<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: fullstackchris</title><link>https://news.ycombinator.com/user?id=fullstackchris</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 05 Aug 2026 02:08:32 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=fullstackchris" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by fullstackchris in "Pseudpocalypse"]]></title><description><![CDATA[
<p>a lot of these comments have no understanding of basic statistics. for example, did you know, at just 30 words of grammatically acceptable text, at least in english, youre already at more possible combinations of phrasings than atoms in the universe. you cant just throw a problem like that at LLMs and expect them to "just work"<p>folks should also look at burrows delta - i forgot which books but some folks were able to identify a ghost writer by stylometry alone.<p>ive said this on many threads, you cant just have text output from an llm (regardless of style / "pseudonym") and have it be "unique" because the nature of the transformer model itself is literally present in the output words. it will be detected as llm output every time. it has to be!<p>for pure anonymity, i suppose then it is an answer... for the actual craft and art style of writing it is not</p>
]]></description><pubDate>Fri, 17 Jul 2026 06:23:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=48943917</link><dc:creator>fullstackchris</dc:creator><comments>https://news.ycombinator.com/item?id=48943917</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48943917</guid></item><item><title><![CDATA[New comment by fullstackchris in "Fable 5 Is Back"]]></title><description><![CDATA[
<p>so... long term here meaning until the next frontier model comes out?</p>
]]></description><pubDate>Thu, 02 Jul 2026 02:28:26 +0000</pubDate><link>https://news.ycombinator.com/item?id=48755717</link><dc:creator>fullstackchris</dc:creator><comments>https://news.ycombinator.com/item?id=48755717</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48755717</guid></item><item><title><![CDATA[New comment by fullstackchris in "Previewing GPT‑5.6 Sol: a next-generation model"]]></title><description><![CDATA[
<p>"History doesn't echo - it is a distant early warning sign." - Leslie Harris</p>
]]></description><pubDate>Fri, 26 Jun 2026 22:25:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=48692778</link><dc:creator>fullstackchris</dc:creator><comments>https://news.ycombinator.com/item?id=48692778</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48692778</guid></item><item><title><![CDATA[New comment by fullstackchris in "Ask HN: Where is our profession (programmer) going?"]]></title><description><![CDATA[
<p>My profession is not, and never was, _programmer_. Lines of code—the actual text, is a means to an end, not an end in and of itself. I'll take heat for that here for sure. But do you think a carpenter considers himself "one who screws nails" or "glues joints"? No, the small minutiae of the job was never the job itself.</p>
]]></description><pubDate>Thu, 25 Jun 2026 05:19:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=48669266</link><dc:creator>fullstackchris</dc:creator><comments>https://news.ycombinator.com/item?id=48669266</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48669266</guid></item><item><title><![CDATA[New comment by fullstackchris in "Show HN: Are You in the Weights?"]]></title><description><![CDATA[
<p>I think its guys just who don't really understand how the internet works. I'm flabbergasted that its 2026 and I still see the "oh no my IP" trope.<p>If you're worried about it use a VPN.<p>Your ISP anyway knows your IP or at the very least your current one if its dynamic.</p>
]]></description><pubDate>Fri, 19 Jun 2026 04:40:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=48594824</link><dc:creator>fullstackchris</dc:creator><comments>https://news.ycombinator.com/item?id=48594824</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48594824</guid></item><item><title><![CDATA[New comment by fullstackchris in "Don't trust large context windows"]]></title><description><![CDATA[
<p>Thats another problem of this post, the author mentions Claude but not explicitely what models...<p>100k tokens "by lunch" is also not my finding, the newer models will hit that already right in the initial exploratory phase</p>
]]></description><pubDate>Sun, 14 Jun 2026 07:51:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=48525116</link><dc:creator>fullstackchris</dc:creator><comments>https://news.ycombinator.com/item?id=48525116</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48525116</guid></item><item><title><![CDATA[New comment by fullstackchris in "Statement on US government directive to suspend access to Fable 5 and Mythos 5"]]></title><description><![CDATA[
<p>lets be genuine here: those local models are no where near the capabilities of true modern llms like codex 5.5 and fable 5<p>but i also dont doubt in a few years time models with those benchmarks will be able to be run locally<p>still many many breakthroughs to be had</p>
]]></description><pubDate>Sat, 13 Jun 2026 06:47:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=48514159</link><dc:creator>fullstackchris</dc:creator><comments>https://news.ycombinator.com/item?id=48514159</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48514159</guid></item><item><title><![CDATA[New comment by fullstackchris in "They’re made out of weights"]]></title><description><![CDATA[
<p>The prose in the post is what I've been shouting from a rooftop since the LLM hype started.<p>Just tokens produced by weights.<p>Useful, but never forget that ground truth!</p>
]]></description><pubDate>Thu, 04 Jun 2026 05:39:41 +0000</pubDate><link>https://news.ycombinator.com/item?id=48394443</link><dc:creator>fullstackchris</dc:creator><comments>https://news.ycombinator.com/item?id=48394443</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48394443</guid></item><item><title><![CDATA[New comment by fullstackchris in "The Website Specification"]]></title><description><![CDATA[
<p>How can it know which tokens not to read without reading them? and llms.txt is a single file for the whole site... not the same</p>
]]></description><pubDate>Sun, 31 May 2026 21:43:42 +0000</pubDate><link>https://news.ycombinator.com/item?id=48350048</link><dc:creator>fullstackchris</dc:creator><comments>https://news.ycombinator.com/item?id=48350048</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48350048</guid></item><item><title><![CDATA[New comment by fullstackchris in "The Website Specification"]]></title><description><![CDATA[
<p>modern agents already do this via content negotiation and will attempt to retrieve the markdown version of a given site<p><a href="https://www.sanity.io/learn/course/markdown-routes-with-nextjs/why-markdown-routes" rel="nofollow">https://www.sanity.io/learn/course/markdown-routes-with-next...</a></p>
]]></description><pubDate>Sun, 31 May 2026 11:22:36 +0000</pubDate><link>https://news.ycombinator.com/item?id=48344850</link><dc:creator>fullstackchris</dc:creator><comments>https://news.ycombinator.com/item?id=48344850</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48344850</guid></item><item><title><![CDATA[New comment by fullstackchris in "Elements of Story"]]></title><description><![CDATA[
<p>Hi HN,<p>To my pleasant surprise, I’ve been noticing a sort of revival of posts related to writing here and on the web at large. This is either due to my own return to the craft of writing, or it really is a broader trend of AI power users realizing that AI is really, really bad at generating good prose.<p>Regardless, I’ve found AI to be a useful tool for filling in the gaps in creative writing craft and terminology that I never learned in school. I am an engineer by training and trade, so most of the writing “skills” we learned were for technical writing, lab reports, and the like.<p>This site was also heavily inspired by the “Laws of Software Engineering” post that was quite popular a few weeks back:<p><a href="https://news.ycombinator.com/item?id=47847179">https://news.ycombinator.com/item?id=47847179</a></p>
]]></description><pubDate>Sun, 31 May 2026 08:57:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=48344103</link><dc:creator>fullstackchris</dc:creator><comments>https://news.ycombinator.com/item?id=48344103</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48344103</guid></item><item><title><![CDATA[Elements of Story]]></title><description><![CDATA[
<p>Article URL: <a href="https://elementsofstory.com/">https://elementsofstory.com/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48344102">https://news.ycombinator.com/item?id=48344102</a></p>
<p>Points: 2</p>
<p># Comments: 1</p>
]]></description><pubDate>Sun, 31 May 2026 08:57:15 +0000</pubDate><link>https://elementsofstory.com/</link><dc:creator>fullstackchris</dc:creator><comments>https://news.ycombinator.com/item?id=48344102</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48344102</guid></item><item><title><![CDATA[New comment by fullstackchris in "I hated writing until I learned there’s a science to it (2024)"]]></title><description><![CDATA[
<p>except AI writing is near 100% detectable. check out something like pangram. no matter what you generate, the cadence of their word choices, sentance structures, etc. are always the same and often blantently visible in the prose. in fact i doubt an LLM of any size now and into the future can properly write without a "fingerprint". real writing, in almost any language, given the possible combination of writing even just a few sentences, even given valid grammar, already exceeds the number of atoms in the universe. because LLMs are transformers, they will always leave behind clues.</p>
]]></description><pubDate>Thu, 28 May 2026 23:12:27 +0000</pubDate><link>https://news.ycombinator.com/item?id=48316839</link><dc:creator>fullstackchris</dc:creator><comments>https://news.ycombinator.com/item?id=48316839</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48316839</guid></item><item><title><![CDATA[New comment by fullstackchris in "Can we have the day off?"]]></title><description><![CDATA[
<p>Its wild to me that the concept of working 80% (1 day off a week) or even 60% (2 days off a week) isn't even a concept in the US, while in europe such part time situations make up a huge share of the work force.<p>In short, people have been having the day off for decades now. It's called part-time work.</p>
]]></description><pubDate>Thu, 28 May 2026 06:29:16 +0000</pubDate><link>https://news.ycombinator.com/item?id=48305366</link><dc:creator>fullstackchris</dc:creator><comments>https://news.ycombinator.com/item?id=48305366</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48305366</guid></item><item><title><![CDATA[New comment by fullstackchris in "Frontier AI has broken the open CTF format"]]></title><description><![CDATA[
<p>There are also widely accepted standards to written word.<p>The best example is when an abbreviation can be expanded to more than one phrase, and both are widely used.</p>
]]></description><pubDate>Sun, 17 May 2026 18:35:07 +0000</pubDate><link>https://news.ycombinator.com/item?id=48171824</link><dc:creator>fullstackchris</dc:creator><comments>https://news.ycombinator.com/item?id=48171824</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48171824</guid></item><item><title><![CDATA[New comment by fullstackchris in "We've made the world too complicated"]]></title><description><![CDATA[
<p>> The world doesn't make sense. It's always been this way, so we don't even know another way to exist.<p>This is the main line for me. Even around the bonfire with fellow grugs if you got eaten by a tiger, I'm not sure you fully would understand that either. So I'm not exactly sure what this post is getting at? That human history so far is "bad" and we "did it the wrong way"? I'd argue 99% of human adults are just folks trying to do their best to provide for their family. Maybe I'm too much of an optimist though.</p>
]]></description><pubDate>Sun, 17 May 2026 06:48:21 +0000</pubDate><link>https://news.ycombinator.com/item?id=48166597</link><dc:creator>fullstackchris</dc:creator><comments>https://news.ycombinator.com/item?id=48166597</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48166597</guid></item><item><title><![CDATA[New comment by fullstackchris in "Project Glasswing: Securing critical software for the AI era"]]></title><description><![CDATA[
<p>Agreed. Do we have any information on what these "vulnerabilities" actually are?  Every vulnerability is typically immediately reported to CVE or NIST... are these "so destructive" they have to be kept behind closed doors? Give me a break...</p>
]]></description><pubDate>Wed, 08 Apr 2026 16:28:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=47692447</link><dc:creator>fullstackchris</dc:creator><comments>https://news.ycombinator.com/item?id=47692447</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47692447</guid></item><item><title><![CDATA[New comment by fullstackchris in "Some things just take time"]]></title><description><![CDATA[
<p>I don't see the problem - everything the author describes has, and will always be, true. You can't vibe code anything of value in a weekend exactly because anyone _else_ with the same level of experience can do the exact same thing in the same weekend! This has always been true across all trades and technologies. Once again, the domain expertise, wisdom, and simply _time_ of doing something always win. LLMs literally don't change that at all.</p>
]]></description><pubDate>Sat, 21 Mar 2026 18:16:57 +0000</pubDate><link>https://news.ycombinator.com/item?id=47469691</link><dc:creator>fullstackchris</dc:creator><comments>https://news.ycombinator.com/item?id=47469691</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47469691</guid></item><item><title><![CDATA[New comment by fullstackchris in "GPT‑5.4 Mini and Nano"]]></title><description><![CDATA[
<p>Have you used gemini models for code work? Claude and Codex are miles ahead in terms of quality and how thorough they are</p>
]]></description><pubDate>Wed, 18 Mar 2026 05:34:25 +0000</pubDate><link>https://news.ycombinator.com/item?id=47421895</link><dc:creator>fullstackchris</dc:creator><comments>https://news.ycombinator.com/item?id=47421895</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47421895</guid></item><item><title><![CDATA[New comment by fullstackchris in "What CI looks like at a 100-person team (PostHog)"]]></title><description><![CDATA[
<p>this is extremely strawman - with this your basically saying any software ever that has parts written by automation or cron jobs (even before llms) is not a product worth using? foolish.</p>
]]></description><pubDate>Tue, 17 Mar 2026 13:00:16 +0000</pubDate><link>https://news.ycombinator.com/item?id=47412052</link><dc:creator>fullstackchris</dc:creator><comments>https://news.ycombinator.com/item?id=47412052</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47412052</guid></item></channel></rss>