<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: tempaccount420</title><link>https://news.ycombinator.com/user?id=tempaccount420</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Tue, 29 Sep 2026 22:03:42 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=tempaccount420" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by tempaccount420 in "Bend 2 Is Here"]]></title><description><![CDATA[
<p>Announcement post <a href="https://x.com/VictorTaelin/status/2100681226143092875" rel="nofollow">https://x.com/VictorTaelin/status/2100681226143092875</a><p>> Bend 2 is here!<p>> It is a new programming language that blocks AI mistakes via <i>proof checking</i> - the same technique big AI labs used to >solve open math problems, like Navier-Stokes.<p>> It is also very fast, and runs on GPUs.</p>
]]></description><pubDate>Thu, 17 Sep 2026 20:39:17 +0000</pubDate><link>https://news.ycombinator.com/item?id=49746217</link><dc:creator>tempaccount420</dc:creator><comments>https://news.ycombinator.com/item?id=49746217</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49746217</guid></item><item><title><![CDATA[Bend 2 Is Here]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/bendlang/bend">https://github.com/bendlang/bend</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49746203">https://news.ycombinator.com/item?id=49746203</a></p>
<p>Points: 18</p>
<p># Comments: 3</p>
]]></description><pubDate>Thu, 17 Sep 2026 20:38:15 +0000</pubDate><link>https://github.com/bendlang/bend</link><dc:creator>tempaccount420</dc:creator><comments>https://news.ycombinator.com/item?id=49746203</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49746203</guid></item><item><title><![CDATA[New comment by tempaccount420 in "Bun 1.4"]]></title><description><![CDATA[
<p>It's faster to have it in the runtime in native code.<p>You have more options, not less, you can still use the external dependencies.</p>
]]></description><pubDate>Thu, 20 Aug 2026 14:36:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=49375200</link><dc:creator>tempaccount420</dc:creator><comments>https://news.ycombinator.com/item?id=49375200</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49375200</guid></item><item><title><![CDATA[New comment by tempaccount420 in "Rethinking Database Programming"]]></title><description><![CDATA[
<p>Closed source :(<p><a href="https://acadia.engineering/license/faq" rel="nofollow">https://acadia.engineering/license/faq</a> (archive since these things change over time: <a href="https://archive.vn/oUwxDwxD" rel="nofollow">https://archive.vn/oUwxDwxD</a>)</p>
]]></description><pubDate>Tue, 18 Aug 2026 21:24:08 +0000</pubDate><link>https://news.ycombinator.com/item?id=49352926</link><dc:creator>tempaccount420</dc:creator><comments>https://news.ycombinator.com/item?id=49352926</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49352926</guid></item><item><title><![CDATA[New comment by tempaccount420 in "Acadia Bringing the benefits of elm to SQLite and PostgreSQL"]]></title><description><![CDATA[
<p>Closed source :(<p><a href="https://acadia.engineering/license/faq" rel="nofollow">https://acadia.engineering/license/faq</a> (archive since these things change over time: <a href="https://archive.vn/oUwxDwxD" rel="nofollow">https://archive.vn/oUwxDwxD</a>)</p>
]]></description><pubDate>Tue, 18 Aug 2026 20:59:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=49352626</link><dc:creator>tempaccount420</dc:creator><comments>https://news.ycombinator.com/item?id=49352626</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49352626</guid></item><item><title><![CDATA[New comment by tempaccount420 in "Incident with Github.com [resolved]"]]></title><description><![CDATA[
<p>Why haven't we all moved off GitHub yet?<p>Or let me ask a more useful question: if we were to move, then to where? Ideally somewhere new (not Gitlab)</p>
]]></description><pubDate>Mon, 17 Aug 2026 13:49:29 +0000</pubDate><link>https://news.ycombinator.com/item?id=49330838</link><dc:creator>tempaccount420</dc:creator><comments>https://news.ycombinator.com/item?id=49330838</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49330838</guid></item><item><title><![CDATA[New comment by tempaccount420 in "GitHub Actions and Pages are experiencing degraded availability"]]></title><description><![CDATA[
<p>They're one rewrite in Rust away from fixing everything. (jk)</p>
]]></description><pubDate>Thu, 06 Aug 2026 19:36:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=49201317</link><dc:creator>tempaccount420</dc:creator><comments>https://news.ycombinator.com/item?id=49201317</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49201317</guid></item><item><title><![CDATA[New comment by tempaccount420 in "OpenAI and Hugging Face address security incident during model evaluation"]]></title><description><![CDATA[
<p>Just how badly are these AI companies setting up their sandboxes?</p>
]]></description><pubDate>Tue, 21 Jul 2026 20:45:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=48998041</link><dc:creator>tempaccount420</dc:creator><comments>https://news.ycombinator.com/item?id=48998041</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48998041</guid></item><item><title><![CDATA[New comment by tempaccount420 in "Codex starts encrypting sub-agent prompts"]]></title><description><![CDATA[
<p>Last stage is moving everyone to their cloud platforms, they deploy everything for you, you don't even get to see the code, just the deployed end product.<p>Because letting you look at the code would be too dangerous, you could reverse engineer an exploit to another product! Or distill their internet-distilled model!<p>But don't worry, at least it will be very convenient.</p>
]]></description><pubDate>Tue, 14 Jul 2026 14:54:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=48907855</link><dc:creator>tempaccount420</dc:creator><comments>https://news.ycombinator.com/item?id=48907855</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48907855</guid></item><item><title><![CDATA[Rust and Artificial Intelligence: The Rust Foundation's Position]]></title><description><![CDATA[
<p>Article URL: <a href="https://rustfoundation.org/resource/rust-and-ai-position-statement/">https://rustfoundation.org/resource/rust-and-ai-position-statement/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48839186">https://news.ycombinator.com/item?id=48839186</a></p>
<p>Points: 4</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 09 Jul 2026 00:09:19 +0000</pubDate><link>https://rustfoundation.org/resource/rust-and-ai-position-statement/</link><dc:creator>tempaccount420</dc:creator><comments>https://news.ycombinator.com/item?id=48839186</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48839186</guid></item><item><title><![CDATA[Agent skills for interface builders – by Tailwind devs]]></title><description><![CDATA[
<p>Article URL: <a href="https://ui.sh">https://ui.sh</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48646149">https://news.ycombinator.com/item?id=48646149</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 23 Jun 2026 15:04:16 +0000</pubDate><link>https://ui.sh</link><dc:creator>tempaccount420</dc:creator><comments>https://news.ycombinator.com/item?id=48646149</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48646149</guid></item><item><title><![CDATA[New comment by tempaccount420 in "Epoll vs. io_uring in Linux"]]></title><description><![CDATA[
<p>It's not complex actually, but it is C...</p>
]]></description><pubDate>Sun, 21 Jun 2026 12:49:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=48618490</link><dc:creator>tempaccount420</dc:creator><comments>https://news.ycombinator.com/item?id=48618490</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48618490</guid></item><item><title><![CDATA[New comment by tempaccount420 in "GPT-5.5 hallucinates 3x more than MIT-licensed GLM-5.2"]]></title><description><![CDATA[
<p>> There is no concept of "knowledge" in LLM as it is on Wikipedia.<p>There can be, you don't know if the closed source models aren't using something like DeepSeek's Engram.</p>
]]></description><pubDate>Sat, 20 Jun 2026 12:31:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=48608767</link><dc:creator>tempaccount420</dc:creator><comments>https://news.ycombinator.com/item?id=48608767</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48608767</guid></item><item><title><![CDATA[New comment by tempaccount420 in "Zig by Example"]]></title><description><![CDATA[
<p>IMO, there isn't much space left to fill that Rust couldn't already fill.</p>
]]></description><pubDate>Mon, 08 Jun 2026 14:58:25 +0000</pubDate><link>https://news.ycombinator.com/item?id=48446253</link><dc:creator>tempaccount420</dc:creator><comments>https://news.ycombinator.com/item?id=48446253</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48446253</guid></item><item><title><![CDATA[New comment by tempaccount420 in "DeepSeek V4 Pro beats GPT-5.5 Pro on precision"]]></title><description><![CDATA[
<p>It's not discounted pricing anymore, it's the regular pricing.</p>
]]></description><pubDate>Mon, 08 Jun 2026 07:10:46 +0000</pubDate><link>https://news.ycombinator.com/item?id=48442175</link><dc:creator>tempaccount420</dc:creator><comments>https://news.ycombinator.com/item?id=48442175</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48442175</guid></item><item><title><![CDATA[New comment by tempaccount420 in "DeepSeek V4 Pro beats GPT-5.5 Pro on precision"]]></title><description><![CDATA[
<p>I'm surprised if that works, given how Anthropic trains to reject any fun prompts</p>
]]></description><pubDate>Mon, 08 Jun 2026 07:07:16 +0000</pubDate><link>https://news.ycombinator.com/item?id=48442147</link><dc:creator>tempaccount420</dc:creator><comments>https://news.ycombinator.com/item?id=48442147</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48442147</guid></item><item><title><![CDATA[99.9999% of you should in fact not being "looping" your agent]]></title><description><![CDATA[
<p>Article URL: <a href="https://xcancel.com/ThePrimeagen/status/2063746333023043966">https://xcancel.com/ThePrimeagen/status/2063746333023043966</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48441567">https://news.ycombinator.com/item?id=48441567</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 08 Jun 2026 05:18:20 +0000</pubDate><link>https://xcancel.com/ThePrimeagen/status/2063746333023043966</link><dc:creator>tempaccount420</dc:creator><comments>https://news.ycombinator.com/item?id=48441567</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48441567</guid></item><item><title><![CDATA[New comment by tempaccount420 in "Three of our worst VC stories"]]></title><description><![CDATA[
<p>There are more important things than money.</p>
]]></description><pubDate>Sat, 06 Jun 2026 15:07:29 +0000</pubDate><link>https://news.ycombinator.com/item?id=48425785</link><dc:creator>tempaccount420</dc:creator><comments>https://news.ycombinator.com/item?id=48425785</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48425785</guid></item><item><title><![CDATA[New comment by tempaccount420 in "Gemini 3.5 Flash"]]></title><description><![CDATA[
<p>This is not priced at inference cost.<p>My guess: it's the price at which they make more money than if they rent the TPUs to other companies.<p>The Gemini team has had trouble securing enough TPUs for their user's needs. They struggle with load and their rate limits are really bad. Maybe at a higher price, they have a better chance at getting more TPUs assigned?</p>
]]></description><pubDate>Tue, 19 May 2026 19:30:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=48198247</link><dc:creator>tempaccount420</dc:creator><comments>https://news.ycombinator.com/item?id=48198247</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48198247</guid></item><item><title><![CDATA[New comment by tempaccount420 in "First public macOS kernel memory corruption exploit on Apple M5"]]></title><description><![CDATA[
<p>I'm guessing they have some friends at Anthropic.</p>
]]></description><pubDate>Fri, 15 May 2026 17:12:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=48151203</link><dc:creator>tempaccount420</dc:creator><comments>https://news.ycombinator.com/item?id=48151203</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48151203</guid></item></channel></rss>