Hacker News: fullstackchris

New comment by fullstackchris in "Don't trust large context windows"

fullstackchris — Sun, 14 Jun 2026 07:51:31 +0000

Thats another problem of this post, the author mentions Claude but not explicitely what models...

100k tokens "by lunch" is also not my finding, the newer models will hit that already right in the initial exploratory phase

New comment by fullstackchris in "Statement on US government directive to suspend access to Fable 5 and Mythos 5"

fullstackchris — Sat, 13 Jun 2026 06:47:33 +0000

lets be genuine here: those local models are no where near the capabilities of true modern llms like codex 5.5 and fable 5

but i also dont doubt in a few years time models with those benchmarks will be able to be run locally

still many many breakthroughs to be had

New comment by fullstackchris in "They’re made out of weights"

fullstackchris — Thu, 04 Jun 2026 05:39:41 +0000

The prose in the post is what I've been shouting from a rooftop since the LLM hype started.

Just tokens produced by weights.

Useful, but never forget that ground truth!

New comment by fullstackchris in "The Website Specification"

fullstackchris — Sun, 31 May 2026 21:43:42 +0000

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

New comment by fullstackchris in "The Website Specification"

fullstackchris — Sun, 31 May 2026 11:22:36 +0000

modern agents already do this via content negotiation and will attempt to retrieve the markdown version of a given site

https://www.sanity.io/learn/course/markdown-routes-with-next...

New comment by fullstackchris in "Elements of Story"

fullstackchris — Sun, 31 May 2026 08:57:15 +0000

Hi HN,

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.

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.

This site was also heavily inspired by the “Laws of Software Engineering” post that was quite popular a few weeks back:

https://news.ycombinator.com/item?id=47847179

Elements of Story

fullstackchris — Sun, 31 May 2026 08:57:15 +0000

Article URL: https://elementsofstory.com/

Comments URL: https://news.ycombinator.com/item?id=48344102

Points: 2

# Comments: 1

New comment by fullstackchris in "I hated writing until I learned there’s a science to it (2024)"

fullstackchris — Thu, 28 May 2026 23:12:27 +0000

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.

New comment by fullstackchris in "Can we have the day off?"

fullstackchris — Thu, 28 May 2026 06:29:16 +0000

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.

In short, people have been having the day off for decades now. It's called part-time work.

New comment by fullstackchris in "Frontier AI has broken the open CTF format"

fullstackchris — Sun, 17 May 2026 18:35:07 +0000

There are also widely accepted standards to written word.

The best example is when an abbreviation can be expanded to more than one phrase, and both are widely used.

New comment by fullstackchris in "We've made the world too complicated"

fullstackchris — Sun, 17 May 2026 06:48:21 +0000

> The world doesn't make sense. It's always been this way, so we don't even know another way to exist.

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.

New comment by fullstackchris in "Project Glasswing: Securing critical software for the AI era"

fullstackchris — Wed, 08 Apr 2026 16:28:11 +0000

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...

New comment by fullstackchris in "Some things just take time"

fullstackchris — Sat, 21 Mar 2026 18:16:57 +0000

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.

New comment by fullstackchris in "GPT‑5.4 Mini and Nano"

fullstackchris — Wed, 18 Mar 2026 05:34:25 +0000

Have you used gemini models for code work? Claude and Codex are miles ahead in terms of quality and how thorough they are

New comment by fullstackchris in "What CI looks like at a 100-person team (PostHog)"

fullstackchris — Tue, 17 Mar 2026 13:00:16 +0000

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.

New comment by fullstackchris in "How we rebuilt Next.js with AI in one week"

fullstackchris — Wed, 25 Feb 2026 02:22:57 +0000

Lots of hate for NextJS in here so im wondering what people use as an alternative framework...

Gatsby? I used to use that one until the updates basically ceased to exist.

Vite with - looks good, but at initial glance seems to favor just pure speed for any other feature support like MDX, advanced SEO, etc.

Roll your own with React and webpack? Good luck, and you'll probably end up with something that looks like the others I've mentioned above.

Just surprised many comments are just stating complaints about Next and not providing any counter examples, its very un-HN.

New comment by fullstackchris in "Claws are now a new layer on top of LLM agents"

fullstackchris — Sun, 22 Feb 2026 16:48:37 +0000

You put this in much better words than I obviously could!

New comment by fullstackchris in "Claws are now a new layer on top of LLM agents"

fullstackchris — Sat, 21 Feb 2026 21:26:06 +0000

[flagged]

New comment by fullstackchris in "Fastest Front End Tooling for Humans and AI"

fullstackchris — Wed, 18 Feb 2026 21:16:41 +0000

anyone have any insight as to why microsoft chose go? I feel like with rust it could have been even faster!

New comment by fullstackchris in "The Future of AI Software Development"

fullstackchris — Wed, 18 Feb 2026 17:02:56 +0000

regardless its been 3 years since the release of chatgpt. literally 3. imagine in just 5 more years how much low hanging (or even big breakthroughs) will get into the pricing, things like quantization, etc. no doubt in my mind the question of "price per token" will head towards 0