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

541–550 of 728 posts

Re: Gemini 2.5 Pro Preview

#541

Post by Tainnor »

alex1138 wrote: post #505
Tainnor wrote: post #175

Earlier quoted context omitted.

I definitely get more use out of Gemini Pro than other models I've tried, but it's still very prone to bullshitting. I asked it a complicated question about the Scala ZIO framework that involved subtyping, type inference, etc. - something that would definitely be hard to figure out just from reading the docs. The first answer it gave me was very detailed, very convincing and very wrong. Thankfully I noticed it myself…

The fact that SO much is only discovered after the fact by asking it "Are you sure?" is just insane There has to be some kind of recursive error checking thing, or something

I did a bit more than "are you sure", though. I said "I don't think X is right because ..." (after reading the type signature of some function and thinking through what would happen). That seemed to lead it into the right direction.

Re: Gemini 2.5 Pro Preview

#542

Post by frontfor »

jajko wrote: post #537
liefde wrote: post #533

Earlier quoted context omitted.

The tension between human creativity and emerging tools is not new. What is new is the speed. When we cling to the uniqueness of human abstraction, we may be protecting something sacred—or we may be resisting evolution. The fear that machines will surpass us in design, architecture, or even intuition is not just technical. It is existential. It touches our identity, our worth, our place in the unfolding story of inte…

I do care. If I will lose job next year (if I do it won't be due to some llms, that I know 100%) or 5 years. Kids will be much older, our financial situation will be most probably more stable than now and as a family we will be more resilient for such shock. I know its just me and millions are in a very different situation. But as with everybody, as a provider and a parent I do care about my closest ones infinitely m…

This is a good point. Society as a whole will do fine, technology will keep improving, and the global stock market will keep trending up in the long term. But at the cost of destroying the livelihoods of some individuals of the species through no fault of their own.

Re: Gemini 2.5 Pro Preview

#543

Post by solumunus »

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…

As someone who uses AI daily that’s not entirely clear to me at all.

The timeline could easily be 50 or 100 years. No emerging development of technology is resistant to diminishing returns and it seems highly likely that novel breakthroughs, rather than continuing LLM improvement, are required to reach that next step of reasoning.

Re: Gemini 2.5 Pro Preview

#544

Post by FridgeSeal »

liefde wrote: post #533
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…

The tension between human creativity and emerging tools is not new. What is new is the speed. When we cling to the uniqueness of human abstraction, we may be protecting something sacred—or we may be resisting evolution. The fear that machines will surpass us in design, architecture, or even intuition is not just technical. It is existential. It touches our identity, our worth, our place in the unfolding story of inte…

> The grief of letting go of old roles is real. So is the joy of discovering new ones. The future is not a threat. It is a mirror.

That’s all well and good to say if you have a solid financial safety net. However, there’s a lot of people who do not have that, and just as many who might have a decent net _now_ but how long is that going to last? Especially if they’re now competing with everyone else who lost their job to LLM’s.

What do you suppose everyone does? Retrain? Oh yeah, excited to replicate the thundering herd problem but for professions??

Re: Gemini 2.5 Pro Preview

#545

Post by realusername »

ArthurStacks wrote: post #512
ssalazar wrote: post #454

Earlier quoted context omitted.

I code with multiple LLMs every day and build products that use LLM tech under the hood. I dont think we're anywhere near LLMs being good at code design. Existing models make _tons_ of basic mistakes and require supervision even for relatively simple coding tasks in popular languages, and its worse for languages and frameworks that are less represented in public sources of training data. I am _frequently_ having to t…

I run a software development company with dozens of staff across multiple countries. Gemini has us to the point where we can actually stop hiring for certain roles and staff have been informed they must make use of these tools or they are surplus to requirements. At the current rate of improvement I believe we will be operating on far less staff in 2 years time.

I'd be worried instead of happy in your case, it means your lunch is getting eaten as a company.

Personally I'm in a software company where this new LLM wave didn't do much of a difference.

Re: Gemini 2.5 Pro Preview

#546

Post by renewiltord »

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.

It's effectively CoT for the model. Just run again after saying "Remove all comments".

Re: Gemini 2.5 Pro Preview

#547

Post by FridgeSeal »

sepositus wrote: post #461
whartung wrote: post #446

Earlier quoted context omitted.

Indeed. The LLMs will ruin it. They still very much struggle to grasp a code set of any reasonable size. Asking one to make changes to such a code set, and you will get whatever branch the dice told the tree to go down that day. To paraphrase, “LLMs are like a box of chocolates…”. And if you have the patience to try and tack the AI to get back on track, you probably could have just done the work faster yourself.

> Asking one to make changes to such a code set, and you will get whatever branch the dice told the tree to go down that day. Has anyone come close to solving this? I keep seeing all of this "cluster of agents" designs that promise to solve all of our problems but I can't help but wonder how it works out in the first place given they're not deterministic.

You’ve got to think like a hype-man: the solution to any AI related problem, is just more compute! AI agent hallucinating? Run 10 of them and have them police each other! Model not keeping up? Easy, make that 100-fold larger, then also do inference-time compute! Cash money yo!

Re: Gemini 2.5 Pro Preview

#548

Post by valenterry »

fullstackchris wrote: post #540
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…

Code design? Perhaps. But how are you going to inform a model of every sprint meeting, standup, decision, commit, feature, and spec that is part of an existing product? It's no longer a problem of intelligence or correctness, its a problem of context, and I DON'T mean context window. Imagine onboarding your companies best programmer to a new project - even they will have dozens of questions and need at least a week t…

Yeah, this is the problem.

The LLM needs vast amounts of training data. And those data needs to have context that goes beyond a simple task and also way beyond a mere description of the end goal.

To just give one example: in a big company, teams will build software differently depending on the relations between teams and people. So basically, you would need to train the LLM based on the company, the "air" or social atmosphere and the code and other things related to it. It's doable but "in a few years" or so is a stretch. Even a few decades seems ambitious.

Re: Gemini 2.5 Pro Preview

#549

Post by codebolt »

postalrat wrote: post #346
paulirish wrote: post #250

> Gemini 2.5 Pro now ranks #1 on the WebDev Arena leaderboard It'd make sense to rename WebDev Arena to React/Tailwind Arena. Its system prompt requires [1] those technologies and the entire tool breaks when requesting vanilla JS or other frameworks. The second-order implications of models competing on this narrow definition of webdev are rather troublesome. [1] https://blog.lmarena.ai/blog/2025/webdev-arena/#:~:text…

I've found them to be pretty good with vanilla html and css.

This model also seems to do a decent job with Angular. When I was using ChatGPT it was mostly stuck in pre-16 land, and struggled with signals etc, but this model seems to correctly suggest use of the latest features by default.

Re: Gemini 2.5 Pro Preview

#550

Post by Kinrany »

ssalazar wrote: post #454
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 code with multiple LLMs every day and build products that use LLM tech under the hood. I dont think we're anywhere near LLMs being good at code design. Existing models make _tons_ of basic mistakes and require supervision even for relatively simple coding tasks in popular languages, and its worse for languages and frameworks that are less represented in public sources of training data. I am _frequently_ having to t…

We're talking about predicting the future, so we can only extrapolate.

Seeing the evidence you're thinking of would mean that LLMs will have solved software development by next month.

Post reply on HN