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

471–480 of 728 posts

Re: Gemini 2.5 Pro Preview

#471

Post by gmm1990 »

sweezyjeezy wrote: post #421
DanHulton wrote: post #351

Earlier quoted context omitted.

> 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.

I would argue that what LLMs are capable of doing right now is already pretty extraordinary, and would fulfil your extraordinary evidence request. To turn it on its head - given the rather astonishing success of the recent LLM training approaches, what evidence do you have that these models are going to plateau short of your own abilities?

I think it’s glorified copying of existing libraries/code. The number of resources already dedicated to the field and the amount of hype around the technology make me wary that it will get better at more comprehensive code design.

Re: Gemini 2.5 Pro Preview

#472

Post by voidspark »

djrj477dhsnv wrote: post #36

I don't understand what I'm doing wrong.. it seems like everyone is saying Gemini is better, but I've compared dozens of examples from my work, and Grok has always produced better results.

Everyone needs to say which programming language they are using

Maybe some LLMs are better for different languages

Re: Gemini 2.5 Pro Preview

#474

Post by arcanemachiner »

fragmede wrote: post #467
babyshake wrote: post #450

Earlier quoted context omitted.

Automation allows one worker to do more things in less time, and allows an organization to have fewer workers doing those things. The result, it would seem, is more people out of work and those who do have work having reduced wages, while the owner class accrues all the benefits.

We're in the jester economy - kids now want to grow up to be influencers on TikTok and not scientists or engineers. Unfortunately, AI is now able to generate those short video clips and voice overs and it's getting harder and harder to tell which is generated and which is an edited recording of actual humans. If influencer is no longer a job, what then is it going to be for kids to aspire to?

Something useful, one can hope.

Re: Gemini 2.5 Pro Preview

#475

Post by dgroshev »

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…

Software engineering (and most professions) also have something that LLMs can't have: an ability to genuinely feel bad. I think [1] it's hugely important and is an irreducible advantage that most engineering-adjacent people ignore for mostly cultural reasons.

[1]: https://dgroshev.com/blog/feel-bad/

Re: Gemini 2.5 Pro Preview

#476

Post by moregrist »

babyshake wrote: post #450
MR4D wrote: post #444

Earlier quoted context omitted.

I think an analogy that is helpful is that of a woodworker. Automation just allowed them to do more things at in less time. Power saws really reduced time, lathes even more so. Power drills changed drilling immensely, and even nail guns are used on roofing project s because manual is way too slow. All the jobs still exist, but their tools are way more capable.

Automation allows one worker to do more things in less time, and allows an organization to have fewer workers doing those things. The result, it would seem, is more people out of work and those who do have work having reduced wages, while the owner class accrues all the benefits.

Table saws do not seem to have reduced the demand for good carpenters. Demand is driven by a larger business cycle and comes and goes with the overall housing market.

As best I can tell, LLMs don’t really reduce the demand for software engineers. It’s also driven by a larger business cycle and, outside of certain AI companies, we’re in a bit of a tech down cycle.

In almost every HN article about LLMs and programming there’s this tendency toward nihilism. Maybe this industry is doomed. Or maybe a lot of current software engineers just haven’t lived through a business down cycle until now.

I don’t know the answer but I know this: if your main value is slinging code, you should diversify your skill set. That was true 20 years ago, 10 years ago, and is still true today.

Re: Gemini 2.5 Pro Preview

#477

Post by ajross »

Volundr wrote: post #390
ajross wrote: post #230

Earlier quoted context omitted.

> Are we sure they know these things as opposed to being able to consistently guess correctly? What is the practical difference you're imagining between "consistently correct guess" and "knowledge"? LLMs aren't databases. We have databases. LLMs are probabilistic inference engines. All they do is guess, essentially. The discussion here is about how to get the guess to "check itself" with a firmer idea of "truth". And…

> What is the practical difference you're imagining between "consistently correct guess" and "knowledge"? Knowing it's correct. You've just instructed it not to guess remember? With practice people can get really good at guessing all sorts of things. I think people have a serious misunderstanding about how these things work. They don't have their training set sitting around for reference. They are usually guessing. M…

> Knowing it's correct.

I love the convergence with philosophy here.

This is the second reply that's naively just asserted a tautology. You can't define "knowledge" in terms of "knowing" in the sense of the English words; they're the same word! (You can, I guess, if you're willing to write a thesis introducing the specifics of your jargon.)

In point of fact LLMs "know" that they're right, because if they didn't "know" that they wouldn't have told you what they know. Which, we all agree, they do know, right? They give answers that are correct. Usually.

Except when they're wrong. But that's the thing: define "when they're wrong" in a way rigorous enough to permit an engineering solution. But you really can't, for the same reason that you can't prevent us yahoos on the internet from being wrong all the time too.

Re: Gemini 2.5 Pro Preview

#478

Post by gtirloni »

mark_l_watson wrote: post #463
DanHulton wrote: post #351

Earlier quoted context omitted.

> 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.

I recently asked o4-mini-high for a system design of something moderately complicated and provided only about 4 paragraphs of prompt for what I wanted. I thought the design was very good, as was the Common Lisp code it wrote when I asked it to implement the design; one caveat though: it did a much better job implementing the design in Python than Common Lisp (where I had to correct the generated code). My friend, we…

That's your extraordinary evidence?

Re: Gemini 2.5 Pro Preview

#479

Post by mark_l_watson »

gtirloni wrote: post #478
mark_l_watson wrote: post #463

Earlier quoted context omitted.

I recently asked o4-mini-high for a system design of something moderately complicated and provided only about 4 paragraphs of prompt for what I wanted. I thought the design was very good, as was the Common Lisp code it wrote when I asked it to implement the design; one caveat though: it did a much better job implementing the design in Python than Common Lisp (where I had to correct the generated code). My friend, we…

That's your extraordinary evidence?

Nope, just my opinion, derived from watching monthly and weekly exponential improvement over a few year period. I worked through at least two,AI winters since 1982, so current progress is good to see.

Re: Gemini 2.5 Pro Preview

#480

Post by SafeDusk »

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…

I’m having reasonable success specifically with Gemini model using only 7 tools: read, write, diff, browse, command, ask, think.

This minimal template might be helpful to you: https://github.com/aperoc/toolkami

Post reply on HN