<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: licjon</title><link>https://news.ycombinator.com/user?id=licjon</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Fri, 03 Jul 2026 08:50:18 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=licjon" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by licjon in "Claude Sonnet 5"]]></title><description><![CDATA[
<p>Is there a router or wrapper that provides a real-time cost estimation for alternative settings? Obviously, you can't predict exact output tokens without running the inference, but a tool that calculates the exact input cost across models and applies a historical average for the output tokens could be useful. Like, you run a task on Sonnet, and it estimates: "Based on your input tokens and a 1:1 output ratio, this would have cost $X on Opus at a low effort level."</p>
]]></description><pubDate>Wed, 01 Jul 2026 11:58:42 +0000</pubDate><link>https://news.ycombinator.com/item?id=48745305</link><dc:creator>licjon</dc:creator><comments>https://news.ycombinator.com/item?id=48745305</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48745305</guid></item><item><title><![CDATA[New comment by licjon in "The case for physical media ownership"]]></title><description><![CDATA[
<p>By not offering a refund, Sony has done damage to the moral superiority claim that pirated media is theft. If they can effectively steal something you bought, then they can't claim the moral high ground, just the fact of legality.</p>
]]></description><pubDate>Sun, 28 Jun 2026 19:12:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=48710482</link><dc:creator>licjon</dc:creator><comments>https://news.ycombinator.com/item?id=48710482</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48710482</guid></item><item><title><![CDATA[New comment by licjon in "Ask HN: How to avoid LLMs struggling with Lisp parens?"]]></title><description><![CDATA[
<p>For common lisp, cl-mcp is great for this (<a href="https://github.com/cl-ai-project/cl-mcp" rel="nofollow">https://github.com/cl-ai-project/cl-mcp</a>). I have not had any parentheses issues while using claude opus and cl-mcp. Other lisp mcps are probably also good, but I can only vouch for cl-mcp.</p>
]]></description><pubDate>Fri, 26 Jun 2026 22:39:25 +0000</pubDate><link>https://news.ycombinator.com/item?id=48692905</link><dc:creator>licjon</dc:creator><comments>https://news.ycombinator.com/item?id=48692905</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48692905</guid></item></channel></rss>