<?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 Surya Maddula on Medium]]></title>
        <description><![CDATA[Stories by Surya Maddula on Medium]]></description>
        <link>https://medium.com/@suryamaddula?source=rss-389694b05f12------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*inZ99EV4Y4EHb6Q8LmMHwQ.jpeg</url>
            <title>Stories by Surya Maddula on Medium</title>
            <link>https://medium.com/@suryamaddula?source=rss-389694b05f12------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Thu, 19 Nov 2026 13:49:37 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@suryamaddula/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[Developing Sophisticated Controllable Agents with RAG.]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://pub.towardsai.net/developing-sophisticated-controllable-agents-with-rag-727f28828815?source=rss-389694b05f12------2"><img src="https://cdn-images-1.medium.com/max/1672/1*2Nth5ujXg2CeRFiKDVsYMA.png" width="1672"></a></p><p class="medium-feed-snippet">How to move past one-shot retrieval and build agents that grade their own evidence, rewrite their own questions, and catch themselves&#x2026;</p><p class="medium-feed-link"><a href="https://pub.towardsai.net/developing-sophisticated-controllable-agents-with-rag-727f28828815?source=rss-389694b05f12------2">Continue reading on Towards AI »</a></p></div>]]></description>
            <link>https://pub.towardsai.net/developing-sophisticated-controllable-agents-with-rag-727f28828815?source=rss-389694b05f12------2</link>
            <guid isPermaLink="false">https://medium.com/p/727f28828815</guid>
            <category><![CDATA[retrieval-augmented-gen]]></category>
            <category><![CDATA[generative-ai]]></category>
            <category><![CDATA[agents]]></category>
            <category><![CDATA[llm]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <dc:creator><![CDATA[Surya Maddula]]></dc:creator>
            <pubDate>Sun, 04 Oct 2026 14:01:02 GMT</pubDate>
            <atom:updated>2026-10-04T14:01:02.283Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[How Do Modern LLMs Cheat the Scaling Laws? (In a Good Way).]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://pub.towardsai.net/how-do-modern-llms-cheat-the-scaling-laws-in-a-good-way-bbdf875c81dc?source=rss-389694b05f12------2"><img src="https://cdn-images-1.medium.com/max/600/0*7iaAWZzynR3o9ehv.png" width="600"></a></p><p class="medium-feed-snippet">If you&#x2019;ve been following LLMs closely, you&#x2019;ve probably noticed a pattern: parameter counts explode, GPU bills explode, but inference still&#x2026;</p><p class="medium-feed-link"><a href="https://pub.towardsai.net/how-do-modern-llms-cheat-the-scaling-laws-in-a-good-way-bbdf875c81dc?source=rss-389694b05f12------2">Continue reading on Towards AI »</a></p></div>]]></description>
            <link>https://pub.towardsai.net/how-do-modern-llms-cheat-the-scaling-laws-in-a-good-way-bbdf875c81dc?source=rss-389694b05f12------2</link>
            <guid isPermaLink="false">https://medium.com/p/bbdf875c81dc</guid>
            <category><![CDATA[llm]]></category>
            <category><![CDATA[deep-learning]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[transformers]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <dc:creator><![CDATA[Surya Maddula]]></dc:creator>
            <pubDate>Wed, 20 May 2026 15:01:03 GMT</pubDate>
            <atom:updated>2026-05-20T15:01:03.048Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[OpenClaw Responses Are Better Than LLMs. Is Memory the Only Difference?]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://pub.towardsai.net/openclaw-responses-are-better-than-llms-is-memory-the-only-difference-dee43aaa9c77?source=rss-389694b05f12------2"><img src="https://cdn-images-1.medium.com/max/1636/1*kxvuAvHQR4vqRTGpmQuxrQ.jpeg" width="1636"></a></p><p class="medium-feed-snippet">OpenClaw responses can be &#x201C;better&#x201D; than raw LLM chat responses. That makes sense, even though OpenClaw&#x2019;s rather newer compared to any&#x2026;</p><p class="medium-feed-link"><a href="https://pub.towardsai.net/openclaw-responses-are-better-than-llms-is-memory-the-only-difference-dee43aaa9c77?source=rss-389694b05f12------2">Continue reading on Towards AI »</a></p></div>]]></description>
            <link>https://pub.towardsai.net/openclaw-responses-are-better-than-llms-is-memory-the-only-difference-dee43aaa9c77?source=rss-389694b05f12------2</link>
            <guid isPermaLink="false">https://medium.com/p/dee43aaa9c77</guid>
            <category><![CDATA[ai-agent]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[openclaw]]></category>
            <category><![CDATA[algorithms]]></category>
            <category><![CDATA[llm]]></category>
            <dc:creator><![CDATA[Surya Maddula]]></dc:creator>
            <pubDate>Fri, 27 Feb 2026 15:01:02 GMT</pubDate>
            <atom:updated>2026-02-27T15:01:02.032Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Agentic Engineering: Humans as Orchestrators, not Coders.]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://pub.towardsai.net/agentic-engineering-humans-as-orchestrators-not-coders-601d015d9c9e?source=rss-389694b05f12------2"><img src="https://cdn-images-1.medium.com/max/2528/0*1LerY4sr9k7w91Yg.jpg" width="2528"></a></p><p class="medium-feed-snippet">Andrej Karpathy coined &#x201C;vibe coding&#x201D; in February 2025. In February 2026, he proposed &#x201C;agentic engineering&#x201D;. Should we take him seriously?</p><p class="medium-feed-link"><a href="https://pub.towardsai.net/agentic-engineering-humans-as-orchestrators-not-coders-601d015d9c9e?source=rss-389694b05f12------2">Continue reading on Towards AI »</a></p></div>]]></description>
            <link>https://pub.towardsai.net/agentic-engineering-humans-as-orchestrators-not-coders-601d015d9c9e?source=rss-389694b05f12------2</link>
            <guid isPermaLink="false">https://medium.com/p/601d015d9c9e</guid>
            <category><![CDATA[llm]]></category>
            <category><![CDATA[ai-agent]]></category>
            <category><![CDATA[data-engineering]]></category>
            <category><![CDATA[software-engineering]]></category>
            <category><![CDATA[vibe-coding]]></category>
            <dc:creator><![CDATA[Surya Maddula]]></dc:creator>
            <pubDate>Sat, 14 Feb 2026 14:01:01 GMT</pubDate>
            <atom:updated>2026-02-14T14:01:01.726Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[I got early access to Tinker’s API, here’s what happened.]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://suryamaddula.medium.com/i-got-early-access-to-tinkers-api-here-s-what-happened-fb0cec1f5ef8?source=rss-389694b05f12------2"><img src="https://cdn-images-1.medium.com/max/2000/0*Ieq8UaT6ONC2NADX.png" width="2000"></a></p><p class="medium-feed-snippet">I Spent Seven Weeks Building Real Systems with Tinker. Here&#x2019;s What Actually Happened.</p><p class="medium-feed-link"><a href="https://suryamaddula.medium.com/i-got-early-access-to-tinkers-api-here-s-what-happened-fb0cec1f5ef8?source=rss-389694b05f12------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://suryamaddula.medium.com/i-got-early-access-to-tinkers-api-here-s-what-happened-fb0cec1f5ef8?source=rss-389694b05f12------2</link>
            <guid isPermaLink="false">https://medium.com/p/fb0cec1f5ef8</guid>
            <category><![CDATA[evaluation]]></category>
            <category><![CDATA[fine-tuning]]></category>
            <category><![CDATA[ai]]></category>
            <category><![CDATA[llm]]></category>
            <category><![CDATA[api]]></category>
            <dc:creator><![CDATA[Surya Maddula]]></dc:creator>
            <pubDate>Fri, 06 Feb 2026 11:27:05 GMT</pubDate>
            <atom:updated>2026-02-06T11:27:05.181Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Starving yourself is unproductive, but what happens when you starve your LLMs…of context?]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://pub.towardsai.net/starving-yourself-is-unproductive-but-what-happens-when-you-starve-your-llms-of-context-fd051fc2b19c?source=rss-389694b05f12------2"><img src="https://cdn-images-1.medium.com/max/2382/1*UQnRtdcfl_e4kIFag88QfQ.png" width="2382"></a></p><p class="medium-feed-snippet">Starving your LLMs might be the key to contextual prompt reduction.</p><p class="medium-feed-link"><a href="https://pub.towardsai.net/starving-yourself-is-unproductive-but-what-happens-when-you-starve-your-llms-of-context-fd051fc2b19c?source=rss-389694b05f12------2">Continue reading on Towards AI »</a></p></div>]]></description>
            <link>https://pub.towardsai.net/starving-yourself-is-unproductive-but-what-happens-when-you-starve-your-llms-of-context-fd051fc2b19c?source=rss-389694b05f12------2</link>
            <guid isPermaLink="false">https://medium.com/p/fd051fc2b19c</guid>
            <category><![CDATA[prompt-engineering]]></category>
            <category><![CDATA[llm]]></category>
            <category><![CDATA[context-engineering]]></category>
            <category><![CDATA[nlp]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <dc:creator><![CDATA[Surya Maddula]]></dc:creator>
            <pubDate>Sat, 03 Jan 2026 00:02:51 GMT</pubDate>
            <atom:updated>2026-01-03T00:02:51.241Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[The Math Behind Ghibli-Fication.]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://pub.towardsai.net/the-math-behind-ghibli-fication-df528d94f45e?source=rss-389694b05f12------2"><img src="https://cdn-images-1.medium.com/max/1536/1*A1PYWeG0b3e346qAeRHYsA.png" width="1536"></a></p><p class="medium-feed-link"><a href="https://pub.towardsai.net/the-math-behind-ghibli-fication-df528d94f45e?source=rss-389694b05f12------2">Continue reading on Towards AI »</a></p></div>]]></description>
            <link>https://pub.towardsai.net/the-math-behind-ghibli-fication-df528d94f45e?source=rss-389694b05f12------2</link>
            <guid isPermaLink="false">https://medium.com/p/df528d94f45e</guid>
            <category><![CDATA[chatgpt]]></category>
            <category><![CDATA[mathematics]]></category>
            <category><![CDATA[genai]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[architecture]]></category>
            <dc:creator><![CDATA[Surya Maddula]]></dc:creator>
            <pubDate>Mon, 31 Mar 2025 12:02:11 GMT</pubDate>
            <atom:updated>2025-03-31T16:38:28.957Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Feedback Loop Mechanisms in Retrieval Systems]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://pub.towardsai.net/feedback-loop-mechanisms-in-retrieval-systems-c9377157c538?source=rss-389694b05f12------2"><img src="https://cdn-images-1.medium.com/max/2600/1*RfVrOxzmxJamOqv-Q4oyWA.png" width="3756"></a></p><p class="medium-feed-snippet">Overview: Examine systems that learn from user interactions to enhance future retrievals through feedback loops.</p><p class="medium-feed-link"><a href="https://pub.towardsai.net/feedback-loop-mechanisms-in-retrieval-systems-c9377157c538?source=rss-389694b05f12------2">Continue reading on Towards AI »</a></p></div>]]></description>
            <link>https://pub.towardsai.net/feedback-loop-mechanisms-in-retrieval-systems-c9377157c538?source=rss-389694b05f12------2</link>
            <guid isPermaLink="false">https://medium.com/p/c9377157c538</guid>
            <category><![CDATA[ai]]></category>
            <category><![CDATA[fine-tuning]]></category>
            <category><![CDATA[information-retrieval]]></category>
            <category><![CDATA[large-language-models]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <dc:creator><![CDATA[Surya Maddula]]></dc:creator>
            <pubDate>Sun, 24 Nov 2024 14:02:11 GMT</pubDate>
            <atom:updated>2024-11-24T14:02:11.048Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Combining Multiple Retrieval Models for Robust Results: RAPTOR]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://pub.towardsai.net/combining-multiple-retrieval-models-for-robust-results-raptor-e26c20dee164?source=rss-389694b05f12------2"><img src="https://cdn-images-1.medium.com/max/2600/1*BYQW6fH9IdOqPId8rvEl8w.png" width="3744"></a></p><p class="medium-feed-link"><a href="https://pub.towardsai.net/combining-multiple-retrieval-models-for-robust-results-raptor-e26c20dee164?source=rss-389694b05f12------2">Continue reading on Towards AI »</a></p></div>]]></description>
            <link>https://pub.towardsai.net/combining-multiple-retrieval-models-for-robust-results-raptor-e26c20dee164?source=rss-389694b05f12------2</link>
            <guid isPermaLink="false">https://medium.com/p/e26c20dee164</guid>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[processing]]></category>
            <category><![CDATA[information-retrieval]]></category>
            <category><![CDATA[retrieval-augmented-gen]]></category>
            <category><![CDATA[raptor]]></category>
            <dc:creator><![CDATA[Surya Maddula]]></dc:creator>
            <pubDate>Sun, 20 Oct 2024 12:02:26 GMT</pubDate>
            <atom:updated>2024-10-21T17:02:39.853Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Not RAG, but RAG Fusion? Understanding Next-Gen Info Retrieval.]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://pub.towardsai.net/not-rag-but-rag-fusion-understanding-next-gen-info-retrieval-477788da02e2?source=rss-389694b05f12------2"><img src="https://cdn-images-1.medium.com/max/2600/1*0ZhcUq7wNBEwkbgxpC3t9A.png" width="3456"></a></p><p class="medium-feed-snippet">AI and Natural Language Processing are advancing at an incredible pace, and now more than ever, we need better and more RELIABLE ways to&#x2026;</p><p class="medium-feed-link"><a href="https://pub.towardsai.net/not-rag-but-rag-fusion-understanding-next-gen-info-retrieval-477788da02e2?source=rss-389694b05f12------2">Continue reading on Towards AI »</a></p></div>]]></description>
            <link>https://pub.towardsai.net/not-rag-but-rag-fusion-understanding-next-gen-info-retrieval-477788da02e2?source=rss-389694b05f12------2</link>
            <guid isPermaLink="false">https://medium.com/p/477788da02e2</guid>
            <category><![CDATA[retrieval-augmented-gen]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[large-language-models]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[nlp]]></category>
            <dc:creator><![CDATA[Surya Maddula]]></dc:creator>
            <pubDate>Sun, 22 Sep 2024 20:02:00 GMT</pubDate>
            <atom:updated>2024-10-01T15:21:26.225Z</atom:updated>
        </item>
    </channel>
</rss>