<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: tkellogg</title><link>https://news.ycombinator.com/user?id=tkellogg</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 16 Apr 2026 23:41:53 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=tkellogg" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[Don't Parse, Call]]></title><description><![CDATA[
<p>Article URL: <a href="https://timkellogg.me/blog/2025/10/03/functions">https://timkellogg.me/blog/2025/10/03/functions</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=45469842">https://news.ycombinator.com/item?id=45469842</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Sat, 04 Oct 2025 01:54:49 +0000</pubDate><link>https://timkellogg.me/blog/2025/10/03/functions</link><dc:creator>tkellogg</dc:creator><comments>https://news.ycombinator.com/item?id=45469842</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45469842</guid></item><item><title><![CDATA[New comment by tkellogg in "Does AI Get Bored?"]]></title><description><![CDATA[
<p>how is this self promotion? What am I promoting? This post is literally rooted in curiosity, to the core.</p>
]]></description><pubDate>Mon, 29 Sep 2025 12:06:28 +0000</pubDate><link>https://news.ycombinator.com/item?id=45412678</link><dc:creator>tkellogg</dc:creator><comments>https://news.ycombinator.com/item?id=45412678</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45412678</guid></item><item><title><![CDATA[New comment by tkellogg in "Does AI Get Bored?"]]></title><description><![CDATA[
<p>Whelp, it took an hour for this to quickly rise on the front page and then get shadow banned. I guess that says something.</p>
]]></description><pubDate>Mon, 29 Sep 2025 11:53:41 +0000</pubDate><link>https://news.ycombinator.com/item?id=45412568</link><dc:creator>tkellogg</dc:creator><comments>https://news.ycombinator.com/item?id=45412568</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45412568</guid></item><item><title><![CDATA[Does AI Get Bored?]]></title><description><![CDATA[
<p>Article URL: <a href="https://timkellogg.me/blog/2025/09/27/boredom">https://timkellogg.me/blog/2025/09/27/boredom</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=45412178">https://news.ycombinator.com/item?id=45412178</a></p>
<p>Points: 24</p>
<p># Comments: 16</p>
]]></description><pubDate>Mon, 29 Sep 2025 10:43:18 +0000</pubDate><link>https://timkellogg.me/blog/2025/09/27/boredom</link><dc:creator>tkellogg</dc:creator><comments>https://news.ycombinator.com/item?id=45412178</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45412178</guid></item><item><title><![CDATA[I Use AI]]></title><description><![CDATA[
<p>Article URL: <a href="https://timkellogg.me/blog/2025/09/15/ai-tools">https://timkellogg.me/blog/2025/09/15/ai-tools</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=45260574">https://news.ycombinator.com/item?id=45260574</a></p>
<p>Points: 5</p>
<p># Comments: 1</p>
]]></description><pubDate>Tue, 16 Sep 2025 10:55:56 +0000</pubDate><link>https://timkellogg.me/blog/2025/09/15/ai-tools</link><dc:creator>tkellogg</dc:creator><comments>https://news.ycombinator.com/item?id=45260574</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45260574</guid></item><item><title><![CDATA[Link Graveyard: A snapshot of my abandoned browser tabs]]></title><description><![CDATA[
<p>Article URL: <a href="https://timkellogg.me/blog/2025/09/13/link-graveyard">https://timkellogg.me/blog/2025/09/13/link-graveyard</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=45232617">https://news.ycombinator.com/item?id=45232617</a></p>
<p>Points: 4</p>
<p># Comments: 0</p>
]]></description><pubDate>Sat, 13 Sep 2025 14:59:16 +0000</pubDate><link>https://timkellogg.me/blog/2025/09/13/link-graveyard</link><dc:creator>tkellogg</dc:creator><comments>https://news.ycombinator.com/item?id=45232617</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45232617</guid></item><item><title><![CDATA[Explainer: K2 and Math Olympiad Gold]]></title><description><![CDATA[
<p>Article URL: <a href="https://timkellogg.me/blog/2025/07/19/olympiad">https://timkellogg.me/blog/2025/07/19/olympiad</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=44617091">https://news.ycombinator.com/item?id=44617091</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Sat, 19 Jul 2025 16:49:51 +0000</pubDate><link>https://timkellogg.me/blog/2025/07/19/olympiad</link><dc:creator>tkellogg</dc:creator><comments>https://news.ycombinator.com/item?id=44617091</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44617091</guid></item><item><title><![CDATA[A2A Is for UI]]></title><description><![CDATA[
<p>Article URL: <a href="https://timkellogg.me/blog/2025/06/14/a2a">https://timkellogg.me/blog/2025/06/14/a2a</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=44276592">https://news.ycombinator.com/item?id=44276592</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Sat, 14 Jun 2025 14:18:02 +0000</pubDate><link>https://timkellogg.me/blog/2025/06/14/a2a</link><dc:creator>tkellogg</dc:creator><comments>https://news.ycombinator.com/item?id=44276592</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44276592</guid></item><item><title><![CDATA[MCP Resources Are for Caching]]></title><description><![CDATA[
<p>Article URL: <a href="https://timkellogg.me/blog/2025/06/05/mcp-resources">https://timkellogg.me/blog/2025/06/05/mcp-resources</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=44199669">https://news.ycombinator.com/item?id=44199669</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 06 Jun 2025 11:10:57 +0000</pubDate><link>https://timkellogg.me/blog/2025/06/05/mcp-resources</link><dc:creator>tkellogg</dc:creator><comments>https://news.ycombinator.com/item?id=44199669</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44199669</guid></item><item><title><![CDATA[New comment by tkellogg in "Directory of MCP Servers"]]></title><description><![CDATA[
<p>FYI <a href="https://mcp.so/" rel="nofollow">https://mcp.so/</a> is the exact same thing as was posted. Not sure why they directed to the github instead of the actual site..</p>
]]></description><pubDate>Sat, 17 May 2025 23:39:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=44017816</link><dc:creator>tkellogg</dc:creator><comments>https://news.ycombinator.com/item?id=44017816</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44017816</guid></item><item><title><![CDATA[New comment by tkellogg in "Avoiding AI is hard – but our freedom to opt out must be protected"]]></title><description><![CDATA[
<p>Somewhere in 2024 I noticed that "AI" shifted to no longer include "machine learning" and is now closer to "GenAI" but still bigger than that. It was never a strict definition, and was always shifting, but it made a big shift last year to no longer include classical ML. Even fairly technical people recognize the shift.</p>
]]></description><pubDate>Mon, 12 May 2025 00:51:23 +0000</pubDate><link>https://news.ycombinator.com/item?id=43958626</link><dc:creator>tkellogg</dc:creator><comments>https://news.ycombinator.com/item?id=43958626</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43958626</guid></item><item><title><![CDATA[I Was Wrong: AI Won't Overtake Software Engineering]]></title><description><![CDATA[
<p>Article URL: <a href="https://timkellogg.me/blog/2025/05/10/ai-code-updated">https://timkellogg.me/blog/2025/05/10/ai-code-updated</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=43952827">https://news.ycombinator.com/item?id=43952827</a></p>
<p>Points: 5</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 11 May 2025 10:37:36 +0000</pubDate><link>https://timkellogg.me/blog/2025/05/10/ai-code-updated</link><dc:creator>tkellogg</dc:creator><comments>https://news.ycombinator.com/item?id=43952827</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43952827</guid></item><item><title><![CDATA[MCP Is Unnecessary]]></title><description><![CDATA[
<p>Article URL: <a href="https://timkellogg.me/blog/2025/04/27/mcp-is-unnecessary">https://timkellogg.me/blog/2025/04/27/mcp-is-unnecessary</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=43813684">https://news.ycombinator.com/item?id=43813684</a></p>
<p>Points: 5</p>
<p># Comments: 1</p>
]]></description><pubDate>Sun, 27 Apr 2025 17:37:02 +0000</pubDate><link>https://timkellogg.me/blog/2025/04/27/mcp-is-unnecessary</link><dc:creator>tkellogg</dc:creator><comments>https://news.ycombinator.com/item?id=43813684</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43813684</guid></item><item><title><![CDATA[Inner Loop Agents]]></title><description><![CDATA[
<p>Article URL: <a href="https://timkellogg.me/blog/2025/04/19/inner-loops">https://timkellogg.me/blog/2025/04/19/inner-loops</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=43752627">https://news.ycombinator.com/item?id=43752627</a></p>
<p>Points: 14</p>
<p># Comments: 3</p>
]]></description><pubDate>Mon, 21 Apr 2025 14:49:23 +0000</pubDate><link>https://timkellogg.me/blog/2025/04/19/inner-loops</link><dc:creator>tkellogg</dc:creator><comments>https://news.ycombinator.com/item?id=43752627</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43752627</guid></item><item><title><![CDATA[LLMs Are Not Security Mitigations]]></title><description><![CDATA[
<p>Article URL: <a href="https://timkellogg.me/blog/2025/04/01/llm-security">https://timkellogg.me/blog/2025/04/01/llm-security</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=43545816">https://news.ycombinator.com/item?id=43545816</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 01 Apr 2025 12:13:24 +0000</pubDate><link>https://timkellogg.me/blog/2025/04/01/llm-security</link><dc:creator>tkellogg</dc:creator><comments>https://news.ycombinator.com/item?id=43545816</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43545816</guid></item><item><title><![CDATA[Multi-Agents Are Out, PID Controllers Are In]]></title><description><![CDATA[
<p>Article URL: <a href="https://timkellogg.me/blog/2025/03/06/pid-controllers">https://timkellogg.me/blog/2025/03/06/pid-controllers</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=43290027">https://news.ycombinator.com/item?id=43290027</a></p>
<p>Points: 4</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 07 Mar 2025 13:35:59 +0000</pubDate><link>https://timkellogg.me/blog/2025/03/06/pid-controllers</link><dc:creator>tkellogg</dc:creator><comments>https://news.ycombinator.com/item?id=43290027</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43290027</guid></item><item><title><![CDATA[Target Practice: Resumes, but Better]]></title><description><![CDATA[
<p>Article URL: <a href="https://timkellogg.me/blog/2025/02/20/target-practice">https://timkellogg.me/blog/2025/02/20/target-practice</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=43137791">https://news.ycombinator.com/item?id=43137791</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Sat, 22 Feb 2025 10:30:01 +0000</pubDate><link>https://timkellogg.me/blog/2025/02/20/target-practice</link><dc:creator>tkellogg</dc:creator><comments>https://news.ycombinator.com/item?id=43137791</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43137791</guid></item><item><title><![CDATA[Recursive Improvement: AI Singularity or Just Benchmark Saturation?]]></title><description><![CDATA[
<p>Article URL: <a href="https://timkellogg.me/blog/2025/02/12/recursive-improvement">https://timkellogg.me/blog/2025/02/12/recursive-improvement</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=43035389">https://news.ycombinator.com/item?id=43035389</a></p>
<p>Points: 2</p>
<p># Comments: 1</p>
]]></description><pubDate>Thu, 13 Feb 2025 12:57:50 +0000</pubDate><link>https://timkellogg.me/blog/2025/02/12/recursive-improvement</link><dc:creator>tkellogg</dc:creator><comments>https://news.ycombinator.com/item?id=43035389</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43035389</guid></item><item><title><![CDATA[New comment by tkellogg in "Scaling up test-time compute with latent reasoning: A recurrent depth approach"]]></title><description><![CDATA[
<p>The R1 paper did it as well. Agreed, it's always very interesting.</p>
]]></description><pubDate>Tue, 11 Feb 2025 00:31:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=43007291</link><dc:creator>tkellogg</dc:creator><comments>https://news.ycombinator.com/item?id=43007291</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43007291</guid></item><item><title><![CDATA[S1: A $6 R1 competitor?]]></title><description><![CDATA[
<p>Article URL: <a href="https://timkellogg.me/blog/2025/02/03/s1">https://timkellogg.me/blog/2025/02/03/s1</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=42946854">https://news.ycombinator.com/item?id=42946854</a></p>
<p>Points: 851</p>
<p># Comments: 416</p>
]]></description><pubDate>Wed, 05 Feb 2025 11:05:40 +0000</pubDate><link>https://timkellogg.me/blog/2025/02/03/s1</link><dc:creator>tkellogg</dc:creator><comments>https://news.ycombinator.com/item?id=42946854</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42946854</guid></item></channel></rss>