<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: matt_d</title><link>https://news.ycombinator.com/user?id=matt_d</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 13 Aug 2026 18:49:10 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=matt_d" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[Spaghettifying DRAM]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/xoreaxeaxeax/skitter-creek-bath-salts">https://github.com/xoreaxeaxeax/skitter-creek-bath-salts</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49286341">https://news.ycombinator.com/item?id=49286341</a></p>
<p>Points: 318</p>
<p># Comments: 97</p>
]]></description><pubDate>Thu, 13 Aug 2026 14:17:13 +0000</pubDate><link>https://github.com/xoreaxeaxeax/skitter-creek-bath-salts</link><dc:creator>matt_d</dc:creator><comments>https://news.ycombinator.com/item?id=49286341</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49286341</guid></item><item><title><![CDATA[Specula: Scaling formal specs for autonomous model checking of system code]]></title><description><![CDATA[
<p>Article URL: <a href="http://muratbuffalo.blogspot.com/2026/08/specula-scaling-formal-specifications.html">http://muratbuffalo.blogspot.com/2026/08/specula-scaling-formal-specifications.html</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49281628">https://news.ycombinator.com/item?id=49281628</a></p>
<p>Points: 6</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 13 Aug 2026 03:54:37 +0000</pubDate><link>http://muratbuffalo.blogspot.com/2026/08/specula-scaling-formal-specifications.html</link><dc:creator>matt_d</dc:creator><comments>https://news.ycombinator.com/item?id=49281628</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49281628</guid></item><item><title><![CDATA[Principia Mathematica is modern and insightful]]></title><description><![CDATA[
<p>Article URL: <a href="https://okmij.org/ftp/Computation/Impressions/PrincipiaMathematica.html">https://okmij.org/ftp/Computation/Impressions/PrincipiaMathematica.html</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49279928">https://news.ycombinator.com/item?id=49279928</a></p>
<p>Points: 260</p>
<p># Comments: 140</p>
]]></description><pubDate>Wed, 12 Aug 2026 23:26:21 +0000</pubDate><link>https://okmij.org/ftp/Computation/Impressions/PrincipiaMathematica.html</link><dc:creator>matt_d</dc:creator><comments>https://news.ycombinator.com/item?id=49279928</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49279928</guid></item><item><title><![CDATA[Estimating Branch Probabilities]]></title><description><![CDATA[
<p>Article URL: <a href="https://maskray.me/blog/2026-08-09-estimating-branch-probabilities">https://maskray.me/blog/2026-08-09-estimating-branch-probabilities</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49269377">https://news.ycombinator.com/item?id=49269377</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 12 Aug 2026 08:33:34 +0000</pubDate><link>https://maskray.me/blog/2026-08-09-estimating-branch-probabilities</link><dc:creator>matt_d</dc:creator><comments>https://news.ycombinator.com/item?id=49269377</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49269377</guid></item><item><title><![CDATA[A SAT Attack on Tarski's High School Algebra Problem]]></title><description><![CDATA[
<p>Article URL: <a href="https://arxiv.org/abs/2608.08421">https://arxiv.org/abs/2608.08421</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49268565">https://news.ycombinator.com/item?id=49268565</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 12 Aug 2026 06:30:57 +0000</pubDate><link>https://arxiv.org/abs/2608.08421</link><dc:creator>matt_d</dc:creator><comments>https://news.ycombinator.com/item?id=49268565</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49268565</guid></item><item><title><![CDATA[What Evolves When We Talk About Harness Evolution?]]></title><description><![CDATA[
<p>Article URL: <a href="https://wenwen-d.github.io/blog/harness-delta-attribution/">https://wenwen-d.github.io/blog/harness-delta-attribution/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49268055">https://news.ycombinator.com/item?id=49268055</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 12 Aug 2026 05:13:19 +0000</pubDate><link>https://wenwen-d.github.io/blog/harness-delta-attribution/</link><dc:creator>matt_d</dc:creator><comments>https://news.ycombinator.com/item?id=49268055</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49268055</guid></item><item><title><![CDATA[LSPs for LLMs]]></title><description><![CDATA[
<p>Article URL: <a href="https://ianbarber.blog/2026/08/11/lsps-for-llms/">https://ianbarber.blog/2026/08/11/lsps-for-llms/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49267518">https://news.ycombinator.com/item?id=49267518</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 12 Aug 2026 03:26:10 +0000</pubDate><link>https://ianbarber.blog/2026/08/11/lsps-for-llms/</link><dc:creator>matt_d</dc:creator><comments>https://news.ycombinator.com/item?id=49267518</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49267518</guid></item><item><title><![CDATA[mmiotic: Latency x-ray for undocumented hardware]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/xoreaxeaxeax/mmiotic">https://github.com/xoreaxeaxeax/mmiotic</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49265900">https://news.ycombinator.com/item?id=49265900</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 11 Aug 2026 23:28:42 +0000</pubDate><link>https://github.com/xoreaxeaxeax/mmiotic</link><dc:creator>matt_d</dc:creator><comments>https://news.ycombinator.com/item?id=49265900</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49265900</guid></item><item><title><![CDATA[The Unseen Delta: Characterizing the Compiler Optimization Landscape]]></title><description><![CDATA[
<p>Article URL: <a href="https://arxiv.org/abs/2608.09530">https://arxiv.org/abs/2608.09530</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49265760">https://news.ycombinator.com/item?id=49265760</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 11 Aug 2026 23:13:54 +0000</pubDate><link>https://arxiv.org/abs/2608.09530</link><dc:creator>matt_d</dc:creator><comments>https://news.ycombinator.com/item?id=49265760</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49265760</guid></item><item><title><![CDATA[Don't Stall Me Now: Hiding Memory Latency in eBPF]]></title><description><![CDATA[
<p>Article URL: <a href="https://dl.acm.org/doi/10.1145/3789240.3829175">https://dl.acm.org/doi/10.1145/3789240.3829175</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49265648">https://news.ycombinator.com/item?id=49265648</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 11 Aug 2026 22:58:55 +0000</pubDate><link>https://dl.acm.org/doi/10.1145/3789240.3829175</link><dc:creator>matt_d</dc:creator><comments>https://news.ycombinator.com/item?id=49265648</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49265648</guid></item><item><title><![CDATA[A Preliminary Study on Simultaneous Coscheduling for Discrete GPU vs. Fused GPU]]></title><description><![CDATA[
<p>Article URL: <a href="https://arxiv.org/abs/2608.09647">https://arxiv.org/abs/2608.09647</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49262243">https://news.ycombinator.com/item?id=49262243</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 11 Aug 2026 18:12:44 +0000</pubDate><link>https://arxiv.org/abs/2608.09647</link><dc:creator>matt_d</dc:creator><comments>https://news.ycombinator.com/item?id=49262243</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49262243</guid></item><item><title><![CDATA[New comment by matt_d in "Scope and Lifetime Restrictions in Swift"]]></title><description><![CDATA[
<p>Context: <a href="https://hachyderm.io/@rjmccall/117073259835476299" rel="nofollow">https://hachyderm.io/@rjmccall/117073259835476299</a><p>"We've been thinking about a lot about the language design of expressing lifetime  restrictions and dependencies for non-escapable types in Swift, and I put all that into a long and somewhat rambling design paper which folks might find interesting."</p>
]]></description><pubDate>Tue, 11 Aug 2026 07:22:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=49254506</link><dc:creator>matt_d</dc:creator><comments>https://news.ycombinator.com/item?id=49254506</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49254506</guid></item><item><title><![CDATA[Scope and Lifetime Restrictions in Swift]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/rjmccall/swift-evolution/blob/scope-restrictions/scope-restriction-models.md">https://github.com/rjmccall/swift-evolution/blob/scope-restrictions/scope-restriction-models.md</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49254505">https://news.ycombinator.com/item?id=49254505</a></p>
<p>Points: 2</p>
<p># Comments: 1</p>
]]></description><pubDate>Tue, 11 Aug 2026 07:22:03 +0000</pubDate><link>https://github.com/rjmccall/swift-evolution/blob/scope-restrictions/scope-restriction-models.md</link><dc:creator>matt_d</dc:creator><comments>https://news.ycombinator.com/item?id=49254505</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49254505</guid></item><item><title><![CDATA[RISC-V: Public Review for the RVA23.1 and RVB23.1 Profiles]]></title><description><![CDATA[
<p>Article URL: <a href="https://groups.google.com/a/groups.riscv.org/g/isa-dev/c/JBT5kq4ryLc">https://groups.google.com/a/groups.riscv.org/g/isa-dev/c/JBT5kq4ryLc</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49254110">https://news.ycombinator.com/item?id=49254110</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 11 Aug 2026 06:29:54 +0000</pubDate><link>https://groups.google.com/a/groups.riscv.org/g/isa-dev/c/JBT5kq4ryLc</link><dc:creator>matt_d</dc:creator><comments>https://news.ycombinator.com/item?id=49254110</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49254110</guid></item><item><title><![CDATA[Cylic Trait Implementations: Motivation]]></title><description><![CDATA[
<p>Article URL: <a href="https://smallcultfollowing.com/babysteps/blog/2026/08/10/cyclic-trait-solving/">https://smallcultfollowing.com/babysteps/blog/2026/08/10/cyclic-trait-solving/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49254084">https://news.ycombinator.com/item?id=49254084</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 11 Aug 2026 06:25:51 +0000</pubDate><link>https://smallcultfollowing.com/babysteps/blog/2026/08/10/cyclic-trait-solving/</link><dc:creator>matt_d</dc:creator><comments>https://news.ycombinator.com/item?id=49254084</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49254084</guid></item><item><title><![CDATA[Moving integer division to floating-point is trivial]]></title><description><![CDATA[
<p>Article URL: <a href="http://marc-b-reynolds.github.io/math/2026/08/10/IntDivByFP.html">http://marc-b-reynolds.github.io/math/2026/08/10/IntDivByFP.html</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49253831">https://news.ycombinator.com/item?id=49253831</a></p>
<p>Points: 10</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 11 Aug 2026 05:48:56 +0000</pubDate><link>http://marc-b-reynolds.github.io/math/2026/08/10/IntDivByFP.html</link><dc:creator>matt_d</dc:creator><comments>https://news.ycombinator.com/item?id=49253831</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49253831</guid></item><item><title><![CDATA[Optimizing GEMM and Activation on CDNA4 with TLX]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.amd.com/en/developer/resources/technical-articles/2026/optimizing-gemm-with-tlx.html">https://www.amd.com/en/developer/resources/technical-articles/2026/optimizing-gemm-with-tlx.html</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49251319">https://news.ycombinator.com/item?id=49251319</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 10 Aug 2026 23:33:11 +0000</pubDate><link>https://www.amd.com/en/developer/resources/technical-articles/2026/optimizing-gemm-with-tlx.html</link><dc:creator>matt_d</dc:creator><comments>https://news.ycombinator.com/item?id=49251319</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49251319</guid></item><item><title><![CDATA[EvoHarnessRL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents]]></title><description><![CDATA[
<p>Article URL: <a href="https://arxiv.org/abs/2608.05446">https://arxiv.org/abs/2608.05446</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49249998">https://news.ycombinator.com/item?id=49249998</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 10 Aug 2026 21:28:07 +0000</pubDate><link>https://arxiv.org/abs/2608.05446</link><dc:creator>matt_d</dc:creator><comments>https://news.ycombinator.com/item?id=49249998</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49249998</guid></item><item><title><![CDATA[Optimizing an NVFP4 Blockscaled GEMM on RTX Pro 6000 Blackwell GPU (SM120)]]></title><description><![CDATA[
<p>Article URL: <a href="https://research.colfax-intl.com/optimizing-an-nvfp4-blockscaled-gemm-on-rtx-pro-6000-blackwell-gpu-sm120/">https://research.colfax-intl.com/optimizing-an-nvfp4-blockscaled-gemm-on-rtx-pro-6000-blackwell-gpu-sm120/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49248291">https://news.ycombinator.com/item?id=49248291</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 10 Aug 2026 19:11:55 +0000</pubDate><link>https://research.colfax-intl.com/optimizing-an-nvfp4-blockscaled-gemm-on-rtx-pro-6000-blackwell-gpu-sm120/</link><dc:creator>matt_d</dc:creator><comments>https://news.ycombinator.com/item?id=49248291</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49248291</guid></item><item><title><![CDATA[Let's Stop Calling Everything "Linear Attention"]]></title><description><![CDATA[
<p>Article URL: <a href="https://htor.inf.ethz.ch/blog/index.php/2026/08/09/lets-stop-calling-everything-linear-attention/">https://htor.inf.ethz.ch/blog/index.php/2026/08/09/lets-stop-calling-everything-linear-attention/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49240499">https://news.ycombinator.com/item?id=49240499</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 10 Aug 2026 07:33:43 +0000</pubDate><link>https://htor.inf.ethz.ch/blog/index.php/2026/08/09/lets-stop-calling-everything-linear-attention/</link><dc:creator>matt_d</dc:creator><comments>https://news.ycombinator.com/item?id=49240499</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49240499</guid></item></channel></rss>