<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: adam_patarino</title><link>https://news.ycombinator.com/user?id=adam_patarino</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 10 Jun 2026 08:09:48 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=adam_patarino" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by adam_patarino in "Claude Opus 4.8"]]></title><description><![CDATA[
<p>Smaller models can already outperform SOTA and massive models on specific tasks / domains.</p>
]]></description><pubDate>Fri, 29 May 2026 12:14:02 +0000</pubDate><link>https://news.ycombinator.com/item?id=48322124</link><dc:creator>adam_patarino</dc:creator><comments>https://news.ycombinator.com/item?id=48322124</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48322124</guid></item><item><title><![CDATA[New comment by adam_patarino in "Using AI to write better code more slowly"]]></title><description><![CDATA[
<p>I like Zed for this. 
We are considering autocomplete for Rig after we launch our agent. Local would be 1000x faster.</p>
]]></description><pubDate>Tue, 26 May 2026 12:17:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=48278708</link><dc:creator>adam_patarino</dc:creator><comments>https://news.ycombinator.com/item?id=48278708</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48278708</guid></item><item><title><![CDATA[New comment by adam_patarino in "Goodbye Visa and Mastercard: 130M Europeans switching to sovereign payment"]]></title><description><![CDATA[
<p>Individual experience is rarely an accurate representation of the broader system.</p>
]]></description><pubDate>Wed, 20 May 2026 16:22:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=48210199</link><dc:creator>adam_patarino</dc:creator><comments>https://news.ycombinator.com/item?id=48210199</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48210199</guid></item><item><title><![CDATA[New comment by adam_patarino in "I don't think AI will make your processes go faster"]]></title><description><![CDATA[
<p>Completely agree. It amazes me how some folks think AI is unlike any other technology revolution. History repeats.</p>
]]></description><pubDate>Sun, 17 May 2026 13:14:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=48168651</link><dc:creator>adam_patarino</dc:creator><comments>https://news.ycombinator.com/item?id=48168651</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48168651</guid></item><item><title><![CDATA[New comment by adam_patarino in "I don't think AI will make your processes go faster"]]></title><description><![CDATA[
<p>> Every software developer knows that you can’t make projects go faster just by typing faster. If that were the case we would all be taking typing lessons.<p>So well said.<p>AI is unveiling how the bureaucracy is the slow part.</p>
]]></description><pubDate>Sun, 17 May 2026 12:55:26 +0000</pubDate><link>https://news.ycombinator.com/item?id=48168513</link><dc:creator>adam_patarino</dc:creator><comments>https://news.ycombinator.com/item?id=48168513</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48168513</guid></item><item><title><![CDATA[New comment by adam_patarino in "I believe there are entire companies right now under AI psychosis"]]></title><description><![CDATA[
<p>I’ve been talking to a lot of engineers about how they use AI in their day to day and it’s dramatically different than what you see from the hypers.<p>The vast majority use one agent at a time and careful step through code. The main benefit they report is often about researching the codebase and possible solutions.</p>
]]></description><pubDate>Sat, 16 May 2026 11:03:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=48159032</link><dc:creator>adam_patarino</dc:creator><comments>https://news.ycombinator.com/item?id=48159032</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48159032</guid></item><item><title><![CDATA[New comment by adam_patarino in "Claude for Small Business"]]></title><description><![CDATA[
<p>Gusto makes payroll zero clicks.<p>I’ve used xero and quickbooks and they integrate with many banks and expense management platforms to automate closing.</p>
]]></description><pubDate>Thu, 14 May 2026 11:55:08 +0000</pubDate><link>https://news.ycombinator.com/item?id=48134131</link><dc:creator>adam_patarino</dc:creator><comments>https://news.ycombinator.com/item?id=48134131</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48134131</guid></item><item><title><![CDATA[New comment by adam_patarino in "Claude for Small Business"]]></title><description><![CDATA[
<p>Closing books and running payroll feel like solved problems with today’s saas and high stakes if you mess up.<p>This is one of those areas I would spend more time checking the outputs than it would take me to click the button myself.</p>
]]></description><pubDate>Thu, 14 May 2026 11:34:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=48133975</link><dc:creator>adam_patarino</dc:creator><comments>https://news.ycombinator.com/item?id=48133975</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48133975</guid></item><item><title><![CDATA[New comment by adam_patarino in "Using Claude Code: The unreasonable effectiveness of HTML"]]></title><description><![CDATA[
<p>It highlights the extremes the anthropic team adopts LLMs in their workflow.<p>I think most of us live somewhere in the middle, using the right tool / output for the job.</p>
]]></description><pubDate>Sat, 09 May 2026 11:41:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=48074142</link><dc:creator>adam_patarino</dc:creator><comments>https://news.ycombinator.com/item?id=48074142</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48074142</guid></item><item><title><![CDATA[New comment by adam_patarino in "Valve releases Steam Controller CAD files under Creative Commons license"]]></title><description><![CDATA[
<p>Sometimes I think Valve is just showing off</p>
]]></description><pubDate>Fri, 08 May 2026 11:52:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=48061806</link><dc:creator>adam_patarino</dc:creator><comments>https://news.ycombinator.com/item?id=48061806</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48061806</guid></item><item><title><![CDATA[New comment by adam_patarino in "GameStop makes $55.5B takeover offer for eBay"]]></title><description><![CDATA[
<p>Diamond hands?</p>
]]></description><pubDate>Mon, 04 May 2026 11:45:40 +0000</pubDate><link>https://news.ycombinator.com/item?id=48007479</link><dc:creator>adam_patarino</dc:creator><comments>https://news.ycombinator.com/item?id=48007479</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48007479</guid></item><item><title><![CDATA[New comment by adam_patarino in "The West forgot how to make things, now it’s forgetting how to code"]]></title><description><![CDATA[
<p>Most workforce reductions are using AI as a cover up for greedy short term bonuses.<p>Any exec using AI to pay fewer people lacks imagination.</p>
]]></description><pubDate>Sun, 26 Apr 2026 11:58:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=47909621</link><dc:creator>adam_patarino</dc:creator><comments>https://news.ycombinator.com/item?id=47909621</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47909621</guid></item><item><title><![CDATA[New comment by adam_patarino in "An update on recent Claude Code quality reports"]]></title><description><![CDATA[
<p>The explanations are all fine.<p>But they come after the team gaslit everyone, telling us it was a skill issue.</p>
]]></description><pubDate>Fri, 24 Apr 2026 11:55:00 +0000</pubDate><link>https://news.ycombinator.com/item?id=47888981</link><dc:creator>adam_patarino</dc:creator><comments>https://news.ycombinator.com/item?id=47888981</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47888981</guid></item><item><title><![CDATA[New comment by adam_patarino in "An update on recent Claude Code quality reports"]]></title><description><![CDATA[
<p>It’s certainly #2. They have shown over dozens of decisions they move very quickly, break stuff, then have to both figure out what broke and how to explain it.</p>
]]></description><pubDate>Fri, 24 Apr 2026 11:53:07 +0000</pubDate><link>https://news.ycombinator.com/item?id=47888970</link><dc:creator>adam_patarino</dc:creator><comments>https://news.ycombinator.com/item?id=47888970</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47888970</guid></item><item><title><![CDATA[New comment by adam_patarino in "An update on recent Claude Code quality reports"]]></title><description><![CDATA[
<p>Token anxiety is real mental overhead.</p>
]]></description><pubDate>Fri, 24 Apr 2026 11:51:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=47888948</link><dc:creator>adam_patarino</dc:creator><comments>https://news.ycombinator.com/item?id=47888948</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47888948</guid></item><item><title><![CDATA[New comment by adam_patarino in "DeepSeek v4"]]></title><description><![CDATA[
<p>Prices are not just hard cost of inference. Training costs are not equal. Chinese labs have cheaper access to large data centers. I also suspect they operate far more efficiently than orgs like openAI.</p>
]]></description><pubDate>Fri, 24 Apr 2026 11:46:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=47888893</link><dc:creator>adam_patarino</dc:creator><comments>https://news.ycombinator.com/item?id=47888893</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47888893</guid></item><item><title><![CDATA[New comment by adam_patarino in "Claude Code to be removed from Anthropic's Pro plan?"]]></title><description><![CDATA[
<p>Either they vibe coded a test that was extremely broken.<p>Or they vibe wrote some bullshit to try and back pedal.</p>
]]></description><pubDate>Wed, 22 Apr 2026 11:26:50 +0000</pubDate><link>https://news.ycombinator.com/item?id=47862036</link><dc:creator>adam_patarino</dc:creator><comments>https://news.ycombinator.com/item?id=47862036</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47862036</guid></item><item><title><![CDATA[New comment by adam_patarino in "Claude Code to be removed from Anthropic's Pro plan?"]]></title><description><![CDATA[
<p>What are you guys subscribed to if not Claude? Copilot? Or is everyone legit bringing their own license?</p>
]]></description><pubDate>Wed, 22 Apr 2026 11:24:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=47862012</link><dc:creator>adam_patarino</dc:creator><comments>https://news.ycombinator.com/item?id=47862012</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47862012</guid></item><item><title><![CDATA[New comment by adam_patarino in "Compressing LLMs with progressive pruning and multi-objective distillation"]]></title><description><![CDATA[
<p>Compressing a mixture of experts model to fit on smaller hardware with a reinforcement learning approach called Self-Distillation Policy Optimization, progressive expert pruning, multi-objective knowledge distillation, speculative decoding, and custom quantization.</p>
]]></description><pubDate>Tue, 21 Apr 2026 12:48:08 +0000</pubDate><link>https://news.ycombinator.com/item?id=47848031</link><dc:creator>adam_patarino</dc:creator><comments>https://news.ycombinator.com/item?id=47848031</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47848031</guid></item><item><title><![CDATA[Compressing LLMs with progressive pruning and multi-objective distillation]]></title><description><![CDATA[
<p>Article URL: <a href="https://rig.ai/blog/compressing-a-model-to-run-locally">https://rig.ai/blog/compressing-a-model-to-run-locally</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47848030">https://news.ycombinator.com/item?id=47848030</a></p>
<p>Points: 4</p>
<p># Comments: 2</p>
]]></description><pubDate>Tue, 21 Apr 2026 12:48:08 +0000</pubDate><link>https://rig.ai/blog/compressing-a-model-to-run-locally</link><dc:creator>adam_patarino</dc:creator><comments>https://news.ycombinator.com/item?id=47848030</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47848030</guid></item></channel></rss>