Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Gemini 3

blog.google

Post reply on HN
Print view View original

821–830 of 1001 posts

Re: Gemini 3

#821

Post by thejarren »

panarky wrote: post #719
thejarren wrote: post #702

Earlier quoted context omitted.

[flagged]

Hmmm, I wrote those words myself, maybe I've spent too much time with LLMs and now I'm talking like them?? I'd be interested in any evidence-based arguments you might have beyond attacking my writing style and insinuating bad intent. I found this commenter had sage advice about how to use HN well, I try to follow it: https://news.ycombinator.com/item?id=38944467

I’ll take you at your word, sorry for the incorrect callout. Your comment format appeared malicious, so my response wasn’t an attempt at being “snarky”, just acting defensively. I like the HN Rules/Guidelines.

Re: Gemini 3

#822

Post by marcus_holmes »

jorvi wrote: post #775
windexh8er wrote: post #740

Earlier quoted context omitted.

If we've learned anything so far it's that the parlor tricks of one-shot efficacy only gets you so far. Drill into anything relatively complex with a few hundred thousand tokens of context and the models all start to fall apart roughly the same. Even when I've used Sonnet 4.5 with 1M token context the model starts to flake out and get confused with a codebase of less than 10k LoC. Everyone seems to keep claiming thes…

Same. I've been needing to update an userscript (JS) that takes stuff like "3 for the price of 1", "5 + 1 free", "35% discount!" from a particular site and then converts the price to a % discount and the price per item / 250 grams. Its an old userscript so it is glitchy and halfway works. I already pre-chewed the work by telling Gemini 3 exactly which new HTML elements it needs to match and which contents it needs to…

1. Coding with LLMs seems to be all about context management. Getting the LLM to deal with the minimum amount of code needed to fix the problem or build the feature, carefully managing token limits and artificially resetting the session when needed so the context handover is managed, all that. Just pointing an LLM at a large code base and expecting good things doesn't work.

2. I've found the same with Gemini; I can rarely get it to actually do useful things. I have tried many times, but it just underperforms compared to the other mainstream LLMs. Other people have different experiences, though, so I suspect I'm holding it wrong.

Re: Gemini 3

#823

Post by Timwi »

sejje wrote: post #797
hollowturtle wrote: post #793

Earlier quoted context omitted.

Let me double down to get even more downvotes, here's a snippet of the code: > setTimeout(() => showSub("Ah, Earl Grey.", 2000), 1000); > setTimeout(() => showSub("Finally some peace.", 2000), 3500); > // Scene 2 > setTimeout(() => showSub(" Armor Clanking ", 2000), 7000); > setTimeout(() => showSub(" Heavy Breathing ", 2000), 10000); If we will lose our jobs to this dumb slop I'd rather be happy doing something else

How would you do it?

I would properly separate data and code so that I can easily change the dialogue and its timing without having to rewrite all of the numbers in all of the code.

Re: Gemini 3

#824

Post by ld4nt3 »

HarHarVeryFunny wrote: post #451
tylervigen wrote: post #164

I am personally impressed by the continued improvement in ARC-AGI-2, where Gemini 3 got 31.1% (vs ChatGPT 5.1's 17.6%). To me this is the kind of problem that does not lend itself well to LLMs - many of the puzzles test the kind of thing that humans intuit because of millions of years of evolution, but these concepts do not necessarily appear in written form (or when they do, it's not clear how they connect to specif…

There's a good chance Gemini 3 was trained on ARG-AGI problems, unless they state otherwise.

Its almost certain that it was, but the purpose of this puzzle benchmark is that it shouldn't really be possible just to be memorized by the amount of variations that can be created and other criteria detailed in it.

Re: Gemini 3

#825

Post by Aeolun »

panarky wrote: post #719
thejarren wrote: post #702

Earlier quoted context omitted.

[flagged]

Hmmm, I wrote those words myself, maybe I've spent too much time with LLMs and now I'm talking like them?? I'd be interested in any evidence-based arguments you might have beyond attacking my writing style and insinuating bad intent. I found this commenter had sage advice about how to use HN well, I try to follow it: https://news.ycombinator.com/item?id=38944467

“If you gaze long into an abyss, the abyss also gazes into you.”

Re: Gemini 3

#827

Post by gnabgib »

Aeolun wrote: post #825
panarky wrote: post #719

Earlier quoted context omitted.

Hmmm, I wrote those words myself, maybe I've spent too much time with LLMs and now I'm talking like them?? I'd be interested in any evidence-based arguments you might have beyond attacking my writing style and insinuating bad intent. I found this commenter had sage advice about how to use HN well, I try to follow it: https://news.ycombinator.com/item?id=38944467

“If you gaze long into an abyss, the abyss also gazes into you.”

Is that you Nietzsche? Or are you Magog https://andromeda.fandom.com/wiki/Spirit_of_the_Abyss

Re: Gemini 3

#828

Post by melagonster »

antonvs wrote: post #743
TechDebtDevin wrote: post #710

Earlier quoted context omitted.

How is it useful other than for people making money off token outout. Continue to fry your brain.

They’re fantastic learning tools, for a start. What you get out of them is proportional to what you put in. You’ve probably heard of the Luddites, the group who destroyed textile mills in the early 1800s. If not: https://en.wikipedia.org/wiki/Luddite Luddites often get a bad rap, probably in large part because of employer propaganda and influence over the writing of history, as well as the common tendency of people t…

Today, we found better ways to prevent machines from crushing children, e.g., more regulation from democracy.

Re: Gemini 3

#829

Post by decide1000 »

oezi wrote: post #501
epolanski wrote: post #464

Earlier quoted context omitted.

Imho Gemini 2.5 was by far the better model on non-trivial tasks.

To this day, I still don't understand why Claude gets more acclaim for coding. Gemini 2.5 consistently outperformed Claude and ChatGPT mostly because of the much larger context.

I use Gemini cli, Claude Code and Codex daily. If I present the same bug to all 3, Gemini often is the one missing a part of the solution or drawing the wrong conclusion. I am curious for G3.

Re: Gemini 3

#830

Post by ciberado »

panarky wrote: post #719
thejarren wrote: post #702

Earlier quoted context omitted.

[flagged]

Hmmm, I wrote those words myself, maybe I've spent too much time with LLMs and now I'm talking like them?? I'd be interested in any evidence-based arguments you might have beyond attacking my writing style and insinuating bad intent. I found this commenter had sage advice about how to use HN well, I try to follow it: https://news.ycombinator.com/item?id=38944467

This is something that is happening to me too, and frankly I'm a little concerned. English is not my first language, so I use AI for checking and writing many things. And I spend a lot of time with coding tools. And now I need sometimes to do a conscient effort to avoid mimicking some LLM patterns...
Post reply on HN