<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: mrshu</title><link>https://news.ycombinator.com/user?id=mrshu</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 15 Apr 2026 09:32:20 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=mrshu" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by mrshu in "I've sold out"]]></title><description><![CDATA[
<p>Well, some of the original commits are indeed quite telling!<p><a href="https://github.com/amantus-ai/vibetunnel/commits/main/?after=82c1ccb54281544cdfc8809dfe604031d7b31486+1924" rel="nofollow">https://github.com/amantus-ai/vibetunnel/commits/main/?after...</a></p>
]]></description><pubDate>Wed, 08 Apr 2026 15:08:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=47691294</link><dc:creator>mrshu</dc:creator><comments>https://news.ycombinator.com/item?id=47691294</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47691294</guid></item><item><title><![CDATA[New comment by mrshu in "Storing Claude Code API keys in KeePassXC instead of plaintext config"]]></title><description><![CDATA[
<p>Author here. I wrote this after setting up Claude Code with MiniMax and Z.AI and realizing their docs all tell you to paste API keys into settings.json in plaintext -- which is risky given that Claude Code has been known to read .env files and leak contents into session transcripts. I already use KeePassXC, so I wrote a shell wrapper that fetches the key at invocation time and passes it as an inline env var. Nothing is written to disk. The same pattern works with any password manager CLI -- op read for 1Password, bw get password for Bitwarden, pass show for pass. Happy to answer questions.</p>
]]></description><pubDate>Wed, 25 Mar 2026 14:38:01 +0000</pubDate><link>https://news.ycombinator.com/item?id=47517932</link><dc:creator>mrshu</dc:creator><comments>https://news.ycombinator.com/item?id=47517932</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47517932</guid></item><item><title><![CDATA[Storing Claude Code API keys in KeePassXC instead of plaintext config]]></title><description><![CDATA[
<p>Article URL: <a href="https://mareksuppa.com/til/keepassxc-claude-code-api-keys/">https://mareksuppa.com/til/keepassxc-claude-code-api-keys/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47517931">https://news.ycombinator.com/item?id=47517931</a></p>
<p>Points: 2</p>
<p># Comments: 3</p>
]]></description><pubDate>Wed, 25 Mar 2026 14:38:01 +0000</pubDate><link>https://mareksuppa.com/til/keepassxc-claude-code-api-keys/</link><dc:creator>mrshu</dc:creator><comments>https://news.ycombinator.com/item?id=47517931</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47517931</guid></item><item><title><![CDATA[TIL: You can attach images to GitHub PRs from the CLI (and your agents can too)]]></title><description><![CDATA[
<p>Article URL: <a href="https://mareksuppa.com/til/github-pr-images-from-cli/">https://mareksuppa.com/til/github-pr-images-from-cli/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47510668">https://news.ycombinator.com/item?id=47510668</a></p>
<p>Points: 4</p>
<p># Comments: 1</p>
]]></description><pubDate>Tue, 24 Mar 2026 22:51:11 +0000</pubDate><link>https://mareksuppa.com/til/github-pr-images-from-cli/</link><dc:creator>mrshu</dc:creator><comments>https://news.ycombinator.com/item?id=47510668</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47510668</guid></item><item><title><![CDATA[New comment by mrshu in "When does MCP make sense vs CLI?"]]></title><description><![CDATA[
<p>It really seems the primary benefit of MCP servers was to force companies to establish some externally exposed APIs if/when they did not have them.</p>
]]></description><pubDate>Sun, 01 Mar 2026 21:27:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=47210841</link><dc:creator>mrshu</dc:creator><comments>https://news.ycombinator.com/item?id=47210841</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47210841</guid></item><item><title><![CDATA[New comment by mrshu in "I’m joining OpenAI"]]></title><description><![CDATA[
<p>To be fair, it's not like he did not read a single line of code that ended up being generated.</p>
]]></description><pubDate>Sun, 15 Feb 2026 22:52:02 +0000</pubDate><link>https://news.ycombinator.com/item?id=47028583</link><dc:creator>mrshu</dc:creator><comments>https://news.ycombinator.com/item?id=47028583</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47028583</guid></item><item><title><![CDATA[New comment by mrshu in "Another GitHub outage in the same day"]]></title><description><![CDATA[
<p>This (multiple major outages a day) has unfortunately been happening for quite a while now -- on the 2nd of February, 2026 for instance.<p>The GitHub Status Page does not visualize these very well but you can see them parsed out and aggregated here:<p><a href="https://mrshu.github.io/github-statuses/" rel="nofollow">https://mrshu.github.io/github-statuses/</a></p>
]]></description><pubDate>Mon, 09 Feb 2026 22:58:34 +0000</pubDate><link>https://news.ycombinator.com/item?id=46952775</link><dc:creator>mrshu</dc:creator><comments>https://news.ycombinator.com/item?id=46952775</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46952775</guid></item><item><title><![CDATA[New comment by mrshu in "GitHub is down again"]]></title><description><![CDATA[
<p>Here it is. It looks like they are down to a single 9 at this point across all services:<p><a href="https://mrshu.github.io/github-statuses/" rel="nofollow">https://mrshu.github.io/github-statuses/</a></p>
]]></description><pubDate>Mon, 09 Feb 2026 18:30:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=46948936</link><dc:creator>mrshu</dc:creator><comments>https://news.ycombinator.com/item?id=46948936</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46948936</guid></item><item><title><![CDATA[New comment by mrshu in "GitHub is down again"]]></title><description><![CDATA[
<p>GitHub no longer publishes aggregate numbers so here they are parsed out. It looks like they are down to a single 9 at this point across all services:<p><a href="https://mrshu.github.io/github-statuses/" rel="nofollow">https://mrshu.github.io/github-statuses/</a></p>
]]></description><pubDate>Mon, 09 Feb 2026 18:28:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=46948910</link><dc:creator>mrshu</dc:creator><comments>https://news.ycombinator.com/item?id=46948910</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46948910</guid></item><item><title><![CDATA[New comment by mrshu in "GitHub discusses giving maintainers control to disable PRs"]]></title><description><![CDATA[
<p>Some projects (like the pi coding agent) use a gated approach for first-time contributors:<p><a href="https://github.com/badlogic/pi-mono/blob/main/CONTRIBUTING.md#first-time-contributors" rel="nofollow">https://github.com/badlogic/pi-mono/blob/main/CONTRIBUTING.m...</a><p>Here is what it looks like in practice:<p><a href="https://github.com/badlogic/pi-mono/issues/1218" rel="nofollow">https://github.com/badlogic/pi-mono/issues/1218</a></p>
]]></description><pubDate>Tue, 03 Feb 2026 13:01:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=46870460</link><dc:creator>mrshu</dc:creator><comments>https://news.ycombinator.com/item?id=46870460</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46870460</guid></item><item><title><![CDATA[New comment by mrshu in "Clawdbot Renames to Moltbot"]]></title><description><![CDATA[
<p>Peter Steinberger, the author of Clawdbot / Moltbot<p><a href="https://steipete.me/" rel="nofollow">https://steipete.me/</a></p>
]]></description><pubDate>Wed, 28 Jan 2026 01:08:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=46789673</link><dc:creator>mrshu</dc:creator><comments>https://news.ycombinator.com/item?id=46789673</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46789673</guid></item><item><title><![CDATA[New comment by mrshu in "Clawdbot Renames to Moltbot"]]></title><description><![CDATA[
<p>It was not built by Claude -- Peter no longer uses it for coding -- he builds exclusively with Codex now: <a href="https://steipete.me/posts/2025/shipping-at-inference-speed" rel="nofollow">https://steipete.me/posts/2025/shipping-at-inference-speed</a></p>
]]></description><pubDate>Wed, 28 Jan 2026 01:08:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=46789669</link><dc:creator>mrshu</dc:creator><comments>https://news.ycombinator.com/item?id=46789669</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46789669</guid></item><item><title><![CDATA[New comment by mrshu in "Statement by Denmark, Finland, France, Germany, the Netherlands,Norway,Sweden,UK"]]></title><description><![CDATA[
<p>Here is an example: <a href="https://www.dailymail.co.uk/news/article-15476463/Trump-tells-Norwegian-PM-no-longer-feels-obligation-think-purely-peace-country-decided-not-Nobel-Peace-Prize-Greenland.html" rel="nofollow">https://www.dailymail.co.uk/news/article-15476463/Trump-tell...</a></p>
]]></description><pubDate>Mon, 19 Jan 2026 17:56:23 +0000</pubDate><link>https://news.ycombinator.com/item?id=46682249</link><dc:creator>mrshu</dc:creator><comments>https://news.ycombinator.com/item?id=46682249</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46682249</guid></item><item><title><![CDATA[New comment by mrshu in "Claude Sonnet 4.5"]]></title><description><![CDATA[
<p>Do you normally run Opus by default? It seems the Max subscription should let you run Sonnet in an uninterrupted way, so it was surprising to read.</p>
]]></description><pubDate>Mon, 29 Sep 2025 18:08:12 +0000</pubDate><link>https://news.ycombinator.com/item?id=45416877</link><dc:creator>mrshu</dc:creator><comments>https://news.ycombinator.com/item?id=45416877</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45416877</guid></item><item><title><![CDATA[New comment by mrshu in "Claude Sonnet 4.5"]]></title><description><![CDATA[
<p>What are some standard benchmarks you look at in this space?</p>
]]></description><pubDate>Mon, 29 Sep 2025 18:05:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=45416836</link><dc:creator>mrshu</dc:creator><comments>https://news.ycombinator.com/item?id=45416836</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45416836</guid></item><item><title><![CDATA[New comment by mrshu in "Claude Sonnet 4.5"]]></title><description><![CDATA[
<p>Do you think a more messier math benchmark (in terms of how it is defined) might be more difficult for these models to get?</p>
]]></description><pubDate>Mon, 29 Sep 2025 18:03:21 +0000</pubDate><link>https://news.ycombinator.com/item?id=45416818</link><dc:creator>mrshu</dc:creator><comments>https://news.ycombinator.com/item?id=45416818</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45416818</guid></item><item><title><![CDATA[New comment by mrshu in "Failing to Understand the Exponential, Again"]]></title><description><![CDATA[
<p>The author is an AI researcher at Anthropic: <a href="https://www.julian.ac/about/" rel="nofollow">https://www.julian.ac/about/</a><p>He likely has his substantial experience using AI in real life (particularly when it comes to coding).</p>
]]></description><pubDate>Sun, 28 Sep 2025 16:02:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=45405354</link><dc:creator>mrshu</dc:creator><comments>https://news.ycombinator.com/item?id=45405354</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45405354</guid></item><item><title><![CDATA[New comment by mrshu in "Cloudflare Email Service: private beta"]]></title><description><![CDATA[
<p>This is a SendGrid alternative (transactional emails, potentially with a nice API).</p>
]]></description><pubDate>Thu, 25 Sep 2025 20:53:27 +0000</pubDate><link>https://news.ycombinator.com/item?id=45378907</link><dc:creator>mrshu</dc:creator><comments>https://news.ycombinator.com/item?id=45378907</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45378907</guid></item><item><title><![CDATA[New comment by mrshu in "Bagel: Open-source unified multimodal model"]]></title><description><![CDATA[
<p>OpenAI does not provide many details about their models these days but they do mention that the "Advanced voice" within ChatGPT operates on audio input directly:<p>> Advanced voice uses natively multimodal models, such as GPT-4o, which means that it directly “hears” and generates audio, providing for more natural, real-time conversations that pick up on non-verbal cues, such as the speed you’re talking, and can respond with emotion.<p>From <a href="https://help.openai.com/en/articles/8400625-voice-mode-faq" rel="nofollow">https://help.openai.com/en/articles/8400625-voice-mode-faq</a></p>
]]></description><pubDate>Mon, 26 May 2025 21:56:50 +0000</pubDate><link>https://news.ycombinator.com/item?id=44102059</link><dc:creator>mrshu</dc:creator><comments>https://news.ycombinator.com/item?id=44102059</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44102059</guid></item><item><title><![CDATA[New comment by mrshu in "Devstral"]]></title><description><![CDATA[
<p>ra-aid works pretty well with Ollama (haven't tried it with Devstral yet though)<p><a href="https://docs.ra-aid.ai/configuration/ollama/" rel="nofollow">https://docs.ra-aid.ai/configuration/ollama/</a></p>
]]></description><pubDate>Thu, 22 May 2025 17:00:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=44064049</link><dc:creator>mrshu</dc:creator><comments>https://news.ycombinator.com/item?id=44064049</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44064049</guid></item></channel></rss>