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

641–650 of 728 posts

Re: Gemini 2.5 Pro Preview

#641

Post by acedTrex »

1024core wrote: post #428
acedTrex wrote: post #358

Earlier quoted context omitted.

> It's entirely clear that every last human will be beaten on code design in the upcoming years In what world is this statement remotely true.

Proof by negation, I guess? If someone were to claim: no computer will ever be able to beat humans in code design, would you agree with that? If the answer is "no", then there's your proof.

> no computer will ever be able to beat humans in code design

If you define "human" to be "average competent person in the field" then absolutely I will agree with it.

Re: Gemini 2.5 Pro Preview

#642

Post by lytefm »

cheema33 wrote: post #586
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 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. I too use multiple LLMs every day to help with my development work. And I agree with this statement. But, I also recognize that just when we think that LLMs are hitting a ceiling, they turn around and surprise us. A lot of progress is being made on the LLMs, but a…

> I think we will still need software devs, but not as many as we do today.

I'm more of an optimist in that regard. Yes, if you're looking at a very specific feature set/product that needs to be maintained/develop, you'll need less devs for that.

But we're going to see the Jevons Paradox with AI generated code, just as we've seen that in the field of web development where few people are writing raw HTML anymore.

It's going to be fun when nontechnical people who'd maybe know a bit of excel start vibe coding a large amount of software, some of which will succeed and require maintenance. This maintenance might not involve a lot of direct coding either, but a good understanding of how software actually works.

Re: Gemini 2.5 Pro Preview

#643

Post by simonw »

cloudking wrote: post #495
simonw wrote: post #416

Here's a summary of the 394 comments on this post created using the new gemini-2.5-pro-preview-05-06. It looks very good to me - well grouped, nicely formatted. https://gist.github.com/simonw/7ef3d77c8aeeaf1bfe9cc6fd68760... 30,408 input, 8,535 output = 12.336 cents. 8,500 is a very long output! Finally a model that obeys my instructions to "go long" when summarizing Hacker News threads. Here's the script I used: htt…

Pelican on a bicycle?

It's very good! https://simonwillison.net/2025/May/6/gemini-25-pro-preview/#...

Re: Gemini 2.5 Pro Preview

#644

Post by numpad0 »

ArthurStacks wrote: post #527
nnnnnande wrote: post #522

Earlier quoted context omitted.

[flagged]

[flagged]

IMO this is completely "based". Delivering customer values and making money off of it is own thing, and software companies collectively being a social club and an place for R&D is another - technically a complete tangent to it. It doesn't always matter how sausages came to be on the served plate. It might be the Costco special that CEO got last week and dumped into the pot. It's none of your business to make sure that doesn't happen. The customer knows. It's consensual. Well maybe not. But none of your business. Literally.

The field of software engineering might be doomed if everyone worked like this user and replaced programmers with machines, or not, but those are sort of above his paygrade. AI destroying the symbiotic relationship between IT companies and its internal social clubs is a societal issue, more macro-scale issues than internal regulation mechanisms of free market economies are expected to solve.

I guess my point is, I don't know this guy or his company is real or not, but it passes my BS detector and I know for the fact that a real medium sized company CEOs are like this. This is technically what everyone should aspire to be. If you think that's morally wrong and completely utterly wrong, congratulations for your first job.

Re: Gemini 2.5 Pro Preview

#645

Post by numpad0 »

DanHulton wrote: post #351
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 Citation needed. In fact, I think this pretty clearly hits the "extraordinary claims require extraordinary evidence" bar.

We were all crazy hyped when NVIDIA demoed end-to-end self driving, weren't we? First order derivatives of a hype cycle curve at lower X values is always extremely large but it's not so useful. At large X it's obviously obvious. It's always had been that way.

Re: Gemini 2.5 Pro Preview

#646

Post by scbenet »

simianwords wrote: post #266
scbenet wrote: post #178

Earlier quoted context omitted.

It's very good at Go, which makes sense because I'm assuming it's trained on a lot of Google's code

How would they train it on google code without revealing internal IP?

Google has 2.8k public repositories on just their main github account (github.com/google).

Even if they're not training on their closed source internal codebases (which they most certainly are, but fair point that they're probably not releasing the models trained on that data), it definitely seems like they have a lot of Go code in the training data.

Re: Gemini 2.5 Pro Preview

#647

Post by rtaylorgarlock »

planb wrote: post #587

> We’ve seen developers doing amazing things with Gemini 2.5 Pro, so we decided to release an updated version a couple of weeks early to get into developers hands sooner. Today we’re excited to release Gemini 2.5 Pro Preview (I/O edition). What's up with AI companies and their model naming? So is this an updated 2.5 Pro and they indicate it by appending "Preview" to the name? Or was it always called 2.5 Preview and t…

Agreed. The current 'Pro 2.5 Preview' following another 'Preview' hurts my brain, and the beta badges we're all throwing on products aren't stopping people from using things in production. Rate limits only go so far.

Re: Gemini 2.5 Pro Preview

#648

Post by jpadkins »

cheema33 wrote: post #586
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 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. I too use multiple LLMs every day to help with my development work. And I agree with this statement. But, I also recognize that just when we think that LLMs are hitting a ceiling, they turn around and surprise us. A lot of progress is being made on the LLMs, but a…

> I think we will still need software devs, but not as many as we do today.

There is already another reply referencing Jevons Paradox, so I won't belabor that point. Instead, let me give an analogy. Imagine programmers today are like scribes and monks of 1000 years ago, and are considering the impact of the printing press. Only 5% of the population knew how to read & write, so the scribes and monks felt like they were going to be replaced. What happened is the "job" of writing language will mostly go away, but every job will require writing as a core skill. I believe the same will happen with programming. A thousand years from now, people will have a hard time imagining jobs that don't involve instructing computers in some form (just like today it's hard for us to imagine jobs that don't involve reading/writing).

Re: Gemini 2.5 Pro Preview

#649

Post by vessenes »

laborcontract wrote: post #271
laborcontract wrote: post #79

My guess is that they've done a lot of tuning to improve diff based code editing. Gemini 2.5 is fantastic at agentic work, but it still is pretty rough around the edges in terms of generating perfectly matching diffs to edit code. It's probably one of the very few issues with the model. Luckily, aider tracks this. They measure the old gemini 2.5 generating proper diffs 92% of the time. I bet this goes up to ~95-98% h…

Update 2: I've been using this model in both aider and cline and I've haven't gotten a diff matching error yet, even with some pretty difficult substitutions across different places in multiple files. The overall feel of this model is nice. I don't have a formal benchmark but there's a notable improvement in code generation due to this alone. I've had gemini chug away on plans that have taken ~1 hour to implement. (~…

Question; are you calling it with “aider -model gemini”? And if so do you see 05-04 listed or the old one?

Re: Gemini 2.5 Pro Preview

#650

Post by vessenes »

cubefox wrote: post #229
jjani wrote: post #183

Earlier quoted context omitted.

Every frontier model now is a distill of a larger unpublished model. This could be a slightly smaller distill, with potentially the extra tuning you're mentioning.

That's an unsubstantiated claim. I doubt this is true, since people are disproportionately more willing to pay for the best of the best, rather than for something worse.

“Every” is unsubstantiated but probably accurate. Meta has published theirs (behemoth) and it’s clear this is largely how frontier models are being used and trained right now: too slow and expensive for daily driving inference, distillable at various levels for different tradeoffs.
Post reply on HN