<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: rockwotj</title><link>https://news.ycombinator.com/user?id=rockwotj</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Tue, 16 Jun 2026 04:42:54 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=rockwotj" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by rockwotj in "/architect: Reduce Fable tokens by 80%, Fable orchestrates/reviews, Codex builds"]]></title><description><![CDATA[
<p>I actually just started doing this by having Fable roleplay as Jeff Dean and to use Codex as Sanjay driving the implementation and have them go back and forth. Works really well and it’s cool to see AI pair program</p>
]]></description><pubDate>Sat, 13 Jun 2026 00:40:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=48511026</link><dc:creator>rockwotj</dc:creator><comments>https://news.ycombinator.com/item?id=48511026</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48511026</guid></item><item><title><![CDATA[New comment by rockwotj in "Show HN: Hm – a task runner with a Python DSL, growing into a CI/CD system"]]></title><description><![CDATA[
<p>This seems really great! I am a long time Bazel fan, but it’s not perfect, and I have always thought there was something simpler than bazel that would give a lot of these kinds of benefits. Having something that works for a hybrid rust/typescript codebase would be great.<p>I encourage you for you dev command to work with frontend setups like vite so it’s unified with backends and still supports HMR</p>
]]></description><pubDate>Thu, 28 May 2026 01:11:08 +0000</pubDate><link>https://news.ycombinator.com/item?id=48303004</link><dc:creator>rockwotj</dc:creator><comments>https://news.ycombinator.com/item?id=48303004</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48303004</guid></item><item><title><![CDATA[New comment by rockwotj in "The fastest Linux timestamps"]]></title><description><![CDATA[
<p>IIRC (it’s been awhile) this was an optimization that was inspired by someone noticing all of Google spent a lot of time in vDSO using <a href="https://research.google/pubs/google-wide-profiling-a-continuous-profiling-infrastructure-for-data-centers/" rel="nofollow">https://research.google/pubs/google-wide-profiling-a-continu...</a>
Google generally doesn’t have any (well that I have ever heard of) hard realtime requirements like the high frequency trading or HPC systems do.<p>Cool stuff thanks for sharing!</p>
]]></description><pubDate>Mon, 27 Apr 2026 11:12:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=47920106</link><dc:creator>rockwotj</dc:creator><comments>https://news.ycombinator.com/item?id=47920106</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47920106</guid></item><item><title><![CDATA[New comment by rockwotj in "The fastest Linux timestamps"]]></title><description><![CDATA[
<p>Related reading is absl’s linear approximation of gettime from cycle counters, which I thought is a neat trick: <a href="https://github.com/abseil/abseil-cpp/blob/351086314d46e73d430296c9eca1f6d6c0372cd1/absl/time/clock.cc#L289" rel="nofollow">https://github.com/abseil/abseil-cpp/blob/351086314d46e73d43...</a></p>
]]></description><pubDate>Mon, 27 Apr 2026 02:39:16 +0000</pubDate><link>https://news.ycombinator.com/item?id=47917136</link><dc:creator>rockwotj</dc:creator><comments>https://news.ycombinator.com/item?id=47917136</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47917136</guid></item><item><title><![CDATA[New comment by rockwotj in "Zindex – Diagram Infrastructure for Agents"]]></title><description><![CDATA[
<p>> Production-grade
17 operation types. 40+ semantic validation rules. Auth, rate limiting, PostgreSQL storage.<p>Man where in the LLM training data did the “production ready “ come from? That whole list screams AI. Humans want social proof, not a list.</p>
]]></description><pubDate>Wed, 22 Apr 2026 02:21:28 +0000</pubDate><link>https://news.ycombinator.com/item?id=47858009</link><dc:creator>rockwotj</dc:creator><comments>https://news.ycombinator.com/item?id=47858009</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47858009</guid></item><item><title><![CDATA[New comment by rockwotj in "Google's 200M-parameter time-series foundation model with 16k context"]]></title><description><![CDATA[
<p><a href="https://www.datadoghq.com/blog/datadog-time-series-foundation-model/" rel="nofollow">https://www.datadoghq.com/blog/datadog-time-series-foundatio...</a><p><a href="https://moment-timeseries-foundation-model.github.io/" rel="nofollow">https://moment-timeseries-foundation-model.github.io/</a><p><a href="https://arxiv.org/abs/2403.07815" rel="nofollow">https://arxiv.org/abs/2403.07815</a><p>A friend at work used one to predict when our CEO would post in Slack, which is verry entertaining to see if correct.</p>
]]></description><pubDate>Tue, 31 Mar 2026 06:00:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=47583289</link><dc:creator>rockwotj</dc:creator><comments>https://news.ycombinator.com/item?id=47583289</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47583289</guid></item><item><title><![CDATA[New comment by rockwotj in "Google's 200M-parameter time-series foundation model with 16k context"]]></title><description><![CDATA[
<p>Probably the better link: <a href="https://research.google/blog/a-decoder-only-foundation-model-for-time-series-forecasting/" rel="nofollow">https://research.google/blog/a-decoder-only-foundation-model...</a></p>
]]></description><pubDate>Tue, 31 Mar 2026 05:56:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=47583267</link><dc:creator>rockwotj</dc:creator><comments>https://news.ycombinator.com/item?id=47583267</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47583267</guid></item><item><title><![CDATA[New comment by rockwotj in "Meta acquires Moltbook"]]></title><description><![CDATA[
<p>> which isn't saying that much<p>I mean I also think this move doesn’t make sense, but I always find these type of comments interesting. Do people think they could do better in Mark’s shoes?</p>
]]></description><pubDate>Tue, 10 Mar 2026 17:48:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=47326533</link><dc:creator>rockwotj</dc:creator><comments>https://news.ycombinator.com/item?id=47326533</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47326533</guid></item><item><title><![CDATA[New comment by rockwotj in "Glaze by Raycast"]]></title><description><![CDATA[
<p>Or it’s compiled in the cloud?</p>
]]></description><pubDate>Wed, 04 Mar 2026 13:48:10 +0000</pubDate><link>https://news.ycombinator.com/item?id=47247359</link><dc:creator>rockwotj</dc:creator><comments>https://news.ycombinator.com/item?id=47247359</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47247359</guid></item><item><title><![CDATA[New comment by rockwotj in "Glaze by Raycast"]]></title><description><![CDATA[
<p>One would think it must otherwise there are all these issues with compiling, signing tc if they don’t have xcode installed etc. I would guess it’s some webview wrapper with a layer to expose desktop app functionality</p>
]]></description><pubDate>Wed, 04 Mar 2026 13:47:54 +0000</pubDate><link>https://news.ycombinator.com/item?id=47247354</link><dc:creator>rockwotj</dc:creator><comments>https://news.ycombinator.com/item?id=47247354</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47247354</guid></item><item><title><![CDATA[New comment by rockwotj in "Show HN: I built a sub-500ms latency voice agent from scratch"]]></title><description><![CDATA[
<p>Fundamentally, the "guessing when its your turn thing" needs to be baked into the model. I think the full duplex mode that Moshi pioneered is probably where the puck is going to end up: <a href="https://arxiv.org/abs/2410.00037" rel="nofollow">https://arxiv.org/abs/2410.00037</a></p>
]]></description><pubDate>Tue, 03 Mar 2026 03:01:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=47227431</link><dc:creator>rockwotj</dc:creator><comments>https://news.ycombinator.com/item?id=47227431</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47227431</guid></item><item><title><![CDATA[New comment by rockwotj in "Tasklet Instant Apps"]]></title><description><![CDATA[
<p>A category of SaaS companies are cooked in the age of AI - why not just have the perfect purpose built thing instead of fighting bloated enterprise software with a billion customizations and knobs that makes everything complicated?</p>
]]></description><pubDate>Thu, 26 Feb 2026 18:12:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=47169765</link><dc:creator>rockwotj</dc:creator><comments>https://news.ycombinator.com/item?id=47169765</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47169765</guid></item><item><title><![CDATA[Tasklet Instant Apps]]></title><description><![CDATA[
<p>Article URL: <a href="https://tasklet.ai/release-notes#instant-apps">https://tasklet.ai/release-notes#instant-apps</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47169764">https://news.ycombinator.com/item?id=47169764</a></p>
<p>Points: 3</p>
<p># Comments: 1</p>
]]></description><pubDate>Thu, 26 Feb 2026 18:12:59 +0000</pubDate><link>https://tasklet.ai/release-notes#instant-apps</link><dc:creator>rockwotj</dc:creator><comments>https://news.ycombinator.com/item?id=47169764</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47169764</guid></item><item><title><![CDATA[What If LLMs Could See Trust Boundaries?]]></title><description><![CDATA[
<p>Article URL: <a href="https://rockwotj.com/blog/llm-trust-boundaries/">https://rockwotj.com/blog/llm-trust-boundaries/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47095169">https://news.ycombinator.com/item?id=47095169</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 20 Feb 2026 22:53:36 +0000</pubDate><link>https://rockwotj.com/blog/llm-trust-boundaries/</link><dc:creator>rockwotj</dc:creator><comments>https://news.ycombinator.com/item?id=47095169</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47095169</guid></item><item><title><![CDATA[New comment by rockwotj in "I’m joining OpenAI"]]></title><description><![CDATA[
<p>I am sure they made a bid. The blog makes it sounds like he talked to multiple labs.</p>
]]></description><pubDate>Sun, 15 Feb 2026 22:30:25 +0000</pubDate><link>https://news.ycombinator.com/item?id=47028376</link><dc:creator>rockwotj</dc:creator><comments>https://news.ycombinator.com/item?id=47028376</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47028376</guid></item><item><title><![CDATA[New comment by rockwotj in "I’m joining OpenAI"]]></title><description><![CDATA[
<p>Technology does not determine the success of a company. I’ve seen amazing tech fail, and things strapped together with ducktape and bubblegum be a wild success.</p>
]]></description><pubDate>Sun, 15 Feb 2026 22:28:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=47028357</link><dc:creator>rockwotj</dc:creator><comments>https://news.ycombinator.com/item?id=47028357</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47028357</guid></item><item><title><![CDATA[New comment by rockwotj in "We interfaced single-threaded C++ with multi-threaded Rust"]]></title><description><![CDATA[
<p><a href="https://rockwotj.com/blog/async-wasm-in-seastar/" rel="nofollow">https://rockwotj.com/blog/async-wasm-in-seastar/</a> - been meaning to write about this for a long time. Thanks for the nudge :)</p>
]]></description><pubDate>Sat, 14 Feb 2026 03:51:29 +0000</pubDate><link>https://news.ycombinator.com/item?id=47011366</link><dc:creator>rockwotj</dc:creator><comments>https://news.ycombinator.com/item?id=47011366</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47011366</guid></item><item><title><![CDATA[New comment by rockwotj in "We interfaced single-threaded C++ with multi-threaded Rust"]]></title><description><![CDATA[
<p>I have done this integrating wasmtime into a a C++ seastar.io application. I’ll have to write a post about it</p>
]]></description><pubDate>Fri, 13 Feb 2026 12:55:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=47002194</link><dc:creator>rockwotj</dc:creator><comments>https://news.ycombinator.com/item?id=47002194</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47002194</guid></item><item><title><![CDATA[New comment by rockwotj in "Gemini 3 Deep Think"]]></title><description><![CDATA[
<p>Claude is king for agentic workflows right now because it’s amazing at tool calling and following instructions well (among other things)</p>
]]></description><pubDate>Fri, 13 Feb 2026 01:22:07 +0000</pubDate><link>https://news.ycombinator.com/item?id=46997765</link><dc:creator>rockwotj</dc:creator><comments>https://news.ycombinator.com/item?id=46997765</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46997765</guid></item><item><title><![CDATA[New comment by rockwotj in "Ex-GitHub CEO launches a new developer platform for AI agents"]]></title><description><![CDATA[
<p>I thought everyone was just using open telemetry traces for this? This is just a classic observability problem that isn’t unique with agents. More important yes, but not unique functionally.</p>
]]></description><pubDate>Wed, 11 Feb 2026 02:46:21 +0000</pubDate><link>https://news.ycombinator.com/item?id=46970114</link><dc:creator>rockwotj</dc:creator><comments>https://news.ycombinator.com/item?id=46970114</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46970114</guid></item></channel></rss>