<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: purplerabbit</title><link>https://news.ycombinator.com/user?id=purplerabbit</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Fri, 17 Apr 2026 17:44:23 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=purplerabbit" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by purplerabbit in "A dot a day keeps the clutter away"]]></title><description><![CDATA[
<p>Something freeing to me that my wife said:<p>"If you get rid of clutter, there <i>will</i> be cases where you'll have gotten rid of something useful at that moment. It's not about avoiding that -- it's about accepting the right tradeoff between cleanliness and functionality."</p>
]]></description><pubDate>Wed, 01 Apr 2026 18:01:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=47604303</link><dc:creator>purplerabbit</dc:creator><comments>https://news.ycombinator.com/item?id=47604303</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47604303</guid></item><item><title><![CDATA[New comment by purplerabbit in "Anthropic, please make a new Slack"]]></title><description><![CDATA[
<p>Anyone know any interesting OSS Slack alternatives with a decent API?</p>
]]></description><pubDate>Fri, 06 Mar 2026 21:53:48 +0000</pubDate><link>https://news.ycombinator.com/item?id=47281605</link><dc:creator>purplerabbit</dc:creator><comments>https://news.ycombinator.com/item?id=47281605</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47281605</guid></item><item><title><![CDATA[Solve Everything]]></title><description><![CDATA[
<p>Article URL: <a href="https://solveeverything.org/">https://solveeverything.org/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47015184">https://news.ycombinator.com/item?id=47015184</a></p>
<p>Points: 5</p>
<p># Comments: 2</p>
]]></description><pubDate>Sat, 14 Feb 2026 15:23:35 +0000</pubDate><link>https://solveeverything.org/</link><dc:creator>purplerabbit</dc:creator><comments>https://news.ycombinator.com/item?id=47015184</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47015184</guid></item><item><title><![CDATA[Outcome Engineering]]></title><description><![CDATA[
<p>Article URL: <a href="https://o16g.com/">https://o16g.com/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46978648">https://news.ycombinator.com/item?id=46978648</a></p>
<p>Points: 5</p>
<p># Comments: 2</p>
]]></description><pubDate>Wed, 11 Feb 2026 18:18:11 +0000</pubDate><link>https://o16g.com/</link><dc:creator>purplerabbit</dc:creator><comments>https://news.ycombinator.com/item?id=46978648</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46978648</guid></item><item><title><![CDATA[New comment by purplerabbit in "Advancing finance with Claude Opus 4.6"]]></title><description><![CDATA[
<p>I know plenty of nondeterministic accountants</p>
]]></description><pubDate>Thu, 05 Feb 2026 22:33:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=46906368</link><dc:creator>purplerabbit</dc:creator><comments>https://news.ycombinator.com/item?id=46906368</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46906368</guid></item><item><title><![CDATA[New comment by purplerabbit in "Claude Opus 4.6"]]></title><description><![CDATA[
<p>The lack of broad benchmark reports in this makes me curious: Has OpenAI reverted to benchmaxxing? Looking forward to hearing opinions once we all try both of these out</p>
]]></description><pubDate>Thu, 05 Feb 2026 18:29:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=46902982</link><dc:creator>purplerabbit</dc:creator><comments>https://news.ycombinator.com/item?id=46902982</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46902982</guid></item><item><title><![CDATA[New comment by purplerabbit in "Ask HN: What Are You Working On? (December 2025)"]]></title><description><![CDATA[
<p>You could have to your chat give them direction</p>
]]></description><pubDate>Tue, 16 Dec 2025 03:24:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=46284391</link><dc:creator>purplerabbit</dc:creator><comments>https://news.ycombinator.com/item?id=46284391</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46284391</guid></item><item><title><![CDATA[New comment by purplerabbit in "Why I Chose Elixir Phoenix over Rails, Laravel, and Next.js"]]></title><description><![CDATA[
<p>Have you checked out t3 stack? Curious which pieces are missing from that that you'd deem critical</p>
]]></description><pubDate>Thu, 16 Oct 2025 16:18:25 +0000</pubDate><link>https://news.ycombinator.com/item?id=45607302</link><dc:creator>purplerabbit</dc:creator><comments>https://news.ycombinator.com/item?id=45607302</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45607302</guid></item><item><title><![CDATA[New comment by purplerabbit in "Two things LLM coding agents are still bad at"]]></title><description><![CDATA[
<p>Most of us probably do the same thing when we read a HN comment about something specific: "This rando seems to know what they're talking about. I'll assume it as fact until I encounter otherwise."<p>Not doing this might actually cause bigger problems... Getting first-hand experience or even reputable knowledge about something is extremely expensive compared to gut-checking random info you come across. So the "cheap knowledge" may be worth it on balance.</p>
]]></description><pubDate>Thu, 09 Oct 2025 20:53:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=45532948</link><dc:creator>purplerabbit</dc:creator><comments>https://news.ycombinator.com/item?id=45532948</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45532948</guid></item><item><title><![CDATA[New comment by purplerabbit in "Inflammation now predicts heart disease more strongly than cholesterol"]]></title><description><![CDATA[
<p>Just to throw into the mix: apparently sitting in a hyperbaric oxygen chamber does. Who would've thought.</p>
]]></description><pubDate>Tue, 30 Sep 2025 21:12:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=45431318</link><dc:creator>purplerabbit</dc:creator><comments>https://news.ycombinator.com/item?id=45431318</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45431318</guid></item><item><title><![CDATA[New comment by purplerabbit in "Study mode"]]></title><description><![CDATA[
<p>In case you find it interesting: I deployed an early version of a "lesson administering" bot deployed on a college campus that guides students through tutored activities of content curated by a professor in the "study mode" style -- that is, forcing them to think for themselves. We saw an immediate student performance gain on exams of about 1 stdev in the course. So with the right material and right prompting, things are looking promising.</p>
]]></description><pubDate>Tue, 29 Jul 2025 23:07:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=44729288</link><dc:creator>purplerabbit</dc:creator><comments>https://news.ycombinator.com/item?id=44729288</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44729288</guid></item><item><title><![CDATA[New comment by purplerabbit in "We fell out of love with Next.js and back in love with Ruby on Rails"]]></title><description><![CDATA[
<p>Everyone ITT will hate me for saying this, but: T3 stack.</p>
]]></description><pubDate>Sat, 03 May 2025 20:30:48 +0000</pubDate><link>https://news.ycombinator.com/item?id=43882029</link><dc:creator>purplerabbit</dc:creator><comments>https://news.ycombinator.com/item?id=43882029</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43882029</guid></item><item><title><![CDATA[New comment by purplerabbit in "GPT-4.1 in the API"]]></title><description><![CDATA[
<p>What model are you personally using in your aider coding? :)</p>
]]></description><pubDate>Tue, 15 Apr 2025 02:38:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=43688503</link><dc:creator>purplerabbit</dc:creator><comments>https://news.ycombinator.com/item?id=43688503</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43688503</guid></item><item><title><![CDATA[New comment by purplerabbit in "Smallpond – A lightweight data processing framework built on DuckDB and 3FS"]]></title><description><![CDATA[
<p>Maybe they just mean for the type of projects they care about</p>
]]></description><pubDate>Sun, 02 Mar 2025 20:44:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=43234861</link><dc:creator>purplerabbit</dc:creator><comments>https://news.ycombinator.com/item?id=43234861</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43234861</guid></item><item><title><![CDATA[New comment by purplerabbit in "EdgeDB is now Gel and Postgres is the future"]]></title><description><![CDATA[
<p>Have you tried drizzle? If so, what's your beef? (The only one I've had is lack of down-migrations)</p>
]]></description><pubDate>Tue, 25 Feb 2025 23:39:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=43178931</link><dc:creator>purplerabbit</dc:creator><comments>https://news.ycombinator.com/item?id=43178931</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43178931</guid></item><item><title><![CDATA[New comment by purplerabbit in "Honeycrisp apples went from marvel to mediocre"]]></title><description><![CDATA[
<p>Sounds like your market is a few years behind the US :)<p>Seriously, I hope you get honey/cosmic crisps -- they converted me to buying apples regularly.</p>
]]></description><pubDate>Sat, 30 Nov 2024 22:43:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=42284589</link><dc:creator>purplerabbit</dc:creator><comments>https://news.ycombinator.com/item?id=42284589</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42284589</guid></item><item><title><![CDATA[New comment by purplerabbit in "Why aren't LLMs trained on action / cause+effect data vs. just analytical stuff?"]]></title><description><![CDATA[
<p>The tokens could describe a sequence of actions and their consequences vs. blog / forum type content</p>
]]></description><pubDate>Tue, 01 Oct 2024 18:46:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=41712542</link><dc:creator>purplerabbit</dc:creator><comments>https://news.ycombinator.com/item?id=41712542</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41712542</guid></item><item><title><![CDATA[Why aren't LLMs trained on action / cause+effect data vs. just analytical stuff?]]></title><description><![CDATA[
<p>Stupid question, but if we want models that are capable of <i>doing</i> things (agents) vs just spitting out interesting content, why isn't anyone training them on data that represents actions?<p>Models are incredible at generating analytical / blog-ish / stack overflowish content, but suck at doing things that are complex enough that they require iteration.<p>For instance: If we want models that can handle complex projects, why don't we record actions taken in the execution of complex projects, and train models on that? Or if we want models that can use a browser competently, why don't we train models on screenshots + action descriptions? (Or is this what was done with o1, which is why it seems to have unprecedented capabilities?)<p>Is the problem just getting high-quality data? I know we've got internet dumps full of blog-ish content, but no big, easy-to-gather dumps of high-quality information about actions or chains of actions and their effects over time<p>(I'm sure there are tons of framing problems in this question -- sorry)</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=41711251">https://news.ycombinator.com/item?id=41711251</a></p>
<p>Points: 3</p>
<p># Comments: 4</p>
]]></description><pubDate>Tue, 01 Oct 2024 17:12:25 +0000</pubDate><link>https://news.ycombinator.com/item?id=41711251</link><dc:creator>purplerabbit</dc:creator><comments>https://news.ycombinator.com/item?id=41711251</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41711251</guid></item><item><title><![CDATA[New comment by purplerabbit in "Nearly half of Nvidia's revenue comes from four mystery whales each buying $3B+"]]></title><description><![CDATA[
<p>"Who could it be... Hmm... Such a tough nut to crack..."<p>(Even without a report on this it would be obvious)</p>
]]></description><pubDate>Sat, 31 Aug 2024 20:20:57 +0000</pubDate><link>https://news.ycombinator.com/item?id=41411666</link><dc:creator>purplerabbit</dc:creator><comments>https://news.ycombinator.com/item?id=41411666</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41411666</guid></item><item><title><![CDATA[New comment by purplerabbit in "Blitzortung – real time lightning strikes around the world"]]></title><description><![CDATA[
<p>Sponge bath lying down in insulated closet is safest option</p>
]]></description><pubDate>Wed, 28 Aug 2024 03:31:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=41375664</link><dc:creator>purplerabbit</dc:creator><comments>https://news.ycombinator.com/item?id=41375664</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41375664</guid></item></channel></rss>