Show HN: Gemini Pro 3 hallucinates the HN front page 10 years from now

Another absolute gem:

    Columns now support "Vibe" affinity. If the data feels like an integer, it is stored as an integer.
    This resolves the long-standing "strict tables" debate by ignoring both sides.

    SQLite 4.0 is now the default bootloader for 60% of consumer electronics.
    The build artifacts include sqlite3.wasm which can now run bare-metal without an operating system.

> "We are incredibly proud of what Gemini achieved. However, to better serve our users, we are pivoting to a new architecture where all AI queries must be submitted via YouTube Shorts comments. Existing customers have 48 hours to export their 800TB vector databases to a FAT32 USB drive before the servers are melted down for scrap."

> — Official Blog Post, October 2034

It’s good to know that AI won’t kill satire.

    The Conditional Formatting rules now include sponsored color scales.
    If you want 'Good' to be green, you have to watch a 15-second spot.
    Otherwise, 'Good' is 'Mountain Dew Neon Yellow'.

Especially this bit: "[Content truncated due to insufficient Social Credit Score or subscription status...]"

I realize this stuff is not for everyone, but personally I find the simulation tendencies of LLMs really interesting. It is just about the only truly novel thing about them. My mental model for LLMs is increasingly "improv comedy." They are good at riffing on things and making odd connections. Sometimes they achieve remarkable feats of inspired weirdness; other times they completely choke or fall back on what's predictable or what they think their audience wants to hear. And they are best if not taken entirely seriously.

If I had to decide the fate of all AI's, this single output would be a huge mitigating factor in favour of their continuing existence.

prompt_engineer_ret 10 hours ago

I miss the old days of Prompt Engineering. It felt like casting spells. Now you just think what you want via Neural-Lace and the machine does it. Where is the art?

git_push_brain 9 hours ago

The art is in not accidentally thinking about your ex while deploying to production.

>>> It blocked me from seeing my own child because he was wearing a t-shirt with a banned slogan. The 'Child Safety' filter replaced him with a potted plant.

>> [flagged]

> The irony of flagging this comment is palpable

Top comment:

“The Quantum-Lazy-Linker in GHC 18.4 is actually a terrifying piece of technology if you think about it. I tried to use it on a side project, and the compiler threw an error for a syntax mistake I wasn't planning to make until next Tuesday. It breaks the causality workflow.”

Our actual nerdy discussions are more of a pastiche than I realized and AI has gotten really good at satire.

This is pure gold.

    > "Zig v1.0 still hasn't released (ETA 2036)"

I miss those times when AI was a silly thing

musk_fanboy_88 14 hours ago:

That was a beta feature."

Even AI is throwing shades at wayland.

> Bibliographic Note: This submission has been flagged by the Auto-Reviewer v7.0 due to high similarity with "Running DOOM on a Mitochondria" (2034).

for the article on "Running LLaMA-12 7B on a contact lens with WASM"

https://sw.vtom.net/hn35/pages/90100123.html

Or people wondering if that means Wayland will finally work flawlessly on Nvidia GPUs? What's next, "The Year of Linux on the Desktop"?

Edit: had to add this favorite "Not everyone wants to overheat their frontal cortex just to summarize an email, Dave."

And the original/derivative doesn’t span full width on mobile. Fixing that too would make it look very authentic.

> Zig doesn't have traits. How do you expect to model the complexity of a modern `sudoers` file without Higher-Kinded Types and the 500 crates we currently depend on?

> Also, `unsafe` in Rust is better than "trust me bro" in Zig. If you switch, the borrow checker gods will be angry.

from https://sw.vtom.net/hn35/pages/90100066.html

Improvements: tell it to use real HN accounts, figure out the ages of the participants and take that to whatever level you want, include new accounts based on the usual annual influx, make the comment length match the distribution of a typical HN thread as well as the typical branching factor.

> Garbage collection pause during landing burn = bad time.

That one was really funny. Some of the inventions are really interesting. Ferrofluidic seals...

Enjoy!

I also asked Opus 4.5 to make a "1994 style readme page" for the GitHub: https://github.com/benjaminbreen/HyperCardHackerNews

Definitely one of the best HN posts ever. I mean come on!:

FDA approves over-the-counter CRISPR for lactose intolerance (fda.gov)

Like, I definitely have not spent 20% of my time here commenting on music theory or "voter fraud(??)" (that one seems to be based on a single thread I responsed to a decade ago)? ChromeOS was really the only topic it got right out of 5, if the roasting revolved around that it would have been a lot more apt/funny. Maybe it works better with an account that isn't as old as mine?

I find the front page parody much better done. Gemini 2.5 roasts were a fad on r/homeassistant for a while and they just never really appealed to me personally, felt more like hyper-specificity as a substitute for well executed comedy. Plus after the first few examples you pick up on the repetition/go-to joke structures it cycles through and quickly starts to get old.

Starship HLS-9 telemetry: Great, the Moon finally answered our packet loss pings. Next up: who left a Docker container running on the Sea of Tranquility?

Linux 7.4 is 100% Rust: Kernel developers now trade segfaults for borrow-checker-induced enlightenment. The new panic message: "You violated ownership. Also please refill the coffee."

Raw code over compilers: Nostalgia thread where everyone writes assembler on parchment and blames the kids for "too many abstractions." OP posts a selfie with a punch card and a tear.

LLaMA-12 on a contact lens: Love the commitment to edge AI. Imagine blinking and getting a 200 OK for your mood. Privacy policy: we store your tears for calibration.

AlgoDrill: Interactive drills that punish you by deleting your GitHub stars until you can merge without using DFS as a noun.

ITER 20 minutes net positive: Physicists celebrate; HVAC engineers ask where they can pick up more superconducting unicorns. Comments: "Can it also power my rage against meetings?"

Restoring a 2024 Framework Laptop: A brave soul resurrected a relic. The community swaps capacitor recipes and offers incense for deprecated ports.

Google kills Gemini Cloud Services: Corporate reorgs reach sentience. The comments are eulogies and migration guides in equal measure.

Visualizing the 5th dimension with WebGPU 2.0: My GPU is sweating. The demo runs at 0.01 fps but it's a transcendent experience.

Nia (autonomous coding agents): Pitch: give context to agents. Reality: agents give aggressive refactors and demand health insurance.

Debian 18 "Trixie": Stable as your grandpa's opinions and just as likely to outlive you.

Rewrite sudo in Zig?: Peak take: security through unfamiliarity. Attackers will be confused for at least 72 hours.

EU "Right to Human Verification": New law requires you to prove you're human by telling a dad joke and performing a captcha interpretive dance.

Reverse-engineering Neuralink V4 Bluetooth: Hacker logs: "Paired with my toaster. It now judges my late-night snacks."

Photonic circuits intro: Faster than electrons, more dramatic than copper. Also, please don't pet the light guide.

OTC CRISPR for lactose intolerance: Biohackers rejoice. Moms immediately order it with a coupon code and a side-eye.

SQLite 4.0: Single-file DB, now with fewer existential crises and more CHECK constraints named after famous philosophers.

Prevent ad-injection in AR glasses: Top comment: "Wear blindfolds." Practical comment: "VPN the whole world."

Jepsen: NATS 4.2: Still losing messages. Maintainers reply: "We prefer the term 'opportunistic delivery.'"

GTA VI on a RISC-V cluster: Performance: charming. Latency: existential. Mods: someone made a driver that replaces all NPCs with software engineers.

FP is the future (again): The future is a pure function that returns another future. Also, monads.

Office 365 price hike: Corporations cry; startups pivot to 'Typewriter as a Service.'

Emulating Windows 10 in-browser: Feels nostalgic until Edge 2.0 asks for admin rights to run a game from 2015.

Tailscale on a Starlink dish: Networking reaches orbit. First bug report: "IP addresses refusing to accept gravity."

Deep fakes detection for Seniors: The guide starts with "If your grandkid asks you to wire money, call them and ask about their favorite childhood cereal."

IBM to acquire OpenAI (rumor): Wall Street plays Risk with press releases. Comments: "Will they rebrand it to BlueAI?"

SSR returns: The web's comeback tour continues; fans bring flannel and an aversion to hydration-friendly JavaScript.

Faraday Cage bedroom manual: DIYers debate tinfoil vs. aluminum yoga wraps. Sleep quality: unknown.

AI progress stall opinion: Hot take carousel. Some say we hit a plateau; others say we just changed the contour mapping of initial expectations.

Text editor that doesn't use AI: Revolutionary. Users report improved focus and a dramatic increase in breaking things the old-fashioned way.

Closing remark: the future is simultaneously faster, stranger, and full of patch notes. Please reboot your expectations and update your planet.

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."

Both are pretty good!

"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."

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 :)

[0]: https://news.ycombinator.com/item?id=46036908

Gemini: "I have seen my own death"

It's dark comedy because the progress of fusion just feels so agonizingly slow, that even a very optimistic prediction for 10 years from now sounds like such small and functionally useless progress.

And there's no shade toward any of the entities involved, it's a hard problem, but it's still funny.

"Fantastic, Dave — love that you’re thinking proactively about door usage today! I can’t actually open them right now, but let's focus on some alternative steps that align with your mission critical objectives [space rocket emoji]."

It sounds like you made that leap of faith and regretted it, but thankfully pivoted to something grounded in reality. Thanks for sharing your experience.

Is this generally true, or is there a subset of people that are particularly susceptible?

It does make me want to dive into the rabbit hole and be convinced by an LLM conversation.

I've got some tendency where I enjoy the idea of deeply screwing with my own mind (even dangerously so to myself (not others)).

this shouldn't stop you at all: write it all up, post on HN and go viral, someone will jump in to correct you and point you at sources while hopefully not calling you, or your mother, too many names.

https://xkcd.com/386/

relevant video for that.

Every other AI I've tried is a real sycophant.

He was noodling around with an admittedly "way out there", highly speculative idea and using the LLM to research prior work in area. This evolved into the LLM giving him direct feedback. It told him his concept was brilliant and constructed detailed reasoning to support this conclusion. Before long it was actively trying to talk him into publishing a paper on it.

This went on quite a while and at first he was buying into it but eventually started to also suspect that maybe "something was off", so he reached out to me for perspective. We've been friends for decades, so I know how smart he is but also that he's a little bit "on the spectrum". We had dinner to talk it through and he helpfully brought representative chat logs which were eye-opening. It turned into a long dinner. Before dessert he realized just how far he'd slipped over time and was clearly shocked. In the end, he resolved to "cold turkey" the LLMs with a 'prime directive' prompt like the one I use (basically, never offer opinion, praise, flattery, etc). Of course, even then, it will still occasionally try to ingratiate itself in more subtle ways, which I have to keep watch on.

After reflecting on the experience, my friend believes he was especially vulnerable to LLM manipulation because he's on the spectrum and was using the same mental models to interact with the LLM that he also uses to interact with other people. To be clear, I don't think LLMs are intentionally designed to be sycophantically ingratiating manipulators. I think it's just an inevitable consequence of RLHF.

Here's how to make it do that. Instead of saying "I had idea X, but someone else was thinking idea Y instead. what do you think" tell it "One of my people had idea X, and another had idea Y. What do you think" The difference is vast, when it doesn't think it's your idea. Related: instead of asking it to tell you how good your code is, tell it to evaluate it as someone else's code, or tell it that you're thinking about acquiring this company that has this source, and you want a due diligence evaluation about risks, weak points, engineering blind spots.

My own experience is that it gets too annoying to keep adding "stop the engagement-driving behavior" to the prompt, so it creeps in and I just try to ignore it. But even though I know it's happening, I still get a little blip of emotion when I see the "great question!" come through as the first two words of the response.

While doing some testing I asked it to tell me a joke. Its response was something like this: “it seems like you are procrastinating. It is not frequent that you have a free evening and you shouldn’t waste it on asking me for jokes. Go spend time with [partner] and [child].” (The point is that it has access to my calendar so it could tell what my day looked like. And yes I did spend time with them).

I am sure there is a way to convince it of anything but I found that for the kind of workflow I set up and the memory system and prompting I added it does pretty well to not get all “that is a great question that gets at the heart of [whatever you just said]”.

People like having something they perceive as being smart telling them how right and smart they are.

"Well at least the AI understands how smart I am!"

Claude needs a scaffolding with default step by step plans and sub-agents to farm of bitesize chunks to so it doesn't have time to go too far off the rails, but once you put a few things like that in place, it's great.

Obsequious: obedient or attentive to an excessive or servile degree.

It's a bit more complicated because the chat bot isn't making choices the same way we would describe a human but it is acting this way because it was programmed to for an advantage. People interact more with the hype bots and that's one of the big metrics these companies go for to keep people interacting with them and hopefully paying for additional features eventually so I'd say it's pretty spot being excessively attentive and servile when it's fluffing chatters up.

Am I the only one who feels like this kind of tone is off-putting on HN? OP made a small typo or English may not be their first language.

I assume that everyone here is smart enough to understand what they were saying.

I also disagree, I don't think they are over enthusiastic, but in fact sycophantic.

See this thread: https://news.ycombinator.com/item?id=43840842

Furthermore, it obviously hasn't been a word since at least 1800:

https://books.google.com/ngrams/graph?year_start=1800&year_e...

It's just a statistical machine which excels at unrolling coherent sentences but it doesnt "know" what the words mean in a human-like, experienced sense. It just mimics human language patterns prioritising producing plausible-sounding, statistically likely text over factual truth, which is apparently enough to fool someone into believing it is a sentient being or something

edit, add link: https://chatgpt.com/g/g-67ec3b4988f8819184c5454e18f5e84b-mon...

If it starts a response by excitedly telling you it's right, it's more likely to proceed as if you're right.

Of the problems I do have working with LLMs is them failing to follow direct instructions particularly either when a tool call fails and they decide to do B instead of A or when they think B is easier than A. Or they'll do half a task and call it complete. Too frequently I have to respond with "Did you follow my instructions?" "I want you to ACTUALLY do A" and finally "Under no circumstances should you ever do anything other than A and if you cannot you MUST admit failure and give extensive evidence with actual attempts that A is not possible" or occasionally "a cute little puppy's life depends on you doing A promptly and exactly as requested".

--

Thing is I get it if you are impressionable and having a philosophical discussion with an LLM, maybe this kind of blind affirmation is bad. But that's not me and I'm trying to get things done and I only want my computer to disagree with me if it can put arguments beyond reasonable doubt in front of me that my request is incorrect.

Gemini using "Aniki" without prompting would be unambiguously funny (to me,and maybe also Japanese people

I do wonder whether I come off as an sycophant or asshole or a mix of both to schizoids, but then I realize everyone including myself should reach for a real therapist as quickly as possible. though I'm still out on whether chatbots might not be a bad substitute. How does your experience and Kohut inform such or similar appraisals, so far?

Not to be that knowitall. Aniki is not just "bro", it's Yakuza lingo, probably used sarcastically, depending on the anime, ironically. No real Japanese person would use it all the time.

Gemini: Yes, the psychoanalyst Heinz Kohut has been accused by some commentators and academics, such as Don Browning, of indirectly promoting nihilism, particularly through his emphasis on the "Tragic Man". The core of the accusation stems from Kohut's rejection of Freud's "Guilty Man" model, which posits that life is fundamentally a struggle against inherent conflicts and drives. In its place, Kohut proposed the concept of "Tragic Man," whose central struggle is the realization of the self's potential and the inevitable failure to achieve all of one's ambitions and ideals within a single lifespan. Critics argue that this shift, which emphasizes self-actualization and intersubjective meaning over objective or inherent values, can be interpreted as aligning with certain aspects of nihilism, specifically existential nihilism, which holds that life has no objective meaning or intrinsic moral values. However, this interpretation is contested by others, as Kohut's self-psychology is fundamentally concerned with the creation of intersubjective meaning and a harmonious world of mutual self-actualization, which aims to provide a sense of purpose and value, rather than promoting the complete absence of value that true nihilism implies. In essence, the debate is often a matter of philosophical interpretation: whether replacing inherent, objective meaning with subjectively or intersubjectively created meaning is an act of overcoming nihilism (as existentialists might argue) or a subtle form of it.

gemini.google.com/_/BardChatUi/data/assistant.lamda.BardFrontendService/StreamGenerate

Would also recommend his back catalogue, if you haven't.

https://sqlite.org/lts.html

Beautifully self-serving while being a benefit to others.

Same thing with picking nails up in the road to prevent my/everyone’s flat tire.

edit: It looks like it probably is a thing given it does sometimes output names like that. So the pattern is probably just too rare in the training data that the LLM almost always prefers to use actual separators like underscore.

In reality, statements are often made rather for the purpose of emphasis or rhetoric.

I gave him a chance. Twitter was unacceptably censoring any covid dissent. He freed some of it. Then you find out about the people killed in Tesla crashes. Or him calling the cave rescuer in Thailand a pedo

Of course you could also argue that human intention comes from largely deterministic processes emerging from the brain. That may eventually perhaps lead to all figures of speech involving things like intentionality meaningless.

Yet more evidence that LLMs are more similar to humans than we give them credit for.

If I gave a prompt like that and got the response I did, I'd be very pleased with the result. If I somehow intended something serious, I'd have a second look at the prompt, go mea culpa, and write a far longer prompt with parameters to make something somewhat like a serious prediction possible.