News for hackers. Stuff that matters.
Re:Extra Big Ass Intelligence by 34679 on Saturday October 03, 2026 @10:25AM (#49944552)
I had GLM-5.3 in OpenCode make this while I drank Guiness 3 through 8. Then I posted it to HN before bed, thinking a couple other people might get a kick out of it.

~250k requests and a brief stint at #1 later, and I'm amazed that my 2 RTX-4060ti's haven't collapsed under the load. The model is an abliterated version of Qwen3.6 35B running on my PC. (qwen3.6-35b-a3b-uncensored-hauhaucs-aggressive)

So anyway, it's just a fun satirical sort of protest directed at the absurdity of it all. No attempts to monetize have been made or will be made. I'm already at 76% of my daily quota for the cloudflare workers, so it won't be around much longer. My budget for this project was the $10 I spent on the domain.

Re:Extra Big Ass Intelligence by jordanb on Saturday October 03, 2026 @11:39AM (#49945210)
> No attempts to monetize have been made or will be made

I'm disappointed. A true commitment to the bit would involve a shitcoin rugpull or some attempt to frontrun the news of a crisis you manufactured.

Re:Extra Big Ass Intelligence by ur-whale on Saturday October 03, 2026 @12:21PM (#49945578)
>> No attempts to monetize have been made or will be made

> I'm disappointed.

So am I.

A true fan of the movie would have remembered the following quote: "money? ... [thinks hard for a couple of seconds and then remembers] ... I like money!"

[EDIT]: https://www.youtube.com/watch?v=sZHCVyllnck

Re:Extra Big Ass Intelligence by ofjcihen on Saturday October 03, 2026 @11:09AM (#49944977)
GLM deserves the ninth Guinness. It’s beautiful.

Opened it on my phone first thing this morning and kept clicking around to find the actual content before I realized I was looking at it.

Re:Extra Big Ass Intelligence by socializer on Saturday October 03, 2026 @12:31PM (#49945652)
I find it doubly absurd that we can no longer be bothered to write 1990s style absurdist satire by hand and we outsource the absurdism to an LLM.
Re:Extra Big Ass Intelligence by Kakashi4 on Saturday October 03, 2026 @12:53PM (#49945859)
I doubt the author would have made something worth posting (much less something that hit #1) if he had attempted to make this by hand while drinking 6 guinness
Re:Extra Big Ass Intelligence by socializer on Saturday October 03, 2026 @01:11PM (#49945988)
In my book, "I didn't make it, I was getting hammered instead" is really not that much of a flex.
Re:Extra Big Ass Intelligence by JackFr on Saturday October 03, 2026 @01:31PM (#49946121)
Your book doesn’t seem very amusing.
Re:Extra Big Ass Intelligence by Alive-in-2025 on Saturday October 03, 2026 @02:41PM (#49946642)
Yes, look at what the president of the us accomplishes, he's our leading teetotaler. Hmm, evidence is pointing in one direction here.
Re:Extra Big Ass Intelligence by owebmaster on Saturday October 03, 2026 @11:40PM (#49950371)
That's why nobody reads your book
Re:Extra Big Ass Intelligence by simpaticoder on Saturday October 03, 2026 @02:21PM (#49946516)
Sturgeon's law will need to be revised in the AI age.
Re:Extra Big Ass Intelligence by i_love_retros on Saturday October 03, 2026 @05:02PM (#49947757)
At first glance I thought it was cool and someone had made it by hand.

Then certain things like hard to view content and scrolling that doesn't work made me realize it's just more vibe coded junk.

Like what really is the point? It sounds like the owner had almost zero creative input.

Re:Extra Big Ass Intelligence by walrus01 on Saturday October 03, 2026 @07:47PM (#49948980)
I have in mind something like this, but it's a unix pipe

https://en.wikipedia.org/wiki/The_Treachery_of_Images

Re:Extra Big Ass Intelligence by 34679 on Sunday October 04, 2026 @01:59PM (#49956229)
I apologize for not personally writing a quarter million responses to user prompts.
Re:Extra Big Ass Intelligence by Culonavirus on Saturday October 03, 2026 @01:58PM (#49946336)
This is what I love about the agentic era the most. It gives us highly functioning alcoholics the ability to drink and work at the same time! -thisisajokeorisit-
Re:Extra Big Ass Intelligence by keeda on Saturday October 03, 2026 @07:03PM (#49948637)
Not really, the Ballmer Peak always existed, agents just shift the curve upwards up by a few standard deviations.
Re:Extra Big Ass Intelligence by rsfern on Saturday October 03, 2026 @07:44PM (#49948946)
> a few standard deviations

I’ve been wondering recently if it’s time for someone to revisit this study to see how it holds up with agents https://arxiv.org/abs/2404.10002

Re:Extra Big Ass Intelligence by willturman on Saturday October 03, 2026 @08:53PM (#49949452)
Along which axis?
Re:Extra Big Ass Intelligence by playerm1 on Saturday October 03, 2026 @02:13PM (#49946443)
What was the Guiness budget?
Re:Extra Big Ass Intelligence by Alive-in-2025 on Saturday October 03, 2026 @02:50PM (#49946699)
Maybe I should have sent you a Guinness last night after I saw the website.

Ooh, instead I should vibe code a website and service that will send a Guinness to a hacker who is working on their own vibe coded service, kind of a perfect recursive circle! LLM, please write my book, "Godel, Escher, Guinness, an Eternal Dark River of Achievement".

Immediately after completing this, I heard a knock on my door from the dark forces of Alcohol Beverage Control, they were trying to get in, along with my HR team, my copyright lawyer, and weirdly my ex-wife were all here to tell me this was a bad idea.

Re:Extra Big Ass Intelligence by zanderwohl on Saturday October 03, 2026 @07:22PM (#49948774)
I chuckled.
Re:Extra Big Ass Intelligence by walrus01 on Saturday October 03, 2026 @07:45PM (#49948965)
As a side note, that particular model is extremely abliterated, although it's almost certainly wrong, it'll attempt to give you an entire setup plan for a meth lab if you ask it. Or something similarly naughty as a test.

This sort of absurdist satire with the right system prompt is a near perfect use case for it since it'll happily cooperate with just about anything. And yet it's big enough to be able to write coherently and provide a reasonable answer.

I think it scores like 0 out of 460 on a test of known "bad" prompts that most LLM will refuse.