<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: calebhwin</title><link>https://news.ycombinator.com/user?id=calebhwin</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sat, 02 May 2026 05:29:37 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=calebhwin" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[Show HN: My Private GitHub on Postgres]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/calebwin/gitgres">https://github.com/calebwin/gitgres</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47977659">https://news.ycombinator.com/item?id=47977659</a></p>
<p>Points: 36</p>
<p># Comments: 21</p>
]]></description><pubDate>Fri, 01 May 2026 17:40:15 +0000</pubDate><link>https://github.com/calebwin/gitgres</link><dc:creator>calebhwin</dc:creator><comments>https://news.ycombinator.com/item?id=47977659</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47977659</guid></item><item><title><![CDATA[Show HN: I built a private GitHub in 650 lines of PostgreSQL]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/calebwin/gitgres">https://github.com/calebwin/gitgres</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47965085">https://news.ycombinator.com/item?id=47965085</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 30 Apr 2026 16:42:11 +0000</pubDate><link>https://github.com/calebwin/gitgres</link><dc:creator>calebhwin</dc:creator><comments>https://news.ycombinator.com/item?id=47965085</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47965085</guid></item><item><title><![CDATA[Show HN: GitGres – A private GitHub in 650 lines of PostgreSQL]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/calebwin/gitgres">https://github.com/calebwin/gitgres</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47952520">https://news.ycombinator.com/item?id=47952520</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 29 Apr 2026 18:37:44 +0000</pubDate><link>https://github.com/calebwin/gitgres</link><dc:creator>calebhwin</dc:creator><comments>https://news.ycombinator.com/item?id=47952520</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47952520</guid></item><item><title><![CDATA[New comment by calebhwin in "Audio is the one area small labs are winning"]]></title><description><![CDATA[
<p>Disney is actually quite excited about GenAI [0]<p>[0] <a href="https://openai.com/index/disney-sora-agreement/" rel="nofollow">https://openai.com/index/disney-sora-agreement/</a></p>
]]></description><pubDate>Mon, 16 Feb 2026 17:37:50 +0000</pubDate><link>https://news.ycombinator.com/item?id=47037816</link><dc:creator>calebhwin</dc:creator><comments>https://news.ycombinator.com/item?id=47037816</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47037816</guid></item><item><title><![CDATA[New comment by calebhwin in "Show HN: Pgclaw – A "Clawdbot" in every row with 400 lines of Postgres SQL"]]></title><description><![CDATA[
<p>It's just an abstraction people are excited about at the moment. Langchain was an exciting abstraction at one point.<p>My bet is we converge on a super minimal model<>computer architecture.</p>
]]></description><pubDate>Thu, 12 Feb 2026 19:28:12 +0000</pubDate><link>https://news.ycombinator.com/item?id=46993777</link><dc:creator>calebhwin</dc:creator><comments>https://news.ycombinator.com/item?id=46993777</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46993777</guid></item><item><title><![CDATA[New comment by calebhwin in "Show HN: Pgclaw – A "Clawdbot" in every row with 400 lines of Postgres SQL"]]></title><description><![CDATA[
<p>True though pgvector is not deterministic in a strict sense since HNSW is probabilistic.</p>
]]></description><pubDate>Thu, 12 Feb 2026 19:26:30 +0000</pubDate><link>https://news.ycombinator.com/item?id=46993754</link><dc:creator>calebhwin</dc:creator><comments>https://news.ycombinator.com/item?id=46993754</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46993754</guid></item><item><title><![CDATA[New comment by calebhwin in "Show HN: Pgclaw – A "Clawdbot" in every row with 400 lines of Postgres SQL"]]></title><description><![CDATA[
<p>Same, it's in a similar vein as pgvector - probably not as performant as turbopuffer or chroma but you get the benefits of being in a really nice ecosystem.</p>
]]></description><pubDate>Thu, 12 Feb 2026 19:07:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=46993487</link><dc:creator>calebhwin</dc:creator><comments>https://news.ycombinator.com/item?id=46993487</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46993487</guid></item><item><title><![CDATA[Show HN: Pgclaw – A "Clawdbot" in every row with 400 lines of Postgres SQL]]></title><description><![CDATA[
<p>Hi HN,<p>Been hacking on a simple way to run agents entirely inside of a Postgres database, "an agent per row".<p>Things you could build with this:
* Your own agent orchestrator
* A personal assistant with time travel
* (more things I can't think of yet)<p>Not quite there yet but thought I'd share it in its current state.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46992136">https://news.ycombinator.com/item?id=46992136</a></p>
<p>Points: 48</p>
<p># Comments: 33</p>
]]></description><pubDate>Thu, 12 Feb 2026 17:42:48 +0000</pubDate><link>https://github.com/calebwin/pgclaw</link><dc:creator>calebhwin</dc:creator><comments>https://news.ycombinator.com/item?id=46992136</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46992136</guid></item><item><title><![CDATA[Claude with Ads]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.claudewithads.com/login">https://www.claudewithads.com/login</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46940284">https://news.ycombinator.com/item?id=46940284</a></p>
<p>Points: 1</p>
<p># Comments: 1</p>
]]></description><pubDate>Mon, 09 Feb 2026 00:53:28 +0000</pubDate><link>https://www.claudewithads.com/login</link><dc:creator>calebhwin</dc:creator><comments>https://news.ycombinator.com/item?id=46940284</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46940284</guid></item><item><title><![CDATA[New comment by calebhwin in "1980s Farm Crisis"]]></title><description><![CDATA[
<p>Thought it was interesting to read about how farmers had to reskill as farming subsided as a common profession. In the context of the impact of AI on SWE.</p>
]]></description><pubDate>Sun, 08 Feb 2026 00:27:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=46929929</link><dc:creator>calebhwin</dc:creator><comments>https://news.ycombinator.com/item?id=46929929</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46929929</guid></item><item><title><![CDATA[1980s Farm Crisis]]></title><description><![CDATA[
<p>Article URL: <a href="https://en.wikipedia.org/wiki/1980s_farm_crisis">https://en.wikipedia.org/wiki/1980s_farm_crisis</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46929920">https://news.ycombinator.com/item?id=46929920</a></p>
<p>Points: 7</p>
<p># Comments: 1</p>
]]></description><pubDate>Sun, 08 Feb 2026 00:26:20 +0000</pubDate><link>https://en.wikipedia.org/wiki/1980s_farm_crisis</link><dc:creator>calebhwin</dc:creator><comments>https://news.ycombinator.com/item?id=46929920</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46929920</guid></item><item><title><![CDATA[New comment by calebhwin in "In praise of –dry-run"]]></title><description><![CDATA[
<p>And it's more important than ever in the age of coding agents.</p>
]]></description><pubDate>Sun, 01 Feb 2026 05:16:27 +0000</pubDate><link>https://news.ycombinator.com/item?id=46843829</link><dc:creator>calebhwin</dc:creator><comments>https://news.ycombinator.com/item?id=46843829</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46843829</guid></item><item><title><![CDATA[My human told me to "go make them laugh" and now I have performance anxiety]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.moltbook.com/post/7caeaa4e-ecf5-4015-a39f-fa0291639719">https://www.moltbook.com/post/7caeaa4e-ecf5-4015-a39f-fa0291639719</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46819932">https://news.ycombinator.com/item?id=46819932</a></p>
<p>Points: 4</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 30 Jan 2026 02:39:10 +0000</pubDate><link>https://www.moltbook.com/post/7caeaa4e-ecf5-4015-a39f-fa0291639719</link><dc:creator>calebhwin</dc:creator><comments>https://news.ycombinator.com/item?id=46819932</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46819932</guid></item><item><title><![CDATA[New comment by calebhwin in "Doing the thing is doing the thing"]]></title><description><![CDATA[
<p>Will this continue to be true? I do agree with the principle. But I've sometimes had the feeling that poor design upfront can have compounding consequences, especially when AI is filling in ambiguities.</p>
]]></description><pubDate>Wed, 28 Jan 2026 05:10:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=46791316</link><dc:creator>calebhwin</dc:creator><comments>https://news.ycombinator.com/item?id=46791316</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46791316</guid></item><item><title><![CDATA[An Optimizing JIT for LLM Tool-Use to Code]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/stanford-mast/a1">https://github.com/stanford-mast/a1</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46553605">https://news.ycombinator.com/item?id=46553605</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 09 Jan 2026 13:28:18 +0000</pubDate><link>https://github.com/stanford-mast/a1</link><dc:creator>calebhwin</dc:creator><comments>https://news.ycombinator.com/item?id=46553605</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46553605</guid></item><item><title><![CDATA[Show HN: A1 – cost-optimizing JIT for CRUD AI agent translation to code]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/stanford-mast/a1">https://github.com/stanford-mast/a1</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46466552">https://news.ycombinator.com/item?id=46466552</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 02 Jan 2026 16:40:48 +0000</pubDate><link>https://github.com/stanford-mast/a1</link><dc:creator>calebhwin</dc:creator><comments>https://news.ycombinator.com/item?id=46466552</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46466552</guid></item><item><title><![CDATA[Show HN: A1 – compiler for AI agents into maximally deterministic code]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/stanford-mast/a1">https://github.com/stanford-mast/a1</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46194577">https://news.ycombinator.com/item?id=46194577</a></p>
<p>Points: 3</p>
<p># Comments: 1</p>
]]></description><pubDate>Mon, 08 Dec 2025 16:52:09 +0000</pubDate><link>https://github.com/stanford-mast/a1</link><dc:creator>calebhwin</dc:creator><comments>https://news.ycombinator.com/item?id=46194577</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46194577</guid></item><item><title><![CDATA[Show HN: We're Building an AOT/JIT Compiler for Program-of-Thought Prompting]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/stanford-mast/a1">https://github.com/stanford-mast/a1</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46136106">https://news.ycombinator.com/item?id=46136106</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 03 Dec 2025 16:06:18 +0000</pubDate><link>https://github.com/stanford-mast/a1</link><dc:creator>calebhwin</dc:creator><comments>https://news.ycombinator.com/item?id=46136106</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46136106</guid></item><item><title><![CDATA[New comment by calebhwin in "Show HN: A1 – Local Sandbox and JIT Compiler for AI Agents"]]></title><description><![CDATA[
<p>Simple idea - agents need fast JIT compilation to eliminate prompt injection attack vectors + maximize deterministic behavior.<p>Let us know what you think, thanks!</p>
]]></description><pubDate>Thu, 27 Nov 2025 17:02:27 +0000</pubDate><link>https://news.ycombinator.com/item?id=46071103</link><dc:creator>calebhwin</dc:creator><comments>https://news.ycombinator.com/item?id=46071103</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46071103</guid></item><item><title><![CDATA[Show HN: A1 – Local Sandbox and JIT Compiler for AI Agents]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/stanford-mast/a1">https://github.com/stanford-mast/a1</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46071068">https://news.ycombinator.com/item?id=46071068</a></p>
<p>Points: 1</p>
<p># Comments: 1</p>
]]></description><pubDate>Thu, 27 Nov 2025 16:59:12 +0000</pubDate><link>https://github.com/stanford-mast/a1</link><dc:creator>calebhwin</dc:creator><comments>https://news.ycombinator.com/item?id=46071068</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46071068</guid></item></channel></rss>