<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: zeusk</title><link>https://news.ycombinator.com/user?id=zeusk</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Tue, 19 May 2026 07:35:07 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=zeusk" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by zeusk in "The USB Situation"]]></title><description><![CDATA[
<p>> copper can barely support 10G and is terribly power hungry when it does that.<p>AFAIK, thunderbolt cables are also copper - so what trickery do they use for supporting USB4-80? i believe both connectors use differential pair wires for signalling.</p>
]]></description><pubDate>Sun, 03 May 2026 04:14:25 +0000</pubDate><link>https://news.ycombinator.com/item?id=47993282</link><dc:creator>zeusk</dc:creator><comments>https://news.ycombinator.com/item?id=47993282</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47993282</guid></item><item><title><![CDATA[New comment by zeusk in "Roblox shares plummet 18% as child safety measures weigh on bookings"]]></title><description><![CDATA[
<p>Half life alyx and their push for openVR has made a big impact in that part of the gaming world.<p>But yeah, their games are just as filled with lootbox, crates, skin garbage as other low effort money grabs; saving grace being its all cosmetics only (and they’re private about their financials).</p>
]]></description><pubDate>Sat, 02 May 2026 18:27:08 +0000</pubDate><link>https://news.ycombinator.com/item?id=47988997</link><dc:creator>zeusk</dc:creator><comments>https://news.ycombinator.com/item?id=47988997</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47988997</guid></item><item><title><![CDATA[New comment by zeusk in "Investigating Split Locks on x86-64"]]></title><description><![CDATA[
<p>ordering lock acquisition is a tested strategy to avoid deadlocks; so locking the cache lines sorted by PA would cover that?</p>
]]></description><pubDate>Sat, 11 Apr 2026 15:21:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=47731369</link><dc:creator>zeusk</dc:creator><comments>https://news.ycombinator.com/item?id=47731369</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47731369</guid></item><item><title><![CDATA[New comment by zeusk in "People Love to Work Hard"]]></title><description><![CDATA[
<p>This is very spot on in my experience.</p>
]]></description><pubDate>Tue, 07 Apr 2026 06:00:26 +0000</pubDate><link>https://news.ycombinator.com/item?id=47671237</link><dc:creator>zeusk</dc:creator><comments>https://news.ycombinator.com/item?id=47671237</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47671237</guid></item><item><title><![CDATA[New comment by zeusk in "Apple discontinues the Mac Pro"]]></title><description><![CDATA[
<p>> My personal dream is that vms would support pci pass through and so you can just spin up a Linux vm and let it drive the gpus.<p>SR-IOV is just that? and is well supported by both Windows and Linux.</p>
]]></description><pubDate>Fri, 27 Mar 2026 03:23:41 +0000</pubDate><link>https://news.ycombinator.com/item?id=47538807</link><dc:creator>zeusk</dc:creator><comments>https://news.ycombinator.com/item?id=47538807</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47538807</guid></item><item><title><![CDATA[New comment by zeusk in "SIMD programming in pure Rust"]]></title><description><![CDATA[
<p>They’re used by the internal register renamer/allocator so if it sees you’re storing the results to memory then reusing the named register for a new result - it will allocate a new physical register so your instruction doesn’t stall for the previous write to go through.</p>
]]></description><pubDate>Thu, 22 Jan 2026 01:50:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=46714201</link><dc:creator>zeusk</dc:creator><comments>https://news.ycombinator.com/item?id=46714201</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46714201</guid></item><item><title><![CDATA[New comment by zeusk in "CES 2026: Taking the Lids Off AMD's Venice and MI400 SoCs"]]></title><description><![CDATA[
<p>This has already been tried :)<p>iirc, in the 2016 a quadcore intel cpu ran the original crysis at ~15fps</p>
]]></description><pubDate>Wed, 07 Jan 2026 04:11:16 +0000</pubDate><link>https://news.ycombinator.com/item?id=46522478</link><dc:creator>zeusk</dc:creator><comments>https://news.ycombinator.com/item?id=46522478</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46522478</guid></item><item><title><![CDATA[New comment by zeusk in "Big GPUs don't need big PCs"]]></title><description><![CDATA[
<p>Get the DGX Spark computers? They’re exactly what you’re trying to build.</p>
]]></description><pubDate>Sat, 20 Dec 2025 19:48:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=46338958</link><dc:creator>zeusk</dc:creator><comments>https://news.ycombinator.com/item?id=46338958</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46338958</guid></item><item><title><![CDATA[New comment by zeusk in "1.5 TB of VRAM on Mac Studio – RDMA over Thunderbolt 5"]]></title><description><![CDATA[
<p>the TB5 link (RDMA) is much slower than direct access to system memory</p>
]]></description><pubDate>Thu, 18 Dec 2025 23:31:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=46320306</link><dc:creator>zeusk</dc:creator><comments>https://news.ycombinator.com/item?id=46320306</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46320306</guid></item><item><title><![CDATA[New comment by zeusk in "Open Source Implementation of Apple's Private Compute Cloud"]]></title><description><![CDATA[
<p>Nvidia has been investing in confidential compute for inference workloads in cloud - that covers physical ownership/attacks in their thread model.<p><a href="https://www.nvidia.com/en-us/data-center/solutions/confidential-computing/" rel="nofollow">https://www.nvidia.com/en-us/data-center/solutions/confident...</a><p><a href="https://developer.nvidia.com/blog/protecting-sensitive-data-and-ai-models-with-confidential-computing/" rel="nofollow">https://developer.nvidia.com/blog/protecting-sensitive-data-...</a></p>
]]></description><pubDate>Thu, 06 Nov 2025 23:38:40 +0000</pubDate><link>https://news.ycombinator.com/item?id=45841906</link><dc:creator>zeusk</dc:creator><comments>https://news.ycombinator.com/item?id=45841906</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45841906</guid></item><item><title><![CDATA[New comment by zeusk in "The 512KB Club"]]></title><description><![CDATA[
<p>Yes, but parent comment definitely implied they weren't talking about people running on the latest and best out there. Even the middle-grade smartphones today are leaps and bounds better than the atom from 2010.</p>
]]></description><pubDate>Tue, 04 Nov 2025 18:24:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=45814220</link><dc:creator>zeusk</dc:creator><comments>https://news.ycombinator.com/item?id=45814220</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45814220</guid></item><item><title><![CDATA[New comment by zeusk in "The 512KB Club"]]></title><description><![CDATA[
<p>> And yet, if I go to Youtube or just about any other modern site, it takes literally a minute to load and render, none of the UI elements are responsive, and the site is unusable for playing videos. Why? I'm not asking for anything the hardware isn't capable of doing.<p>but the website and web renderer are definitely not optimized for a netbook from 2010 - even modern smartphones are better at rendering pages and video than your atom (or even 8350u) computers.</p>
]]></description><pubDate>Tue, 04 Nov 2025 18:02:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=45813955</link><dc:creator>zeusk</dc:creator><comments>https://news.ycombinator.com/item?id=45813955</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45813955</guid></item><item><title><![CDATA[New comment by zeusk in "The x86 Interrupt List, aka “Ralf Brown's Interrupt List” (2018)"]]></title><description><![CDATA[
<p>What do you mean by that? Most syscalls are still interrupt based.</p>
]]></description><pubDate>Mon, 03 Nov 2025 07:19:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=45796610</link><dc:creator>zeusk</dc:creator><comments>https://news.ycombinator.com/item?id=45796610</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45796610</guid></item><item><title><![CDATA[New comment by zeusk in "Show HN: MyraOS – My 32-bit operating system in C and ASM (Hack Club project)"]]></title><description><![CDATA[
<p>Double buffering a 4K 4bpp framebuffer itself is 64mb</p>
]]></description><pubDate>Mon, 27 Oct 2025 17:36:48 +0000</pubDate><link>https://news.ycombinator.com/item?id=45723964</link><dc:creator>zeusk</dc:creator><comments>https://news.ycombinator.com/item?id=45723964</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45723964</guid></item><item><title><![CDATA[New comment by zeusk in "Ask HN: What's the best hackable smart TV?"]]></title><description><![CDATA[
<p>> same hardware as the higher end models but needs a firmware bit flip<p>Is this firmware bit flip known? couldn't find anything off google.</p>
]]></description><pubDate>Fri, 10 Oct 2025 17:49:36 +0000</pubDate><link>https://news.ycombinator.com/item?id=45541759</link><dc:creator>zeusk</dc:creator><comments>https://news.ycombinator.com/item?id=45541759</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45541759</guid></item><item><title><![CDATA[New comment by zeusk in "Founder sentenced to seven years in prison for fraudulent sale to JPMorgan"]]></title><description><![CDATA[
<p>AUM is not theirs to keep; and market cap is a very deceitful metric especially for banks where liabilities dwarf the market cap.</p>
]]></description><pubDate>Tue, 30 Sep 2025 16:46:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=45427856</link><dc:creator>zeusk</dc:creator><comments>https://news.ycombinator.com/item?id=45427856</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45427856</guid></item><item><title><![CDATA[New comment by zeusk in "Snapdragon X2 Elite ARM Laptop CPU"]]></title><description><![CDATA[
<p>Well so is the snapdragon X elite, including the older snapdragons (anyone remember scorpion cores on QSD8x50?)</p>
]]></description><pubDate>Thu, 25 Sep 2025 01:05:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=45368059</link><dc:creator>zeusk</dc:creator><comments>https://news.ycombinator.com/item?id=45368059</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45368059</guid></item><item><title><![CDATA[New comment by zeusk in "Writing memory efficient C structs"]]></title><description><![CDATA[
<p>The real issue with packed structs and bitfields happens when concurrency gets involved. Majority of modern CPU caches are private and only allow one core to hold the cache line - so it creates more false dependencies when cores are trying to alter information that was compacted into a cache line on another core.</p>
]]></description><pubDate>Wed, 30 Jul 2025 22:42:32 +0000</pubDate><link>https://news.ycombinator.com/item?id=44740399</link><dc:creator>zeusk</dc:creator><comments>https://news.ycombinator.com/item?id=44740399</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44740399</guid></item><item><title><![CDATA[New comment by zeusk in "Demystifying Debuggers"]]></title><description><![CDATA[
<p>I've used kd/windbg at Microsoft, lldb at Apple, gdb at Intel; WinDbg(Next) and kd are still my absolute favorite.<p>Coolest feature of windbg is time travel debugging - <a href="https://learn.microsoft.com/en-us/windows-hardware/drivers/debuggercmds/time-travel-debugging-replay" rel="nofollow">https://learn.microsoft.com/en-us/windows-hardware/drivers/d...</a></p>
]]></description><pubDate>Wed, 11 Jun 2025 11:36:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=44246516</link><dc:creator>zeusk</dc:creator><comments>https://news.ycombinator.com/item?id=44246516</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44246516</guid></item><item><title><![CDATA[New comment by zeusk in "Denuvo Analysis"]]></title><description><![CDATA[
<p>but afaik, we still don't have a break on xbox one released 2013 - 12 years later.</p>
]]></description><pubDate>Tue, 10 Jun 2025 17:00:27 +0000</pubDate><link>https://news.ycombinator.com/item?id=44239016</link><dc:creator>zeusk</dc:creator><comments>https://news.ycombinator.com/item?id=44239016</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44239016</guid></item></channel></rss>