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

461–470 of 728 posts

Re: Gemini 2.5 Pro Preview

#461

Post by sepositus »

whartung wrote: post #446
astrange wrote: post #437

Earlier quoted context omitted.

> * "my coworkers will just ruin it" This turns out to be a big issue. I read everything about software design I could get my hands on in years, but then at an actual large company it turned out to not help, because I'd never read anything about how to get others to follow the advice in my head from all that reading.

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.

Re: Gemini 2.5 Pro Preview

#462

Post by bentt »

MR4D wrote: post #444
sirstoke wrote: post #440

Earlier quoted context omitted.

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…

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.

This is how I use LLM’s to code. I am still architecting, and the code it writes I could write given enough time and care, but the speed with which I can try ideas and make changes fundamentally alters what I will even attempt. It is very much a table saw.

Re: Gemini 2.5 Pro Preview

#463

Post by mark_l_watson »

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.

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 are living in a world of exponential increase of AI capability, at least for the last few years - who knows what the future will bring!

Re: Gemini 2.5 Pro Preview

#464

Post by n_ary »

chr15m wrote: post #457
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.

Many of the comments don't even describe the code itself, but the change that was made to it. So instead of: x = 1 // set X to 1 You get: x = 1 // added this to set x to 1 And sometimes: // x = 1 // removed this These comments age really fast. They should be in a git commit not a comment. As somebody who prefers code to self-describe what it is doing I find this behaviour a bit frustrating and I can't seem to context…

May be these comments are actually originating from training annotated data? If I were to add code annotations for training data, I would sort of expect such comments which makes not much value for me but for the model, gives more contextual understanding…

Re: Gemini 2.5 Pro Preview

#465

Post by thebytefairy »

energy123 wrote: post #81
uh_uh wrote: post #44

Earlier quoted context omitted.

Noticed this too. There's something funny about billion dollar models being handicapped by stuck buttons.

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.

Re: Gemini 2.5 Pro Preview

#466

Post by fragmede »

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…

https://chatgpt.com/c/681aa95f-fa80-8009-84db-79febce49562

it becomes a question of how much you believe it's all just training data, and how much you believe the LLM's got pieces that are composable. I've given the question on the link as an interview questions and had humans been unable to give as through an answer (which I chose to believe is due to specialization on elsewhere in the stack). So we're already at a place where some human software development abilities have been eclipsed on some questions. So then even if the underlying algorithms don't improve, and they just ingest more training data, then it doesn't seem like a total guess as to what part of the S-curve we're on - the number of questions for software development that LLMs are able to successfully answer will continue to increase.

Re: Gemini 2.5 Pro Preview

#467

Post by fragmede »

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.

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?

Re: Gemini 2.5 Pro Preview

#468

Post by linsomniac »

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…

Do you think it could be that the people who find LLMs useless are (in large) not paying for the LLMs and therefore getting a poor experience, while the people who are more optimistic about the abilities are paying to obtain better tooling?

Re: Gemini 2.5 Pro Preview

#469

Post by SubiculumCode »

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…

Maybe LLM's know so much that it makes it difficult to feel the absence. When someone asks me about the history of the Ethiopian region, I can at most recall very few pieces of information, and critically, there is an absence of feelings of familiarity. In memory research, familiarity signal is can prompt continued retrieval attempts, but importantly absence of that signal can suggest that further retrieval attempts would be fruitless, and that you know that you don't know. Maybe knowing so much means that there is near saturation for stop tokens...or that llms need to produce a familiarity like scoring of the key response of interest.

Re: Gemini 2.5 Pro Preview

#470

Post by dan_lannan »

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…

This is said very confidently but until we see it happen there’s plenty of room for doubt.

My worst experiences with LLMs coding are from my own mistakes giving it the wrong intent. Inconsistent test cases. Laziness in explaining or even knowing what I actually want.

Architecture and abstraction happen in someone’s mind to be able to communicate intent. If intent is the bottleneck it will still come down to a human imagining the abstraction in their head.

I’d be willing to bet abstraction and architecture becomes the only thing left for humans to do.

Post reply on HN