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

901–910 of 1001 posts

Re: Gemini 3

#901

Post by mlrtime »

hollowturtle wrote: post #865
SXX wrote: post #810

Earlier quoted context omitted.

You are missing the point of this exercise. This is not about code quality - its about capacity of model to generate visuals with no guidance. For the code quality it can really be as good or as bad ad as you desire. In this case it is what it is because I put zero effort into it.

non impressive at all to me, visuals are bad not even a student starting in animations would produce that slop. You're glorifying slop, as for the code quality that's not about styling or semantics the tecniques used are BAD and won't scale at all, eg setTimeout is not designed to be run at exactly that interval, it's just a timeout suggestion. And no it cannot be good or bad as you desire it's just bad, I have YET t…

FWIW I don't agree with anything you're saying but again, I'm glad there is some debate from another side.

I suck at writing software, like bad. I can't remember syntax at all. I couldn't write working code on a whiteboard if you asked me.

But I don't know how to solve problems very well, and I'm good at understanding what people want and don't want. I do understand logic and pseudocode.

The code LLMs write is good enough for 99% of the things I need it for, and I'm not writing code that will be used in some life determining situation, and I'd wager that most aren't either.

We could debate on if my code is usable/supportable long-term, by myself or others. However, I don't see how that debate would be any different if I wrote it myself (worse) or somebody else.

Re: Gemini 3

#902

Post by mlrtime »

ahmedfromtunis wrote: post #54
Filligree wrote: post #42

Earlier quoted context omitted.

What's the benchmark?

I don't think it would be a good idea to publish it on a prime source of training data.

This sounds like paranoia to me to be honest. Please tell me I'm wrong.

I could have easily come up with just the same claim, without seeing the benchmark, it doesn't exist.

Maybe if we weren't anonymous and your profile leads to credentials that you have experience in this field, otherwise I don't believe it without seeing/testing myself.

Re: Gemini 3

#904

Post by agumonkey »

Cthulhu_ wrote: post #857
codespin wrote: post #784

Earlier quoted context omitted.

> They are good at transforming one format to another. They are good at boilerplate. You just described 90% of coding

Thing is, and LLM doesn't need motivation or self-discipline to start writing, which at this point I'm confident is the main slowing down factor in software development, after requirements etc.

These also have larger memory in a way, or deeper stacks of facts. They seems to be able to explore way more sources rapidly and thus emit a solution with more knowledge. As a human I will explore less before trying to solve a problem, and only if that fails I will dig deeper.

Re: Gemini 3

#905

Post by GuB-42 »

Filligree wrote: post #42
prodigycorp wrote: post #22

I'm sure this is a very impressive model, but gemini-3-pro-preview is failing spectacularly at my fairly basic python benchmark. In fact, gemini-2.5-pro gets a lot closer (but is still wrong). For reference: gpt-5.1-thinking passes, gpt-5.1-instant fails, gpt-5-thinking fails, gpt-5-instant fails, sonnet-4.5 passes, opus-4.1 passes (lesser claude models fail). This is a reminder that benchmarks are meaningless – you…

What's the benchmark?

NIBBLES.BAS maybe [1]

If you make some assumptions about the species of the snake, it can count as a basic python benchmark ;)

[1] https://en.wikipedia.org/wiki/Nibbles_(video_game)

Re: Gemini 3

#906

Post by Retr0id »

jeron wrote: post #503
Retr0id wrote: post #495

> it’s been incredible to see how much people love it. AI Overviews now have 2 billion users every month Do regular users know how to disable AI Overviews, if they don't love them?

it's as low tech as using adblock - select element and block

Blocking the UI elements probably won't stop you from contributing to Google's usage stats.

Re: Gemini 3

#907

Post by davidmurdoch »

WhyOhWhyQ wrote: post #741
oezi wrote: post #501

Earlier quoted context omitted.

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'm not sure about this. I used gemini and claude for about 12 hours a day for a month and a half straight in an unhealthy programmer bender and claude was FAR superior. It was not really that close. Going to be interesting to test gemini 3 though.

Gemini 2.5 is prone to apology loops, and often confuses its own thinking to user input, replying to itself. Chat GPT 5 likes to refuse tasks with "sorry I can't help with that". At least in VSCode's GitHub Copilot Agent mode. Claude hasn't screwed up like that for me.

Re: Gemini 3

#909

Post by onidj »

lifty wrote: post #376
catigula wrote: post #359

Earlier quoted context omitted.

Claude is still a better agent for software professionals though it is less capable, so there isn't nothing to having the incumbent advantage.

Not my experience. Codex is the top coding model in my experience and has been since it’s out. Makes fewer mistakes and understands better my intentions.

This wasn't my experience at all.

I tried Codex for a short while but quickly went back to Claude. Found myself having to revert Codex changes all the time. Maybe I had subconsciously altered my workflow/prompting to work well with Claude, but somehow wasn't providing Codex with the correct context, not sure.

Re: Gemini 3

#910

Post by elbear »

eru wrote: post #834
drusepth wrote: post #701

Earlier quoted context omitted.

Generally, any expert hopes their tool/paintbrush/etc is as performant as possible.

And in general I'm all for increasing productivity, in all areas of the economy.

To what goal?
Post reply on HN