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

Gemini 2.5 Pro Preview

developers.googleblog.com

Post reply on HN
Print view View original

481–490 of 728 posts

Re: Gemini 2.5 Pro Preview

#481

Post by irjustin »

jstummbillig wrote: post #314
segphault wrote: post #18

My frustration with using these models for programming in the past has largely been around their tendency to hallucinate APIs that simply don't exist. The Gemini 2.5 models, both pro and flash, seem significantly less susceptible to this than any other model I've tried. There are still significant limitations, no amount of prompting will get current models to approach abstraction and architecture the way a person doe…

> no amount of prompting will get current models to approach abstraction and architecture the way a person does I find this sentiment increasingly worrisome. It's entirely clear that every last human will be beaten on code design in the upcoming years (I am not going to argue if it's 1 or 5 years away, who cares?) I wished people would just stop holding on to what amounts to nothing, and think and talk more about wha…

> I find this sentiment increasingly worrisome.

I wouldn't worry about it because, as you say, "in a new world". The old will simply "die".

We're in the midsts of a paradigm shift and it's here to stay. The key is the speed at which it hit and how much it changed. GPT3 overnight changed the game and huge chunks of people are mentally struggling to keep up - in particular education.

But people who resist AI will become the laggards.

Re: Gemini 2.5 Pro Preview

#483

Post by stavros »

Workaccount2 wrote: post #194
ranyume wrote: post #11

I don't know if I'm doing something wrong, but every time I ask gemini 2.5 for code it outputs SO MANY comments. An exaggerated amount of comments. Sections comments, step comments, block comments, inline comments, all the gang.

I have a strong sense that the comments are for the model more than the user. It's effectively more thinking in context.

It definitely dumped its CoT into a huge comment just now when I asked it to add some function calls.

Re: Gemini 2.5 Pro Preview

#484

Post by Borealid »

warkdarrior wrote: post #420
TuringNYC wrote: post #369

Earlier quoted context omitted.

I agree with you it isnt guaranteed to be inevitable, and also agree there have been plenty of journeys which were on a trajectory only to fall off. That said, IMHO it is inevitable. My personal (dismal) view is that businesses see engineering as a huge cost center to be broken up and it will play out just like manufacturing -- decimated without regard to the human cost. The profit motive and cost savings are just to…

> businesses see engineering as a huge cost center to be [...] decimated without regard to the human cost Most cost centers in the past were decimated in order to make progress: from horse-drawn carriages to cars and trucks, from mining pickaxes to mining machines, from laundry at the river to clothes washing machines, etc. Is engineering a particularly unique endeavor that needs to be saved from automation?

There's what people think engineers do: building things.

Then there's what engineers actually do: deciding how things should be built.

Neither "needs to be saved from automation", but automating the latter is much harder than automating the former. The two are often conflated.

Re: Gemini 2.5 Pro Preview

#485

Post by naasking »

sirstoke wrote: post #440
jstummbillig wrote: post #314

Earlier quoted context omitted.

> no amount of prompting will get current models to approach abstraction and architecture the way a person does I find this sentiment increasingly worrisome. It's entirely clear that every last human will be beaten on code design in the upcoming years (I am not going to argue if it's 1 or 5 years away, who cares?) I wished people would just stop holding on to what amounts to nothing, and think and talk more about wha…

I’ve been thinking about the SWE employment conundrum in a post-LLM world for a while now, and since my livelihood (and that of my loved ones’) depends on it, I’m obviously biased. Still, I would like to understand where my logic is flawed, if it is. (I.e I’m trying to argue in good faith here) Isn’t software engineering a lot more than just writing code? And I mean like, A LOT more? Informing product roadmaps, balan…

> Informing product roadmaps, balancing tradeoffs, understanding relationships between teams, prioritizing between separate tasks, pushing back on tech debt, responding to incidents, it’s a feature and not a bug, …

Ask yourself how many of these things still matter if you can tell an AI to tweak something and it can rewrite your entire codebase in a few minutes. Why would you have to prioritize, just tell the AI everything you have to change and it will do it all at once. Why would you have tech debt, that's something that accumulates because humans can only make changes on a limited scope at a mostly fixed rate. LLMs can already respond to feedback about bugs, features and incidents, and can even take advice on balancing tradeoffs.

Many of the things you describe are organizational principles designed to compensate for human limitations.

Re: Gemini 2.5 Pro Preview

#486

Post by blueprint »

bdangubic wrote: post #432
jstummbillig wrote: post #314

Earlier quoted context omitted.

> no amount of prompting will get current models to approach abstraction and architecture the way a person does I find this sentiment increasingly worrisome. It's entirely clear that every last human will be beaten on code design in the upcoming years (I am not going to argue if it's 1 or 5 years away, who cares?) I wished people would just stop holding on to what amounts to nothing, and think and talk more about wha…

It's entirely clear that every last human will be beaten on code design in the upcoming years (I am not going to argue if it's 1 or 5 years away, who cares?) Our entire industry (after all these years) does not have even remotely sane measure or definition as what is good code design. Hence, this statement is dead on arrival as you are claiming something that cannot be either proven or disproven by anyone.

that's bonkers lol have you not heard of entropy

Re: Gemini 2.5 Pro Preview

#487

Post by tiahura »

segphault wrote: post #18

My frustration with using these models for programming in the past has largely been around their tendency to hallucinate APIs that simply don't exist. The Gemini 2.5 models, both pro and flash, seem significantly less susceptible to this than any other model I've tried. There are still significant limitations, no amount of prompting will get current models to approach abstraction and architecture the way a person doe…

Why not add the applicable api references as context?

Re: Gemini 2.5 Pro Preview

#488

Post by energy123 »

thebytefairy wrote: post #465
energy123 wrote: post #81

Earlier quoted context omitted.

The Gemini app has a number of severe bugs that impacts everyone who uses it, and those bugs have persisted for over 6 months. There's something seriously dysfunctional and incompetent about the team that built that web app. What a way to waste the best LLM in the world.

Like what? I use it daily and haven't come across any seriously dysfunctional or incompetent.

Major:

1- Something went wrong error

2- Show Thinking never stops

3- You've been signed out error

4- UI spammed with garbled text if you attach large file

5- Prompt rejected with no error, prompt text returns to chat input but attachments are deleted

6- Pasting small amounts of text takes a few seconds in long chats

Annoying:

1- Scroll is hijacked when the prompt is accepted by server and thinking starts, instead of when you send the prompt or not at all.

---

If you haven't experienced these then I can only hazard a guess that you're keeping your chats at less than 100k token context or you're using AIStudio. The major issues happen when you push it with 90k token prompts or 200k token cumulative chats. They don't all have the same precise trigger, though, some are connected to long chats, others to big attachments, etc.

Re: Gemini 2.5 Pro Preview

#489

Post by andybak »

johnfn wrote: post #380
byearthithatius wrote: post #367

Earlier quoted context omitted.

Sadly. Tailwind is so oof in my opinion. Lets import megabytes just so we don't have to write 5 whole CSS classes. I mean just copy paste the code. Don't get me stared on how ugly the HTML becomes when most tags have 20 f*cking classes which could have been two.

In most reasonably-sized websites, Tailwind will decrease overall bundle size when compared to other ways of writing CSS. Which is less code, 100 instances of "margin-left: 8px" or 100 instances of "ml-2" (and a single definition for ml-2)? Tailwind will dead-code eliminate all rules you're not using. In typical production environments tailwind is only around 10kb[1]. [1]: https://v3.tailwindcss.com/docs/optimizing-f…

So. We've moved rom "human compiler" to "human compression encoder"?

Re: Gemini 2.5 Pro Preview

#490

Post by bdangubic »

blueprint wrote: post #486
bdangubic wrote: post #432

Earlier quoted context omitted.

It's entirely clear that every last human will be beaten on code design in the upcoming years (I am not going to argue if it's 1 or 5 years away, who cares?) Our entire industry (after all these years) does not have even remotely sane measure or definition as what is good code design. Hence, this statement is dead on arrival as you are claiming something that cannot be either proven or disproven by anyone.

that's bonkers lol have you not heard of entropy

now THIS made me laugh out loud which I haven’t done in awhile :))))))))
Post reply on HN