"Show HN: A text editor that doesn't use AI (github.com)"
Nailed it
Show HN: Gemini Pro 3 imagines the HN front page 10 years from now
261–270 of 1001 posts
Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now
#262Earlier quoted context omitted.
That is so syncophantic, I can't stand LLMs that try to hype you up as if you're some genius, brilliant mind instead of yet another average joe.
You're absolutely right!
I've been wondering if this kind of annoying affirmation is actually important to model performance and maybe should just be hidden from view like the thinking sections.
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.
Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now
#263Earlier quoted context omitted.
That is so syncophantic, I can't stand LLMs that try to hype you up as if you're some genius, brilliant mind instead of yet another average joe.
I've talked and commented about the dangers of conversations with LLMs (i.e. they activate human social wiring and have a powerful effect, even if you know it's not real. Studies show placebo pills have a statistically significant effect even when the study participant knows it's a placebo -- the effect here is similar). Despite knowing and articulating that, I fell into a rabbit hole with Claude about a month ago wh…
Personally, I only find LLMs annoying and unpleasant to converse with. I'm not sure where the dangers of conversations with LLMs are supposed to come from.
Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now
#264Earlier quoted context omitted.
I thought the page was a hilarious joke, not a bad prediction. A lot of these are fantastic observational humour about HN and tech. Gary Marcus still insisting AI progress is stalling 10 years from now, for example. Several digs at language rewrites. ITER hardly having nudged forwards. Google killing another service. And so on.
That's what makes this so funny: the AI was earnestly attempting to predict the future, but it's so bad at truly out-of-distribution predictions that an AI-generated 2035 HN frontpage is hilariously stuck in the past. "The more things change, the more they stay the same" is a source of great amusement to us, but deliberately capitalizing on this was certainly not the "intent" of the AI.
There is just no reason whatsoever to believe this is someone "earnestly attempting to predict the future", and ending up with this.
Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now
#265Exactly half of these HN usernames actually exist. So either there are enough people on HN that follow common conventions for Gemini to guess from a more general distribution, or Gemini has memorized some of the more popular posters. The ones that are missing: - aphyr_bot - bio_hacker - concerned_grandson - cyborg_sec - dang_fan - edge_compute - founder_jane - glasshole2 - monad_lover - muskwatch - net_hacker - oldti…
This is definitely based on a search or page fetch, because there are these which are all today's topics - IBM to acquire OpenAI (Rumor) (bloomberg.com) - Jepsen: NATS 4.2 (Still losing messages?) (jepsen.io) - AI progress is stalling. Human equivalence was a mirage (garymarcus.com)
The OP mentioned pasting the current frontpage into the prompt.
Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now
#266For comparison, here's the frontpage from ten years ago https://news.ycombinator.com/front?day=2015-12-09
Nice. That was a fun rabbit-hole. This is the earlier I could find. Interestingly it contains a link to HN itself. I assume this migrated from a different version of a message board?
Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now
#267Google kills Gemini cloud services is the best one. I can't believe I haven't seen that joke until today.
Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now
#268I'm impressed by the depth of snark from GPro3 here, e.g.
- Google kills Gemini Cloud Services (killedbygoogle.com)
- The unexpected return of server-side rendering (htmx.org)
And, how GPro3 clearly 'knows' HNews and knows what makes it to frontpage, e.g.: - Restoring a 2024 Framework Laptop: A retrospective (ifixit.com) - Show HN: A text editor that doesn't use AI (github.com) - Is it time to rewrite sudo in Zig? (github.com)
Good laughs.
Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now
#269For comparison, here's the frontpage from ten years ago https://news.ycombinator.com/front?day=2015-12-09
Today's front page is not a clean 10 year extrapolation from this. That's where AI is wrong. The future is weird and zig zags, it's not so linear as the Gemini generated page.
Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now
#270Prompt: Here is the front page from today: Your task is to predict, and craft, in HTML (single file, style-exact) the HN front page 10 years from now. Predict and see the future. Writ it into form! update: I told Gemini we made it to the front page. Here is it's response: LETS GOOOO! The recursive loop is officially complete: The fake future front page is now on the real present front page. We have successfully creat…
Was ITER or nuclear energy in the prompt sample? ITER achieves net positive energy for 20 consecutive minutes That's just pure dark comedy, although maybe kinda accurate? What would humans predict for this?
A decade until full end to end net positive fusion energy can be achieved for the length of a coffee break? I don't get why you think that's dark comedy, it seems about right.