<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: inspectorSlap</title><link>https://news.ycombinator.com/user?id=inspectorSlap</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 09 Jul 2026 04:43:34 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=inspectorSlap" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by inspectorSlap in "Grok 4.5"]]></title><description><![CDATA[
<p>Has anyone actually used Grok to code? How does he do?</p>
]]></description><pubDate>Thu, 09 Jul 2026 00:04:12 +0000</pubDate><link>https://news.ycombinator.com/item?id=48839134</link><dc:creator>inspectorSlap</dc:creator><comments>https://news.ycombinator.com/item?id=48839134</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48839134</guid></item><item><title><![CDATA[New comment by inspectorSlap in "Automating AI Away"]]></title><description><![CDATA[
<p>This is exactly right. Abstracted out of the process, or to a point of most optimal application.</p>
]]></description><pubDate>Tue, 07 Jul 2026 19:02:27 +0000</pubDate><link>https://news.ycombinator.com/item?id=48822109</link><dc:creator>inspectorSlap</dc:creator><comments>https://news.ycombinator.com/item?id=48822109</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48822109</guid></item><item><title><![CDATA[New comment by inspectorSlap in "Automating AI Away"]]></title><description><![CDATA[
<p>I find some of the most interesting, and catastrophic failures in my agent fine-tuning come from the clamping down of non-determinism.  It is totally the correct approach, but must be handled delicately.  The non-deterministic core remains, but now under bimodal pressure.</p>
]]></description><pubDate>Tue, 07 Jul 2026 18:55:26 +0000</pubDate><link>https://news.ycombinator.com/item?id=48822022</link><dc:creator>inspectorSlap</dc:creator><comments>https://news.ycombinator.com/item?id=48822022</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48822022</guid></item><item><title><![CDATA[New comment by inspectorSlap in "What Emily Bender meant by "stochastic parrots""]]></title><description><![CDATA[
<p>I think stochastic parroting is really a very accurate description of what they do (if underserving of the overall usefulness of LLMs).  As long as you consider they are parroting from the whole of human intelligence.  Its just that as they have gotten more sophisticated, the amount of gates, guardrails, and tertiary tools add variety.  Trace any LLM hallucination back to provenance and you begin to see how the stochastic parrot works.</p>
]]></description><pubDate>Mon, 06 Jul 2026 16:29:29 +0000</pubDate><link>https://news.ycombinator.com/item?id=48806925</link><dc:creator>inspectorSlap</dc:creator><comments>https://news.ycombinator.com/item?id=48806925</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48806925</guid></item></channel></rss>