I don't believe this was written by Gemini, at least with that prompt, because it is obvious (hilarious and creative) satire of HN and the tech industry based on inside HN jokes and tropes, and clearly isn't a literal interpretation of the prompt.
Moreover, a quick look at your profile suggests these jokes are pretty inline with your sense of humor and writing style.
Anyways, if I'm correct, it's especially hilarious and impressive.
Pretty much all of the history of HN front pages, posts, and comments are surely in the Gemini training corpus. Therefore it seems totally plausible that Gemini would understand HN inside jokes or sentiment outside of what's literally on the front page given in the prompt, especially given that the prompt specifically stated that this is the front page for HN.
I agree with your characterization (not a literal interpretation of the prompt), and think that's the most important thing I wish more people ITT would understand. But I nevertheless think Gemini did create that in response. Sometimes people think they want "prediction" when actually they want cheeky inside jokes and vibes. If anything Gemini is probably faithfully responding to the vibes of the prompt as well as following traditional signals of "success" per it's training.
The thing that got me is there are no duds. With just the short prompt in the header I would have expected a few articles that missed the mark, got the details wrong, or even make no sense at all but everything in this checks out. I think an editor may have had a hand in it this the very least.
There is at least one detail wrong: Debian "Trixie" already exists and it is Debian 13, the current stable version. Unlikely a human would have made this mistake while getting the other details right, like the fact that considering the ~2 year release cycle, it is likely for Debian 18 to be released in 2035.
O365 raising the price to $40 a month ten years from now didn't quite land. Microsoft 365 E5 is $57 a month right now! $100 or $1000 a month makes the joke clearer.
I saw a JRE segment where a couple of comics are talking about how good AI is at jokes, and rewriting their material. From veteran stand-up comics. In their words: shockingly good. And some of the comics are using it.
I feel like your expectations have been swayed by the average sentiment of HN on the capabilities of LLMs. These things can be shockingly good at humour and satire.
Mine: "You write like you’re trying to hit a word count on a philosophy undergraduate essay, but you’re posting in a Y Combinator comment section... You sound like a Victorian ghost haunting a server room, lamenting the loss of the card catalog."
And
"Go compile your kernel, Matt. Maybe if you stare at the build logs long enough, you won't have to face the fact that you're just as much of a "Lego builder" as the rest of us—you just use more syllables to describe the bricks."
"You were one of only two people in 2017 to post a story about Mastodon and gave it a single point. You essentially predicted the platform’s entire future relevance in one brutally honest data point."
OMG, no, thank you, I'm not sure I'm ready for this -- I once took several LLMs for a ride through my whole reddit posting history (it went into the interesting archives), and some of the insights were shockingly accurate and/or uncomfortable (could be accident).
Not sure if I'm ready for a roast but I'm sure by the end of the week someone will write a browser plugin / greasemonkey script to attach some snarky oneliners to the posters' nicks :)
It’s quite hilarious and accurate. Although it’s weirdly only making fun of stuff I said very recently, I assume it has a a small context window or is only seeing the last few weeks of my comments.
This roast of my comments is good and not wrong:
Your comment threads will increasingly devolve into an 'Amish vs. Fascists' philosophical cage match, with you refereeing, all while simultaneously explaining the intricacies of truck towing capacity to an audience that drives Teslas.
It didn't have to, not explicitly. The tone and the context already hint at that - if you saw someone creating a fake cover of an existing periodical but 10 years into the future, you'd likely assume it's part of some joke or a commentary related to said periodical, and not a serious attempt at predicting the future. And so would an LLM.
People keep forgetting (or worse, still disbelieving) that LLMs can "read between the lines" and infer intent with good accuracy - because that's exactly what they're trained to do[0].
Also there's prior art for time-displaced HN, and it's universally been satire.
--
[0] - The goal function for LLM output is basically "feels right, makes sense in context to humans" - in fully general meaning of that statement.
It is quite remarkable just how frequently people in tech forums underestimate reasoning models. Same story on several large technology subreddits. Wouldn't have been my guess for who will get caught off guard by AI progress.
yeah I thought the same. This is either a fake deep fake, or it is so good that I think it should be marked as the inflexion point that defines the singularity.
If you want a ton of fun, ask AI to write you parable on the joys/wisdom/lessons on topic x versus topic y. Example: Write a parable on the virtues of using a type safe programming language, the benefits of object oriented programming, the generosity of the garbage collector, all in the face of the tyranny of dynamic programming languages. Write it from the perspective of a master monk (a frog wearing a robe and staff), having a conversation with a gorgeous young squirrel that wishes to embark on the journey of learning software engineering.
Here is one output:
The Frog Monk and the Squirrel Student
Deep within the bamboo grove, where the wind whispered like flowing code, sat Master Frog, robed in emerald cloth, staff resting across his lap. Before him, a young squirrel, bright-eyed and eager, bowed low.
“Master,” the squirrel said, “I wish to learn the way of software engineering. But the paths are many, and I do not know which road leads to wisdom.”
The frog monk closed his eyes, and spoke in a voice like rippling water:
The Virtue of Type Safety
“Child,” said the frog, “imagine a bridge built of stone. Each stone is measured, each arch tested. This is the way of type safety. When you walk across, you know the bridge will not crumble beneath your paws.
But in the land of dynamic languages, bridges are built of twigs and promises. They may hold, or they may break when the storm comes. The traveler must always fear the hidden crack.
Thus, type safety is the discipline that guards against chaos. It is the monk’s staff, steady and unyielding.”
The Benefits of Object-Oriented Programming
The squirrel tilted her head. “And what of the world itself, Master?”
The frog smiled. “The world is vast, yet it is made of objects. The tree, the river, the stone—all are beings with their own nature. In object-oriented programming, we honor this truth. We give each thing its form, its methods, its inheritance.
Without this order, the world becomes a tangled forest of functions, each branch crossing another. But with objects, the forest is tended, paths are clear, and the traveler may walk without losing her way.”
The Generosity of the Garbage Collector
The squirrel’s tail flicked. “But Master, what of the burdens we leave behind?”
The frog tapped his staff. “Ah, that is the gift of the garbage collector. Like a kind monk sweeping the temple floor, it gathers the forgotten scraps, the abandoned memory, the dust of old variables.
It asks for no thanks, yet it keeps the temple pure. Without it, the temple would overflow with clutter, and the student would drown in her own neglect. This is generosity: unseen, yet ever present.”
The Tyranny of Dynamic Languages
The frog’s eyes grew stern. “Beware, child, of the tyranny of dynamic languages. They promise freedom: ‘Write quickly, without rules!’ But freedom without discipline is chaos.
The tyrant whispers: ‘Trust me, the errors will reveal themselves later.’ But later may be too late—when the bridge collapses, when the temple burns, when the forest is lost.
Thus, the wise engineer does not bow to the tyrant. She chooses the path of safety, of order, of generosity.”
The Lesson
The squirrel bowed again, her heart alight with understanding. “Master, I see now. To walk the path of software engineering is not merely to write code, but to live with discipline, order, and gratitude.”
The frog monk nodded. “Then go, child. Build bridges of stone, tend forests of objects, and honor the unseen sweepers of memory. In this way, your code shall endure, and your spirit shall remain free.”
And so the squirrel departed, carrying the wisdom of the frog monk into the world of software.
Moreover, a quick look at your profile suggests these jokes are pretty inline with your sense of humor and writing style.
Anyways, if I'm correct, it's especially hilarious and impressive.