<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: rsalus</title><link>https://news.ycombinator.com/user?id=rsalus</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 28 May 2026 21:09:51 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=rsalus" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by rsalus in "I think Anthropic and OpenAI have found product-market fit"]]></title><description><![CDATA[
<p>they need to make 5t-10t back, but not necessarily through selling tokens. as we can see, the frontier labs are making vertically integrated products. their revenue is no longer strictly tied to inference.</p>
]]></description><pubDate>Thu, 28 May 2026 02:04:28 +0000</pubDate><link>https://news.ycombinator.com/item?id=48303465</link><dc:creator>rsalus</dc:creator><comments>https://news.ycombinator.com/item?id=48303465</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48303465</guid></item><item><title><![CDATA[New comment by rsalus in "Archaeologists find Egyptian mummy buried with the 'Iliad'"]]></title><description><![CDATA[
<p>often times the classical Greeks + Romans would cite their family lineage using works of Homer and other poets</p>
]]></description><pubDate>Thu, 21 May 2026 02:57:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=48217293</link><dc:creator>rsalus</dc:creator><comments>https://news.ycombinator.com/item?id=48217293</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48217293</guid></item><item><title><![CDATA[New comment by rsalus in "Ask HN: What are you working on? (May 2026)"]]></title><description><![CDATA[
<p><a href="https://github.com/lvlup-sw/exarchos" rel="nofollow">https://github.com/lvlup-sw/exarchos</a><p>It's an SDLC workflow harness for agents. Instead of using skills to encode my typical workflows (e.g., create PRD, then create plan using TDD, then dispatch subagents, etc) I've built a concurrent event-sourced process manager to handle it.</p>
]]></description><pubDate>Mon, 11 May 2026 00:27:07 +0000</pubDate><link>https://news.ycombinator.com/item?id=48089645</link><dc:creator>rsalus</dc:creator><comments>https://news.ycombinator.com/item?id=48089645</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48089645</guid></item><item><title><![CDATA[New comment by rsalus in "Principles for agent-native CLIs"]]></title><description><![CDATA[
<p>not really.. I never understand the inclination to be reductive. the patterns emerging can be fairly novel.</p>
]]></description><pubDate>Fri, 08 May 2026 02:35:00 +0000</pubDate><link>https://news.ycombinator.com/item?id=48057812</link><dc:creator>rsalus</dc:creator><comments>https://news.ycombinator.com/item?id=48057812</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48057812</guid></item><item><title><![CDATA[New comment by rsalus in "Principles for agent-native CLIs"]]></title><description><![CDATA[
<p>agree, although the pattern I've been following is to provide a self-contained CLI for portability and usability purposes, and then an "mcp" subcommand which launches an MCP server over stdio. ultimately the "CLI" and "MCP" surfaces act as thin facades over the same functional layer.</p>
]]></description><pubDate>Fri, 08 May 2026 02:31:54 +0000</pubDate><link>https://news.ycombinator.com/item?id=48057792</link><dc:creator>rsalus</dc:creator><comments>https://news.ycombinator.com/item?id=48057792</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48057792</guid></item><item><title><![CDATA[New comment by rsalus in "Principles for agent-native CLIs"]]></title><description><![CDATA[
<p>the real solution is to simply provide hints in responses so that the model may self-correct, e.g., recommended next actions, describe commands to get schema definitions, etc.</p>
]]></description><pubDate>Fri, 08 May 2026 02:28:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=48057770</link><dc:creator>rsalus</dc:creator><comments>https://news.ycombinator.com/item?id=48057770</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48057770</guid></item><item><title><![CDATA[New comment by rsalus in "Commenting and approving pull requests"]]></title><description><![CDATA[
<p>100p agree. Most code reviews devolve to nitpicking anyway. I think it's much more valuable for teammates to review the _design_ and _intent_ rather than the explicit artifacts.</p>
]]></description><pubDate>Sat, 25 Apr 2026 19:42:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=47903972</link><dc:creator>rsalus</dc:creator><comments>https://news.ycombinator.com/item?id=47903972</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47903972</guid></item><item><title><![CDATA[New comment by rsalus in "The AI Layoff Trap"]]></title><description><![CDATA[
<p>Great paper.<p>> If AI displaces human workers faster than the economy can reabsorb them<p>Big if.</p>
]]></description><pubDate>Mon, 13 Apr 2026 06:27:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=47748330</link><dc:creator>rsalus</dc:creator><comments>https://news.ycombinator.com/item?id=47748330</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47748330</guid></item><item><title><![CDATA[New comment by rsalus in "Chrome DevTools MCP"]]></title><description><![CDATA[
<p>mostly by virtue of being a common standard. MCP servers are primarily useful in a remote environment, where centralized management of cross-cutting concerns matters. also its really useful for integrating existing distributed services, e.g., internal data lakes.<p>I think it's clear a self-describing CLI is optimal for local-first tooling and portability. I personally view remote MCP servers as complementary in the space.</p>
]]></description><pubDate>Sun, 15 Mar 2026 23:44:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=47393321</link><dc:creator>rsalus</dc:creator><comments>https://news.ycombinator.com/item?id=47393321</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47393321</guid></item><item><title><![CDATA[New comment by rsalus in "Chrome DevTools MCP (2025)"]]></title><description><![CDATA[
<p>that's a pretty interesting idea. It would be nice if there was such a standard. the approach I'm taking right now: a CLI that accepts structured JSON as input, with an 
'mcp' subcommand that starts a stdio server. I bundle a 'help' command with a 'describe' action for self-service guidance scoped to a particular feature/tool.</p>
]]></description><pubDate>Sun, 15 Mar 2026 23:19:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=47393091</link><dc:creator>rsalus</dc:creator><comments>https://news.ycombinator.com/item?id=47393091</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47393091</guid></item><item><title><![CDATA[New comment by rsalus in "Chrome DevTools MCP (2025)"]]></title><description><![CDATA[
<p>yes, but clis thus need self-service commands to provide guidance, and their responses need to be optimized for consumption by agents. in a sense, this is the same sort of context tax that MCP servers incur. so in my view cli and MCP are complementary tools; one is not strictly superior over the other.</p>
]]></description><pubDate>Sun, 15 Mar 2026 23:15:47 +0000</pubDate><link>https://news.ycombinator.com/item?id=47393067</link><dc:creator>rsalus</dc:creator><comments>https://news.ycombinator.com/item?id=47393067</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47393067</guid></item><item><title><![CDATA[New comment by rsalus in "Chrome DevTools MCP (2025)"]]></title><description><![CDATA[
<p>MCP is very much not dead. centralized remote MCP servers are incredibly useful. also bespoke CLIs still require guidance for models to use effectively, so it's clear that token efficiency is still an issue regardless.</p>
]]></description><pubDate>Sun, 15 Mar 2026 21:37:46 +0000</pubDate><link>https://news.ycombinator.com/item?id=47392222</link><dc:creator>rsalus</dc:creator><comments>https://news.ycombinator.com/item?id=47392222</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47392222</guid></item><item><title><![CDATA[New comment by rsalus in "Show HN: Reviving a 20-year-old puzzle game Chromatron with Ghidra and AI"]]></title><description><![CDATA[
<p>Doubtful.</p>
]]></description><pubDate>Mon, 09 Mar 2026 09:36:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=47306737</link><dc:creator>rsalus</dc:creator><comments>https://news.ycombinator.com/item?id=47306737</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47306737</guid></item><item><title><![CDATA[New comment by rsalus in "Ask HN: What Are You Working On? (March 2026)"]]></title><description><![CDATA[
<p>what does devarch do exactly? why not OSS?</p>
]]></description><pubDate>Mon, 09 Mar 2026 04:31:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=47304907</link><dc:creator>rsalus</dc:creator><comments>https://news.ycombinator.com/item?id=47304907</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47304907</guid></item></channel></rss>