<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: bigcat12345678</title><link>https://news.ycombinator.com/user?id=bigcat12345678</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Fri, 05 Jun 2026 02:55:42 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=bigcat12345678" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by bigcat12345678 in "The ways we contain Claude across products"]]></title><description><![CDATA[
<p>LLM clearly is broken by design when it's been personified, but I think "software" as we understood, is inevitably evolving into "personified entity" (I've left some notes in [1], which are AI generated).<p>There is also an interesting trend that the more personified brand is more dominant: Claude & Doubao vs ChatGPT & DeepSeek.<p>[1] <a href="https://github.com/NascentCore/agentic-suite/tree/main/personified_software" rel="nofollow">https://github.com/NascentCore/agentic-suite/tree/main/perso...</a></p>
]]></description><pubDate>Thu, 04 Jun 2026 08:04:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=48395622</link><dc:creator>bigcat12345678</dc:creator><comments>https://news.ycombinator.com/item?id=48395622</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48395622</guid></item><item><title><![CDATA[New comment by bigcat12345678 in "Artificial intelligence is not conscious"]]></title><description><![CDATA[
<p>I laugh<p>Consciousness is an invention in human language. Just like "cat", it's not a particularly more fundamental essence than any other concept in human language.<p>Its peculiarity is that it's at the pinnacle of abstraction hierarchy. So it's the most fitting to be toyed inside one's mind. Just like the concept of "God" which induces the most fantastic imagination of human mind, consciousness itself also induces the most fascinating thoughts in our modern world.<p>The progress is in human progress distilled into more efficient systems that advanced Universe's own structuredness.</p>
]]></description><pubDate>Thu, 04 Jun 2026 06:53:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=48395015</link><dc:creator>bigcat12345678</dc:creator><comments>https://news.ycombinator.com/item?id=48395015</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48395015</guid></item><item><title><![CDATA[New comment by bigcat12345678 in "Building Pi with Pi"]]></title><description><![CDATA[
<p>Because agents is different than conventional software:<p>1. They behave differently: non-deterministic vs deterministic<p>2. They have different mechanism: harness+llms vs codes+apis<p>3. They have different interfaces: clicking vs chatting<p>They are like boston dynamics robots vs humans</p>
]]></description><pubDate>Mon, 25 May 2026 07:59:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=48264510</link><dc:creator>bigcat12345678</dc:creator><comments>https://news.ycombinator.com/item?id=48264510</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48264510</guid></item><item><title><![CDATA[New comment by bigcat12345678 in "Building Pi with Pi"]]></title><description><![CDATA[
<p>My feeling is that building agent with agent will be the first stable & mature software development pattern emerging. I reached that in several forward-looking induction:<p>1. If agent is continuing the path to trivialize software development, which appears the case given LLMs can generate better quality code than humans almost for free & instantly given the right context, then using agent to develop software is going to happen, but that destroys the whole software industry as writing software is marginally free, that break the foundations of software industry<p>2. To continue making agent a commercially viable thing, it needs to develop more valuable artifacts. Then specialized agent will be the more valuable thing than software, as they offer a higher-level of output than existing software. And because the natural jagged pattern of LLM capability, one can use frontier model to develop domain-specialized agents with 1/10 the running cost. So agent writing agents makes economical sense.<p>3. In terms of knowledge, building agents is like managing highly-skilled team of humans to work on highly-unpredicatble requirements, just like companies are built on top of the thesis that a group of human offer better value than one do that themselves, a team building agents essientially can produce specialized agents for other company to mix & match & optimize, sot that also makes economical sense.<p>4. Engineering-wise building agents with agent essentially is a different skill patterns than building software with agents, It's like the difference between building commercial software vs building hobby software. That makes engineering sense to have agents building agent as the dominant pattern of software development.<p>WDYT?</p>
]]></description><pubDate>Mon, 25 May 2026 04:52:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=48263499</link><dc:creator>bigcat12345678</dc:creator><comments>https://news.ycombinator.com/item?id=48263499</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48263499</guid></item><item><title><![CDATA[New comment by bigcat12345678 in "We've made the world too complicated"]]></title><description><![CDATA[
<p>Echo words here.<p>Modern worlds are led by traumatized, through pathological education and media propaganda, with a undertone of those being hurt and damaged to fear for others suffering the same (while they subconsciously are aware that their suffering is actually their own misfortune that are not actually shared to 90% of the population).<p>I am still feeling that the overall goodness is still the dominant the human trajectory. Even the  traumatized leaders know instinctually when they are close to a sane & happy person. The force of life's energy seems inescapable, like the quantum fabrics that waves everyone's whole existence.</p>
]]></description><pubDate>Sun, 17 May 2026 04:24:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=48166034</link><dc:creator>bigcat12345678</dc:creator><comments>https://news.ycombinator.com/item?id=48166034</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48166034</guid></item><item><title><![CDATA[New comment by bigcat12345678 in "Can a Language Model Paint?"]]></title><description><![CDATA[
<p>what things create?<p>From what I understand from physics, matters are there, nothing can be created. A vague memory of quantum physics hints matters out of vacuum, but my affirmation of that thought is less firm than the classic preservation laws.</p>
]]></description><pubDate>Thu, 14 May 2026 06:22:25 +0000</pubDate><link>https://news.ycombinator.com/item?id=48131787</link><dc:creator>bigcat12345678</dc:creator><comments>https://news.ycombinator.com/item?id=48131787</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48131787</guid></item><item><title><![CDATA[New comment by bigcat12345678 in "Leaving GitHub for Forgejo"]]></title><description><![CDATA[
<p>I am very happy to discover this.<p>Given the trending-to-zero software writing cost, a local self-contained source code management tool would be natural for delivering software, i.e., software becomes an agent with specialized code as its harness (in addition to its default ones) source control would be one default tool for the agentic software to manage its own evolution.</p>
]]></description><pubDate>Thu, 14 May 2026 04:01:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=48130963</link><dc:creator>bigcat12345678</dc:creator><comments>https://news.ycombinator.com/item?id=48130963</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48130963</guid></item><item><title><![CDATA[New comment by bigcat12345678 in "Mythos Finds a Curl Vulnerability"]]></title><description><![CDATA[
<p>My guess:<p>Marketing is not intentional.<p>Evidences: 10 years ago, when I interviewed Baidu AI with Andrew Ng and Dario, Dario is the kind of person is pure-hearted to the point being ideological. Given Dario's successful career so far, that essence has gradually grown into a conviction, and surrounded by a purposely built team which amplifies his ideology.<p>Humans are very convenient creature, a rare few small fraction of them are no doubt the master of convenience: they morph their mental manifold without a hint of contradiction in their own mental mechanisms.</p>
]]></description><pubDate>Mon, 11 May 2026 09:45:01 +0000</pubDate><link>https://news.ycombinator.com/item?id=48092923</link><dc:creator>bigcat12345678</dc:creator><comments>https://news.ycombinator.com/item?id=48092923</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48092923</guid></item><item><title><![CDATA[New comment by bigcat12345678 in "Eight years of wanting, three months of building with AI"]]></title><description><![CDATA[
<p>> Unfortunately, unlike many other languages, SQLite has no formal specification describing how it should be parsed.<p>BorgCfg had exactly the same situation.<p>mpvl (borgcfg original author, author of <a href="https://cuelang.org/" rel="nofollow">https://cuelang.org/</a>) and others had tried to refine bcl while bcl itself is underspecified.<p>Eventually, the team built a drop-in replacement of bcl and specced out the language almost entirely.<p>The biggest lesson to me was that engineering never has any short cut.</p>
]]></description><pubDate>Mon, 06 Apr 2026 02:03:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=47656149</link><dc:creator>bigcat12345678</dc:creator><comments>https://news.ycombinator.com/item?id=47656149</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47656149</guid></item><item><title><![CDATA[New comment by bigcat12345678 in "AI boom risks widening wealth divide, says BlackRock's Larry Fink"]]></title><description><![CDATA[
<p>Isn't this why this statement should be taken seriously?
But your statement implies the opposite, which is to ignore Larry Fink's warning. That appears irrational.</p>
]]></description><pubDate>Tue, 24 Mar 2026 01:49:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=47497726</link><dc:creator>bigcat12345678</dc:creator><comments>https://news.ycombinator.com/item?id=47497726</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47497726</guid></item><item><title><![CDATA[New comment by bigcat12345678 in "Let's discuss sandbox isolation"]]></title><description><![CDATA[
<p>Unikernel/libos is relevant</p>
]]></description><pubDate>Sat, 28 Feb 2026 02:36:34 +0000</pubDate><link>https://news.ycombinator.com/item?id=47189439</link><dc:creator>bigcat12345678</dc:creator><comments>https://news.ycombinator.com/item?id=47189439</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47189439</guid></item><item><title><![CDATA[New comment by bigcat12345678 in "The path to ubiquitous AI (17k tokens/sec)"]]></title><description><![CDATA[
<p>I am thinking if this can be a low-level substrate for composing <i>dumb</i> LLMs into smart swarm, theoretically:<p>1. A whole with disparate parts (<i>smart</i> and <i>dumb</i> components) are almost always more cost-effective to reach a given target of performance
2. With that, a whole with disparate parts, are almost always more performant with the same cost<p>A few inspiration:<p>1. Human body is <i>intelligent</i> composed of so diverse parts
2. Swarm intelligence of insects and small animals are certainly beyond current understanding<p>The cost and speed of this thing is on point to make such a whole composed diverse parts possible.</p>
]]></description><pubDate>Sat, 21 Feb 2026 19:22:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=47103781</link><dc:creator>bigcat12345678</dc:creator><comments>https://news.ycombinator.com/item?id=47103781</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47103781</guid></item><item><title><![CDATA[New comment by bigcat12345678 in "Monty: A minimal, secure Python interpreter written in Rust for use by AI"]]></title><description><![CDATA[
<p>It seems that AI finally give the space to true pure-blood system software systems to unleash their potential.<p>Pretty much all morn software tooling, removing the parts that aim at appeal to humans, becomes much more reliable tools. But it's not clear if the performance will be better or not.</p>
]]></description><pubDate>Sat, 07 Feb 2026 04:24:29 +0000</pubDate><link>https://news.ycombinator.com/item?id=46921280</link><dc:creator>bigcat12345678</dc:creator><comments>https://news.ycombinator.com/item?id=46921280</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46921280</guid></item><item><title><![CDATA[New comment by bigcat12345678 in "OpenCiv3: Open-source, cross-platform reimagining of Civilization III"]]></title><description><![CDATA[
<p>Yes CIV3 still feels to me the peak Civ experience.<p>The content is a bit lacking though, would see more diversity in tech tree, and units.</p>
]]></description><pubDate>Fri, 06 Feb 2026 23:21:01 +0000</pubDate><link>https://news.ycombinator.com/item?id=46919531</link><dc:creator>bigcat12345678</dc:creator><comments>https://news.ycombinator.com/item?id=46919531</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46919531</guid></item><item><title><![CDATA[New comment by bigcat12345678 in "Claude Code for Infrastructure"]]></title><description><![CDATA[
<p>This is the most plausible tool for vibe infra I can think of</p>
]]></description><pubDate>Wed, 04 Feb 2026 22:50:34 +0000</pubDate><link>https://news.ycombinator.com/item?id=46893017</link><dc:creator>bigcat12345678</dc:creator><comments>https://news.ycombinator.com/item?id=46893017</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46893017</guid></item><item><title><![CDATA[New comment by bigcat12345678 in "ManusAI Joins Meta"]]></title><description><![CDATA[
<p>> It’s just that Manus is particularly egregious in their false advertising, and their bullshit is an insult to people doing actual heavy lifting, like DeepSeek or Alibaba Qwen team.<p>I still felt this baseless.<p>Manus at the time is break through result. Are they egregious in advertising they being deepseek moment? I don't know think so. Is it a marketing ploy? Yes, but it's far less egregious than any normal AI startup, like cluely.<p>Comparing to deepseek or qwen, heavy lifting what? Manus is built on Claude at the time it's doing egregious marketing, how can it be considered heavy lifted by unrelated products. What's the point you want to make?</p>
]]></description><pubDate>Wed, 31 Dec 2025 08:41:02 +0000</pubDate><link>https://news.ycombinator.com/item?id=46442461</link><dc:creator>bigcat12345678</dc:creator><comments>https://news.ycombinator.com/item?id=46442461</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46442461</guid></item><item><title><![CDATA[New comment by bigcat12345678 in "ManusAI Joins Meta"]]></title><description><![CDATA[
<p>If it has nothing to do with being Chinese founded, then why it stated obviously baseless statements without objections until myself pointed out the facts. I mean, manus is top tier by any measure in the startup scene, and someone just say that it's a joke, then sane people's immediate reaction should be asking why, right?<p>Why suddenly it becomes automatically accepted, other than being a Chinese founded startup, tell me, what else can prompts such mental inconsistency?</p>
]]></description><pubDate>Tue, 30 Dec 2025 15:17:07 +0000</pubDate><link>https://news.ycombinator.com/item?id=46434118</link><dc:creator>bigcat12345678</dc:creator><comments>https://news.ycombinator.com/item?id=46434118</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46434118</guid></item><item><title><![CDATA[New comment by bigcat12345678 in "ManusAI Joins Meta"]]></title><description><![CDATA[
<p>A failed demo discounted a entire 100mm arr?</p>
]]></description><pubDate>Tue, 30 Dec 2025 15:01:46 +0000</pubDate><link>https://news.ycombinator.com/item?id=46433951</link><dc:creator>bigcat12345678</dc:creator><comments>https://news.ycombinator.com/item?id=46433951</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46433951</guid></item><item><title><![CDATA[New comment by bigcat12345678 in "ManusAI Joins Meta"]]></title><description><![CDATA[
<p>I don't get it<p>Riding a wave of industry is literally the foundation of startups paradiam itself. Why it suddenly became a sin for a Chinese founded startup?<p>This is exactly the disgusting bias (even to the point of racism) I mostly pointed out.<p>It's like everyone automatically applied double standards to Chinese founded startup and not even admit that under such influence.</p>
]]></description><pubDate>Tue, 30 Dec 2025 15:00:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=46433940</link><dc:creator>bigcat12345678</dc:creator><comments>https://news.ycombinator.com/item?id=46433940</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46433940</guid></item><item><title><![CDATA[New comment by bigcat12345678 in "ManusAI Joins Meta"]]></title><description><![CDATA[
<p>> People literally built OpenManus the next day after Manus' launch marketing went viral to demonstrate the point.<p>I tried openmanus and I frowned at openmanus team's intentionally attention grabbing gimmick after manus' overnight success, and open manus does not work at the moment.</p>
]]></description><pubDate>Tue, 30 Dec 2025 07:45:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=46430619</link><dc:creator>bigcat12345678</dc:creator><comments>https://news.ycombinator.com/item?id=46430619</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46430619</guid></item></channel></rss>