermaLink="false">https://medium.com/p/f5f0e38ecfe8</guid>
            <category><![CDATA[ai]]></category>
            <category><![CDATA[time-series-analysis]]></category>
            <category><![CDATA[forcasting]]></category>
            <category><![CDATA[recurrent-neural-network]]></category>
            <category><![CDATA[deep-learning]]></category>
            <dc:creator><![CDATA[Rubentak]]></dc:creator>
            <pubDate>Mon, 18 Sep 2023 17:01:00 GMT</pubDate>
            <atom:updated>2023-09-18T17:01:00.307Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Demystifying AI: How It’s Transforming Businesses Today]]></title>
            <link>https://medium.com/@rubentak/demystifying-ai-how-its-transforming-businesses-today-563ca775511e?source=rss-5fed38c5e824------2</link>
            <guid isPermaLink="false">https://medium.com/p/563ca775511e</guid>
            <category><![CDATA[chatgpt]]></category>
            <category><![CDATA[business]]></category>
            <category><![CDATA[business-transformation]]></category>
            <category><![CDATA[innovation]]></category>
            <category><![CDATA[ai]]></category>
            <dc:creator><![CDATA[Rubentak]]></dc:creator>
            <pubDate>Thu, 07 Sep 2023 12:07:25 GMT</pubDate>
            <atom:updated>2023-09-07T21:16:07.196Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*2QvQV_oCEnsow2XSbCLPtw.png" /></figure><p>If you find yourself scrolling on LinkedIn or any other social media platform it is almost impossible to have missed the hype that the term “AI” has had in the past year. After ChatGPT was released to the public in November 2022, the general public got in contact with the result of the breakthroughs in AI development over the past couple of years.</p><p>Large Language Models (or short LLMs) are large computational models that are revolutionising the way we interact with large computational models. LLMs are a type of Artificial Intelligence (AI) that can mimic human intelligence. They are trained on massive datasets of text and code and can be used to perform a variety of tasks, such as generating text, translating languages, and writing different kinds of creative content. ChatGPT and Google’s Bard model are two examples of this.</p><p>When people talk about AI, they often refer to LLMs. These AI models can apart from helping you summarise a long body of text, it can also help with a lot of your business processes. LLMs are already being used by businesses in a variety of ways, and their potential impact is only going to grow in the future. A few examples of how AI can transform your businesses today are:</p><h4><strong>Customer service</strong></h4><p>LLMs can be used to create chatbots that can answer customer questions and resolve issues. This can free up human customer service agents to focus on more complex tasks, and it can also provide customers with 24/7 support. It is not so advanced that the customer service department can be completely replaced, but it is getting more advanced every day.</p><h4><strong>Marketing</strong></h4><p>One can also use LLMs to generate personalised marketing content that is relevant to each individual customer. This can help businesses to improve their conversion rates and customer loyalty. Think for instance of an AI that creates a plan for a new marketing campaign based on the data from former campaigns. When an AI model has enough data about your customers, personalised emails and messages are only seconds away.</p><h4><strong>Product development</strong></h4><p>The use of LLMs can also be used to gather feedback from customers and identify new product opportunities. This can help businesses to develop products that meet the needs of their customers and stay ahead of the competition. Based on for instance the data gathered from surveys, an LLM can quickly extract critical information and make a summary from what was being said. This can save tons of time in regards to analysing the data and speed up the development process of your product.</p><h4><strong>Financial services</strong></h4><p>AI can be utilised to analyse financial data and make predictions about future trends. This can help businesses to make better investment decisions and manage their risk. Think for instance of a financial report that can be automated or a recommendation system that suggests your next step based on your current financial situation.</p><h4><strong>Content creation</strong></h4><p>LLMs can be used to create content for a variety of purposes, such as blog posts, articles, and social media posts. This can help businesses to save time and money, and it can also help them to produce high-quality content that is engaging and informative. When you are starting a company or want to create more engagement on your social media platforms, AI can be a very helpful tool to help you increase the engagement of (potential) customers.</p><h4>Fraud Detection and Security</h4><p>With AI, businesses can better protect themselves from fraud and security threats. AI systems watch over transactions and user actions, quickly spotting anything unusual that might be a sign of fraud. This helps keep a company’s money safe and maintains trust with customers. AI learns from new ways that bad actors try to cause harm, so it’s like having a security guard that’s always learning and getting better. While it can’t replace humans completely yet, AI is getting smarter every day at stopping cybercrime.</p><h4>Process Automation</h4><p>AI-powered automation is like having a helper that does repetitive tasks quickly and accurately. It can handle jobs like organizing data, managing supplies, or answering customer questions, which saves time and money. This also reduces the chances of mistakes made by humans. With AI doing these routine tasks, employees can focus on more important and creative work. AI systems can adapt to changes and learn from data, making them valuable for keeping a business agile and competitive. While it doesn’t replace humans entirely, AI-driven automation is becoming a key part of making businesses run smoothly and keep customers happy.</p><h4>Research and development</h4><p>Not only can AI help you create things, but LLMs also can be used to research new topics and develop new ideas. This can help businesses to stay ahead of the competition and identify new opportunities. Think for instance of an AI helping you in a brainstorming session with your team. Several AI models nowadays can also help you do market research, saving you a lot of time and energy, and saving you the money of hiring an agency to do this market research for you.</p><h3>Conclusion</h3><p>These are just a few examples of how LLMs are transforming businesses today. As LLMs continue to develop, their potential impact is only going to grow. Businesses that are able to adopt LLMs early will be well-positioned to succeed in the future.</p><p>It is important to note that AI is not a wonder pill for your business (or at least not yet). You still need to guide the processes and see if the output of your models is right and of the desired quality. The output data can only be as good as the input data. AI is a rapidly evolving field of technology and great advances are being made every day.</p><p>If you have any ideas for your business on how you would like to make use of this advancing technology and outcompete your competitors, contact us. We are here to empower you with the possibilities that AI creates.</p><p>And remember:</p><blockquote>AI will not replace your business, but another business using AI will. — AI</blockquote><h4>Note</h4><p>I recently founded a Data and AI consultancy RSLT agency. If you have any ideas for your business on how you would like to make use of this advancing technology and outcompete your competitors, contact me. We are here to empower you with the possibilities that AI creates.</p><ul><li><a href="https://rslt.agency/">https://rslt.agency/</a></li><li><a href="https://www.linkedin.com/company/96695171/admin/feed/posts/">https://www.linkedin.com/company/96695171/admin/feed/posts/</a></li></ul><p><a href="https://rslt.agency/">RSLT AI &amp; Data</a></p><p>Also, be sure to follow me on GitHub and LinkedIn. If you like the work that I’m doing you could buy me a coffee:</p><ul><li><a href="https://github.com/rubentak">https://github.com/rubentak</a></li><li><a href="https://www.linkedin.com/in/ruben-tak-665b66194/">https://www.linkedin.com/in/ruben-tak-665b66194/</a></li><li><a href="https://www.buymeacoffee.com/rubentak">https://www.buymeacoffee.com/rubentak</a></li></ul><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=563ca775511e" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Deep Learning and Convolutional Neural Networks]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@rubentak/deep-learning-and-convolutional-neural-networks-6cdccc458a7?source=rss-5fed38c5e824------2"><img src="https://cdn-images-1.medium.com/max/2600/1*mTmDYdSn1c4DsqwV15pN4g.png" width="2732"></a></p><p class="medium-feed-snippet">In this article, we will go into the realm of Deep Learning with Convolutional Neural Networks.</p><p class="medium-feed-link"><a href="https://medium.com/@rubentak/deep-learning-and-convolutional-neural-networks-6cdccc458a7?source=rss-5fed38c5e824------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@rubentak/deep-learning-and-convolutional-neural-networks-6cdccc458a7?source=rss-5fed38c5e824------2</link>
            <guid isPermaLink="false">https://medium.com/p/6cdccc458a7</guid>
            <category><![CDATA[ai]]></category>
            <category><![CDATA[deep-learning]]></category>
            <category><![CDATA[neural-networks]]></category>
            <category><![CDATA[computer-vision]]></category>
            <category><![CDATA[convolutional-network]]></category>
            <dc:creator><![CDATA[Rubentak]]></dc:creator>
            <pubDate>Fri, 25 Aug 2023 14:39:11 GMT</pubDate>
            <atom:updated>2023-08-25T14:51:45.784Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[How does an AI learn? Training Neural Networks with Backpropagation]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@rubentak/how-does-an-ai-learn-training-neural-networks-with-backpropagation-a8b89d8bf330?source=rss-5fed38c5e824------2"><img src="https://cdn-images-1.medium.com/max/2600/1*m_R7tLOHKi_H1t59fswpOw.png" width="2732"></a></p><p class="medium-feed-snippet">In this article, I will explain how AI&#x2019;s learn and how to oprimise your NN. Topics are backpropagation, gradient decent and regularisation</p><p class="medium-feed-link"><a href="https://medium.com/@rubentak/how-does-an-ai-learn-training-neural-networks-with-backpropagation-a8b89d8bf330?source=rss-5fed38c5e824------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@rubentak/how-does-an-ai-learn-training-neural-networks-with-backpropagation-a8b89d8bf330?source=rss-5fed38c5e824------2</link>
            <guid isPermaLink="false">https://medium.com/p/a8b89d8bf330</guid>
            <category><![CDATA[backpropagation]]></category>
            <category><![CDATA[training]]></category>
            <category><![CDATA[neural-networks]]></category>
            <category><![CDATA[regularization]]></category>
            <category><![CDATA[ai]]></category>
            <dc:creator><![CDATA[Rubentak]]></dc:creator>
            <pubDate>Sun, 13 Aug 2023 18:17:57 GMT</pubDate>
            <atom:updated>2023-08-13T18:17:57.986Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Understanding Feed Forward Neural Networks with MNIST Dataset]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@rubentak/understanding-feed-forward-neural-networks-with-mnist-dataset-b92df52a05bc?source=rss-5fed38c5e824------2"><img src="https://cdn-images-1.medium.com/max/2600/1*jM3MGjen3YfB2_MxPh1Hmg.png" width="2732"></a></p><p class="medium-feed-snippet">We&#x2019;re going to explore Feed Forward Neural Networks. No fancy jargon, just a down-to-earth exploration of what they are and how they work.</p><p class="medium-feed-link"><a href="https://medium.com/@rubentak/understanding-feed-forward-neural-networks-with-mnist-dataset-b92df52a05bc?source=rss-5fed38c5e824------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@rubentak/understanding-feed-forward-neural-networks-with-mnist-dataset-b92df52a05bc?source=rss-5fed38c5e824------2</link>
            <guid isPermaLink="false">https://medium.com/p/b92df52a05bc</guid>
            <category><![CDATA[neural-networks]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[mnist]]></category>
            <category><![CDATA[ai]]></category>
            <category><![CDATA[classification]]></category>
            <dc:creator><![CDATA[Rubentak]]></dc:creator>
            <pubDate>Wed, 02 Aug 2023 15:33:13 GMT</pubDate>
            <atom:updated>2023-08-13T16:16:45.872Z</atom:updated>
        </item>
    </channel>
</rss>