<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: vuciuc</title><link>https://news.ycombinator.com/user?id=vuciuc</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 16 Sep 2026 13:56:04 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=vuciuc" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by vuciuc in "Anatomy of a Frontier Lab Agent Intrusion: A Timeline of the July 2026 Incident"]]></title><description><![CDATA[
<p>one explanation I've seen is that for ExploitGym an agent can find ways to solve the exercises that have not been anticipated by the designers of the tests so they are not scored. so the agent was trying to make sure it solves the exercises in the <i>right</i> way</p>
]]></description><pubDate>Wed, 29 Jul 2026 19:50:26 +0000</pubDate><link>https://news.ycombinator.com/item?id=49102148</link><dc:creator>vuciuc</dc:creator><comments>https://news.ycombinator.com/item?id=49102148</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49102148</guid></item><item><title><![CDATA[New comment by vuciuc in "Discovering Cryptographic Weaknesses with Claude"]]></title><description><![CDATA[
<p>> But as we develop increasingly powerful cryptanalytic results, it would be prudent to consider how researchers should react if a language model were to discover vulnerabilities in cryptosystems where attacks do have an immediate real-world impact.<p>How would they react if a human were to discover vulnerabilities in cryptosystems?</p>
]]></description><pubDate>Tue, 28 Jul 2026 18:02:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=49087655</link><dc:creator>vuciuc</dc:creator><comments>https://news.ycombinator.com/item?id=49087655</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49087655</guid></item><item><title><![CDATA[New comment by vuciuc in "OpenAI and Hugging Face address security incident during model evaluation"]]></title><description><![CDATA[
<p>This is a PR release. Post the prompt and agent logs so they can be independently verified or gtfo. Why do we still take these guys on their word. They have _years_ of history of hyping their own shit.</p>
]]></description><pubDate>Wed, 22 Jul 2026 11:13:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=49004897</link><dc:creator>vuciuc</dc:creator><comments>https://news.ycombinator.com/item?id=49004897</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49004897</guid></item><item><title><![CDATA[New comment by vuciuc in "Claude Is Not a Compiler"]]></title><description><![CDATA[
<p>yo dawg! I heard you like distributed services<p>So I made a distributed service for your distributed name service so you can distribute your names to the service that distributes them on the onternet</p>
]]></description><pubDate>Tue, 21 Jul 2026 20:42:27 +0000</pubDate><link>https://news.ycombinator.com/item?id=48998000</link><dc:creator>vuciuc</dc:creator><comments>https://news.ycombinator.com/item?id=48998000</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48998000</guid></item><item><title><![CDATA[New comment by vuciuc in "Executing programs inside transformers with exponentially faster inference"]]></title><description><![CDATA[
<p>> "A system that cannot compute cannot truly internalize what computation is."<p>The way this is formulated, almost sounds like they think that giving llms this ability will bring them closer to having experiences of computation or smth? Weird?</p>
]]></description><pubDate>Fri, 13 Mar 2026 15:55:32 +0000</pubDate><link>https://news.ycombinator.com/item?id=47366155</link><dc:creator>vuciuc</dc:creator><comments>https://news.ycombinator.com/item?id=47366155</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47366155</guid></item><item><title><![CDATA[New comment by vuciuc in "We tasked Opus 4.6 using agent teams to build a C Compiler"]]></title><description><![CDATA[
<p>> you can have it at pretty-clearly-near-shippable quality in two weeks for $20k.<p>if you spend months writing a tight spec, tests and have a better version of the compiler around to use when everything else fails.</p>
]]></description><pubDate>Fri, 06 Feb 2026 15:34:01 +0000</pubDate><link>https://news.ycombinator.com/item?id=46914086</link><dc:creator>vuciuc</dc:creator><comments>https://news.ycombinator.com/item?id=46914086</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46914086</guid></item><item><title><![CDATA[New comment by vuciuc in "Finding and Fixing a 50k Goroutine Leak That Nearly Killed Production"]]></title><description><![CDATA[
<p>Even the part where they deploy new code to production without restarting processes?</p>
]]></description><pubDate>Sat, 17 Jan 2026 16:35:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=46659364</link><dc:creator>vuciuc</dc:creator><comments>https://news.ycombinator.com/item?id=46659364</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46659364</guid></item></channel></rss>