fullstackchris

I'm sorry but this can't be a serious take. Can AI chop wood in my backyard? Can it go grocery shopping for me? Can it build my garden shed? I highly doubt, in fact I disagree completely that "AI can do everything in 5 years"

Mostly agree, but one very small caveat—the books we all get to enjoy as readers have been through (presumably) beta readers, agent edits, and then publisher edits, and even then a line editor as well. All those hidden decisions you will not be able to learn until you do them.

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"

folks should also look at burrows delta - i forgot which books but some folks were able to identify a ghost writer by stylometry alone.

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!

for pure anonymity, i suppose then it is an answer... for the actual craft and art style of writing it is not

so... long term here meaning until the next frontier model comes out?

"History doesn't echo - it is a distant early warning sign." - Leslie Harris

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.

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.

If you're worried about it use a VPN.

Your ISP anyway knows your IP or at the very least your current one if its dynamic.

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

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

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!

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

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...

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

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.

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.

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.

> 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.

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...

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.

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

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.

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 <insert your favorite here> - 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.

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

so... MCP? can anyone explain what a "claw" is apposed to a "skill" or similar? if not, let's assume in three weeks a new term called "waffle" appears - can you explain what that is?

if not, youre all hype idiots.

its still tokens in, tokens out you fools.

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

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

google is "evil" ok buddy

i mean what clown show are we living in at this point - claims like this simply running rampant with 0 support or references

idk, codex 5.3 frankly kicks opus 4.6 ass IMO... opus i can use for about 30 min - codex i can run almost without any break

dont let it get to you, the only "worse" consequence is people wasting their time like this projecting things they literally cannot predict. remember at the end of the day, its just tokens. tokens cant crack ssl, rsa, visit a stakeholder, cook a meal, and millions of other things i can list here