<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: michaelashley29</title><link>https://news.ycombinator.com/user?id=michaelashley29</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 29 Jul 2026 03:21:43 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=michaelashley29" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by michaelashley29 in "France to ditch Windows for Linux to reduce reliance on US tech"]]></title><description><![CDATA[
<p>been a long time coming for windows. wonder who else will follow suit</p>
]]></description><pubDate>Fri, 10 Apr 2026 12:17:00 +0000</pubDate><link>https://news.ycombinator.com/item?id=47716950</link><dc:creator>michaelashley29</dc:creator><comments>https://news.ycombinator.com/item?id=47716950</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47716950</guid></item><item><title><![CDATA[New comment by michaelashley29 in "We've raised $17M to build what comes after Git"]]></title><description><![CDATA[
<p>I feel like we’re over-capitalizing a problem that could be solved with better protocols. If the "Git successor" is just a wrapper to help agents not hallucinate their own worktrees, it feels like a very expensive solution to a context-window management problem.</p>
]]></description><pubDate>Fri, 10 Apr 2026 11:39:36 +0000</pubDate><link>https://news.ycombinator.com/item?id=47716596</link><dc:creator>michaelashley29</dc:creator><comments>https://news.ycombinator.com/item?id=47716596</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47716596</guid></item><item><title><![CDATA[New comment by michaelashley29 in "I still prefer MCP over skills"]]></title><description><![CDATA[
<p>100%
MCPs truly give the agent tools and allow the agent to make better informed decisions given you can have configured the right MCP tools. Skills are good for knowledge and general guidelines. They give context to the agent, and I have seen some skills being excessively long that could into eat into the context window of the agent.
This tool <a href="https://protomcp.io/" rel="nofollow">https://protomcp.io/</a> helps a lot with testing MCP servers before integrating into the agent workflow. You can even see the agent call different tools in real time and view the trace.</p>
]]></description><pubDate>Fri, 10 Apr 2026 06:54:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=47714492</link><dc:creator>michaelashley29</dc:creator><comments>https://news.ycombinator.com/item?id=47714492</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47714492</guid></item><item><title><![CDATA[New comment by michaelashley29 in "System Card: Claude Mythos Preview [pdf]"]]></title><description><![CDATA[
<p>What’s the expected cost-efficiency? With the current pricing gap between Sonnet and Opus, the biggest factor for adoption (if up for adoption) will be where Mythos lands on the price-per-token scale</p>
]]></description><pubDate>Wed, 08 Apr 2026 05:29:55 +0000</pubDate><link>https://news.ycombinator.com/item?id=47685699</link><dc:creator>michaelashley29</dc:creator><comments>https://news.ycombinator.com/item?id=47685699</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47685699</guid></item><item><title><![CDATA[New comment by michaelashley29 in "Issue: Claude Code is unusable for complex engineering tasks with Feb updates"]]></title><description><![CDATA[
<p>i beg to differ. compaction happens alot for me, and at some point the output becomes extremely nonsensical</p>
]]></description><pubDate>Tue, 07 Apr 2026 13:29:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=47675093</link><dc:creator>michaelashley29</dc:creator><comments>https://news.ycombinator.com/item?id=47675093</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47675093</guid></item><item><title><![CDATA[New comment by michaelashley29 in "Are We Idiocracy Yet?"]]></title><description><![CDATA[
<p>is it just me learning that donald trump is a wwe hall of famer??!</p>
]]></description><pubDate>Tue, 07 Apr 2026 11:06:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=47673343</link><dc:creator>michaelashley29</dc:creator><comments>https://news.ycombinator.com/item?id=47673343</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47673343</guid></item><item><title><![CDATA[New comment by michaelashley29 in "How to use a Claude Subscription in Cursor without paying for API tokens"]]></title><description><![CDATA[
<p>Love the ingenuity here, but man, this feels like an easy way to get banned. Anthropic’s telemetry is going to see those atypical request patterns through a tunnel and probably flag it. Definitely cool for a side project, but I wouldn't risk my main Pro account on it.</p>
]]></description><pubDate>Thu, 02 Apr 2026 11:19:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=47612880</link><dc:creator>michaelashley29</dc:creator><comments>https://news.ycombinator.com/item?id=47612880</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47612880</guid></item><item><title><![CDATA[New comment by michaelashley29 in "Most Claude Code advice is measurably wrong"]]></title><description><![CDATA[
<p>Insightful. I remember back in the day, mentioning "Think hard" would trigger the agent to actually analyze more and give a better output XD</p>
]]></description><pubDate>Thu, 02 Apr 2026 10:45:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=47612573</link><dc:creator>michaelashley29</dc:creator><comments>https://news.ycombinator.com/item?id=47612573</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47612573</guid></item><item><title><![CDATA[New comment by michaelashley29 in "100 Prisoners Problem"]]></title><description><![CDATA[
<p>Coolest variation of this: If the prisoners have a spy (like a friendly warden) who is allowed to enter the room first and swap the contents of just two boxes, the prisoners' survival probability jumps from 31% to 100%.<p>By swapping two items, the spy can break any cycle longer than 50 into two smaller cycles. Since every prisoner is then guaranteed to be on a loop of length 50 or less, everyone is mathematically certain to find their number.</p>
]]></description><pubDate>Thu, 02 Apr 2026 10:38:46 +0000</pubDate><link>https://news.ycombinator.com/item?id=47612524</link><dc:creator>michaelashley29</dc:creator><comments>https://news.ycombinator.com/item?id=47612524</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47612524</guid></item></channel></rss>