<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: justatdotin</title><link>https://news.ycombinator.com/user?id=justatdotin</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Tue, 21 Jul 2026 19:35:28 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=justatdotin" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by justatdotin in "Nativ: Run frontier open models locally on your Mac"]]></title><description><![CDATA[
<p>Hi Simon, sorry to spam your comments but 7 months ago you asked me for a media report to back a claim I made and this week it finally arrived. perhaps a little late to be very useful to anyone who maintains that gating function, but here nonetheless:<p><a href="https://ntindependent.com.au/scientist-says-ministers-pole-flip-and-earth-axis-tilt-water-claims-are-false/" rel="nofollow">https://ntindependent.com.au/scientist-says-ministers-pole-f...</a></p>
]]></description><pubDate>Tue, 21 Jul 2026 03:11:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=48987607</link><dc:creator>justatdotin</dc:creator><comments>https://news.ycombinator.com/item?id=48987607</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48987607</guid></item><item><title><![CDATA[New comment by justatdotin in "DOOMQL – what if SQLite were the game engine?"]]></title><description><![CDATA[
<p>speaking of doom,<p><a href="https://ntindependent.com.au/scientist-says-ministers-pole-flip-and-earth-axis-tilt-water-claims-are-false/" rel="nofollow">https://ntindependent.com.au/scientist-says-ministers-pole-f...</a></p>
]]></description><pubDate>Mon, 20 Jul 2026 23:50:29 +0000</pubDate><link>https://news.ycombinator.com/item?id=48986389</link><dc:creator>justatdotin</dc:creator><comments>https://news.ycombinator.com/item?id=48986389</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48986389</guid></item><item><title><![CDATA[New comment by justatdotin in "Qwen 3.8"]]></title><description><![CDATA[
<p>now do usa</p>
]]></description><pubDate>Sun, 19 Jul 2026 23:36:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=48972708</link><dc:creator>justatdotin</dc:creator><comments>https://news.ycombinator.com/item?id=48972708</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48972708</guid></item><item><title><![CDATA[Optional standards dont cut it]]></title><description><![CDATA[
<p>Article URL: <a href="https://nt-ai-dc.info">https://nt-ai-dc.info</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48893309">https://news.ycombinator.com/item?id=48893309</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 13 Jul 2026 14:29:43 +0000</pubDate><link>https://nt-ai-dc.info</link><dc:creator>justatdotin</dc:creator><comments>https://news.ycombinator.com/item?id=48893309</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48893309</guid></item><item><title><![CDATA[New comment by justatdotin in "The Graph That Should Be Front-Page News"]]></title><description><![CDATA[
<p>Tjanara Goreng Goreng did nothing rong.<p>#LiarDreaming</p>
]]></description><pubDate>Mon, 13 Jul 2026 14:27:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=48893274</link><dc:creator>justatdotin</dc:creator><comments>https://news.ycombinator.com/item?id=48893274</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48893274</guid></item><item><title><![CDATA[New comment by justatdotin in "2025: The Year in LLMs"]]></title><description><![CDATA[
<p>how is that a personal attack?<p>a personal attack would be eg calling him a DC.<p>all I did was point out the intellectual dishonesty of his argument. that's an attack on his intellectually dishonest argument, not his person.<p>by all means go ahead and ban me</p>
]]></description><pubDate>Thu, 01 Jan 2026 03:18:55 +0000</pubDate><link>https://news.ycombinator.com/item?id=46450980</link><dc:creator>justatdotin</dc:creator><comments>https://news.ycombinator.com/item?id=46450980</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46450980</guid></item><item><title><![CDATA[New comment by justatdotin in "Resistance training load does not determine hypertrophy"]]></title><description><![CDATA[
<p>isnt the 1RM the measure of progress?</p>
]]></description><pubDate>Thu, 01 Jan 2026 00:55:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=46450077</link><dc:creator>justatdotin</dc:creator><comments>https://news.ycombinator.com/item?id=46450077</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46450077</guid></item><item><title><![CDATA[New comment by justatdotin in "Toro: Deploy Applications as Unikernels"]]></title><description><![CDATA[
<p>anywhere you want hard isolation and only a subset of OS. especially multiple instances thereof.<p>so, generally at the edge (gateways, shims, protocol boundaries)</p>
]]></description><pubDate>Wed, 31 Dec 2025 07:44:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=46442231</link><dc:creator>justatdotin</dc:creator><comments>https://news.ycombinator.com/item?id=46442231</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46442231</guid></item><item><title><![CDATA[New comment by justatdotin in "Toro: Deploy Applications as Unikernels"]]></title><description><![CDATA[
<p>container can be smaller at rest, but larger at runtime<p>if you're not sure which you want its probably container</p>
]]></description><pubDate>Wed, 31 Dec 2025 07:41:01 +0000</pubDate><link>https://news.ycombinator.com/item?id=46442211</link><dc:creator>justatdotin</dc:creator><comments>https://news.ycombinator.com/item?id=46442211</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46442211</guid></item><item><title><![CDATA[New comment by justatdotin in "LLVM AI tool policy: human in the loop"]]></title><description><![CDATA[
<p>one reason i can imagine for this choice is that human review distributes new knowledge among human maintainers. Automated review might discourage that valuable interaction.<p>The comment is an artefact of an inherently valuable process, not the sole objective. So I'd prefer code is reviewed by a human who maybe initiates a discussion with an agent. I'd hope this minor workflow detail encourages the human to take a more active lead, rather than risk mere ceremonial approval.</p>
]]></description><pubDate>Wed, 31 Dec 2025 05:14:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=46441546</link><dc:creator>justatdotin</dc:creator><comments>https://news.ycombinator.com/item?id=46441546</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46441546</guid></item><item><title><![CDATA[New comment by justatdotin in "AI is forcing us to write good code"]]></title><description><![CDATA[
<p>oh yeah well that's an extreme example of how one dev's use could overwhelm a team's capacity.</p>
]]></description><pubDate>Tue, 30 Dec 2025 03:21:50 +0000</pubDate><link>https://news.ycombinator.com/item?id=46429169</link><dc:creator>justatdotin</dc:creator><comments>https://news.ycombinator.com/item?id=46429169</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46429169</guid></item><item><title><![CDATA[New comment by justatdotin in "AI is forcing us to write good code"]]></title><description><![CDATA[
<p>Hi, the reason I have this expectation is that on a (cognitively) diverse team there will be a range of reactions that all need to be accommodated.<p>some (many?) devs don't want agents. Either because the agent takes away the 'fun' part of their work, or because they don't trust the agent, or because they truly do not find a use for it in their process.<p>I remember being on teams which only remained functional because two devs tried very hard to stay out of one another's way. Nothing wrong with either of them, their approach to the work was just not very compatible.<p>In the same way, I expect diverse teams to struggle with finding a mode of adoption that does not negatively impact on the existing styles of some members.</p>
]]></description><pubDate>Tue, 30 Dec 2025 02:38:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=46428889</link><dc:creator>justatdotin</dc:creator><comments>https://news.ycombinator.com/item?id=46428889</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46428889</guid></item><item><title><![CDATA[New comment by justatdotin in "Karpathy on Programming: “I've never felt this much behind”"]]></title><description><![CDATA[
<p>I think it's mistaken to think in terms of 'falling behind' or 'catching up'<p>I've seen that these tools have different uses for different devs. I know on my current team, each of us devs works very differently to one another, and we make significant allowances to accommodate for one another's different styles. Certain tasks always go to certain devs; one dev is like a steel trap, another is the chaos explorer, another's a beginner, another has great big-picture perspective, etc. (not sure why but there's even space for myself ;)<p>In the same way, different devs use these powerful tools in very different ways. So don't imagine you're falling behind, because the only useful benchmark is yourself. And don't imagine you can wait for consensus: you'll still need to identify your personal relationship to the tools.<p>Most of all, don't be discouraged. Even if you never embrace these tools, there will remain space for your skills and your style of approaching our shared work.<p>Give it another 10 years and I'm sure this will all become clearer...</p>
]]></description><pubDate>Tue, 30 Dec 2025 02:30:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=46428830</link><dc:creator>justatdotin</dc:creator><comments>https://news.ycombinator.com/item?id=46428830</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46428830</guid></item><item><title><![CDATA[New comment by justatdotin in "AI is forcing us to write good code"]]></title><description><![CDATA[
<p>it is MUCH easier for solo devs to get agents to work for them than it is for teams to get agents to work for them.</p>
]]></description><pubDate>Tue, 30 Dec 2025 00:06:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=46427761</link><dc:creator>justatdotin</dc:creator><comments>https://news.ycombinator.com/item?id=46427761</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46427761</guid></item><item><title><![CDATA[New comment by justatdotin in "Two strangers. A terrorist bomb. An extraordinary tale of courage"]]></title><description><![CDATA[
<p>I've shed more tears in the past two weeks than I have in my 40 years of adult life.<p>forget: there I go again.<p>kindness beats terror.</p>
]]></description><pubDate>Mon, 29 Dec 2025 02:07:50 +0000</pubDate><link>https://news.ycombinator.com/item?id=46416670</link><dc:creator>justatdotin</dc:creator><comments>https://news.ycombinator.com/item?id=46416670</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46416670</guid></item><item><title><![CDATA[New comment by justatdotin in "Software engineers should be a little bit cynical"]]></title><description><![CDATA[
<p>I too am an aussie swe (just 3700km up the road) who likes lots of things about working (on a much lower rung) in big (well,  mid) tech. I have learned so much more in large orgs than startups, and I'm not done with it.<p>However:<p>We DO live in a late-stage-capitalist hellscape.<p>Large companies ARE run by aspiring robber barons who have no serious convictions beyond desiring power.<p>I have compromised my principles by giving them (or anyone) my labor.<p>but I don't lie to myself or anyone else about it. I don't find any need to rehabilitate the structural and personal failings I encounter. When my friends call me out for working at EvilCorp, I don't argue. I know it's like any job: it's all dirty money. Instead, I deal with reality: weigh up pros and cons. I judge each year just how much Corporate I'm willing to swallow to support my dependents.<p>I enjoy the author's redefinition of cynicism and optimism. These are useful ideas to consider and I've given it some thought, arriving at an attitude of Becoming that I guess some would call idealism.<p>PS OMFG I just realised its MS. I believe this is what the kids call cringe.</p>
]]></description><pubDate>Sun, 28 Dec 2025 22:56:22 +0000</pubDate><link>https://news.ycombinator.com/item?id=46415362</link><dc:creator>justatdotin</dc:creator><comments>https://news.ycombinator.com/item?id=46415362</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46415362</guid></item><item><title><![CDATA[New comment by justatdotin in "Rust the Process"]]></title><description><![CDATA[
<p>"Fortunately, I’m not that smart." - love that attitude.</p>
]]></description><pubDate>Sun, 28 Dec 2025 00:46:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=46407185</link><dc:creator>justatdotin</dc:creator><comments>https://news.ycombinator.com/item?id=46407185</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46407185</guid></item><item><title><![CDATA[New comment by justatdotin in "Show HN: Mysti – Claude, Codex, and Gemini debate your code, then synthesize"]]></title><description><![CDATA[
<p>multi-agent collaboration on planning is definitely really valuable. I lean in to gemini's long context and have it set up as a long-term observer who I consult about overall direction, project philosophy, patterns in fail and success, and prioritisation. This gives a different perspective from which to assess other agents' plans.</p>
]]></description><pubDate>Sun, 28 Dec 2025 00:13:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=46406945</link><dc:creator>justatdotin</dc:creator><comments>https://news.ycombinator.com/item?id=46406945</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46406945</guid></item><item><title><![CDATA[New comment by justatdotin in "Show HN: Mysti – Claude, Codex, and Gemini debate your code, then synthesize"]]></title><description><![CDATA[
<p>I think it is actually going to happen verrrrry slowly. but it will happen. Many many of my colleagues are understandably resisting. it will take a long time to balance out.</p>
]]></description><pubDate>Sun, 28 Dec 2025 00:00:29 +0000</pubDate><link>https://news.ycombinator.com/item?id=46406852</link><dc:creator>justatdotin</dc:creator><comments>https://news.ycombinator.com/item?id=46406852</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46406852</guid></item><item><title><![CDATA[New comment by justatdotin in "Backing up Spotify"]]></title><description><![CDATA[
<p>'LM are worse' is really not the strong vote of support you think it is.<p>More than two things can be utterly disgusting at the very same time!</p>
]]></description><pubDate>Wed, 24 Dec 2025 02:01:29 +0000</pubDate><link>https://news.ycombinator.com/item?id=46371669</link><dc:creator>justatdotin</dc:creator><comments>https://news.ycombinator.com/item?id=46371669</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46371669</guid></item></channel></rss>