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

531–540 of 728 posts

Re: Gemini 2.5 Pro Preview

#531

Post by ArthurStacks »

goatlover wrote: post #528
ArthurStacks wrote: post #518

Earlier quoted context omitted.

Why? We fully checked the design, what he built, and it was fully tested over weeks for security and stability. Don't parrot what you read online that these systems are unable do this stuff. It's from the clueless or devs coping. Not only are they capable but theyre improving by the month.

I can't tell on this site who has genuinely experienced radical changes in software development from dedicated LLM usage, and who is trying to sell something. But given previous hype cycles with all exciting new tech at the time, including past iterations of AI, I tend to believe it's more in the trying to sell something camp.

Well, youre right to be skeptical because the majority of "AI" going on is hype designed for the purposes of either a scam, getting easy investment funds or inflating company valuations.

But.. the capabilities (and rate of progression) of these top tier LLMs isn't hype.

Re: Gemini 2.5 Pro Preview

#532

Post by croemer »

> We have also updated the model card with the new version of 2.5 Pro

No you haven't? At least not at 6am UTC on May 7. The PDF still mentions (03-25) as date of the model.

What version do I get on gemini.google.com when I select "2.5 Pro (experimental)"? Has anything changed there or not (yet)?

Re: Gemini 2.5 Pro Preview

#533

Post by liefde »

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…

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 intelligence.

But what if the invitation is not to compete, but to co-create? To stop asking what we are better at, and start asking what we are becoming.

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.

Re: Gemini 2.5 Pro Preview

#534

Post by energy123 »

AnIrishDuck wrote: post #521
energy123 wrote: post #517

Earlier quoted context omitted.

This is my view. We've seen this before in other problems where there's an on-hand automatic verifier. The nature of the problem mirrors previously solved problems. The LLM skeptics need to point out what differs with code compared to Chess, DoTA, etc from a RL perspective. I don't believe they can. Until they can, I'm going to assume that LLMs will soon be better than any living human at writing good code.

> The LLM skeptics need to point out what differs with code compared to Chess, DoTA, etc from a RL perspective. An obviously correct automatable objective function? Programming can be generally described as converting a human-defined specification (often very, very rough and loose) into a bunch of precise text files. Sure, you can use proxies like compilation success / failure and unit tests for RL. But key gaps rema…

I'll hand it to you that only part of the problem is easily represented in automatic verification. It's not easy to design a good reward model for softer things like architectural choices, asking for feedback before starting a project, etc. The LLM will be trained to make the tests pass, and make the code take some inputs and produce desired outputs, and it will do that better than any human, but that is going to be slightly misaligned with what we actually want.

So, it doesn't map cleanly onto previously solved problems, even though there's a decent amount of overlap. But I'd like to add a question to this discussion:

- Can we design clever reward models that punish bad architectural choices, executing on unclear intent, etc? I'm sure there's scope beyond the naive "make code that maps input -> output", even if it requires heuristics or the like.

Re: Gemini 2.5 Pro Preview

#535

Post by mvdtnz »

WaltPurvis wrote: post #434
mvdtnz wrote: post #310

I truly do not understand how people are getting worthwhile results from Gemini 2.5 Pro. I have used all of the major models for lots of different programming tasks and I have never once had Gemini produce something useful. It's not just wrong, it's laughably bad. And people are making claims that it's the best. I just... don't... get it.

That's weird. What languages/frameworks/tasks are you using it for? I've been using Gemini 2.5 with Dart recently and it frequently produces indisputably useful code, and indisputably helpful advice. Along with some code that's pretty dumb or misguided, and some advice that would be counterproductive if I actually followed it. But "never once had Gemini produce something useful" is wildly different from my recent exp…

Plain JS with Alpine.js, Java with Spring Boot, Webflux and Netty. Flyway, Tailwind. Here's an example conversation. It claims it made a mistake (there was no mistake) then spits out pathetically unusable code,

* Takes the first player's score, not the current player * Stores it as a high score without even checking if it's higher than the current high score * Stores high scores on a per-lobby basis against the given instructions * Does NOT store high scores on a per-configuration basis as instructed

https://g.co/gemini/share/baafa0e89c3a

Re: Gemini 2.5 Pro Preview

#536

Post by pjmlp »

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…

What can be done, is that the software factory will follow the footsteps of traditional factories.

A few humans will stay around to keep the robots going, a lesser few humans will be the elite allowed to create the robots, and everyone else will have to look for a job elsewhere, where increasingly robots and automated systems are decreasing opportunities.

I am certainly glad to be closer to retirement than early career.

Re: Gemini 2.5 Pro Preview

#537

Post by jajko »

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…

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 more than rest of mankind combined.

Re: Gemini 2.5 Pro Preview

#538

Post by nnnnnande »

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

Earlier quoted context omitted.

[flagged]

[flagged]

Oh, just like every other business then! That's a nice strategic differentiator.

Look, I'm sure focusing on inputs instead of outcomes (not even outputs) will work out great for you. Good luck!

Re: Gemini 2.5 Pro Preview

#539

Post by auggierose »

ArthurStacks wrote: post #518
auggierose wrote: post #516

Earlier quoted context omitted.

Hehe, have fun with that distributed system down the line.

Why? We fully checked the design, what he built, and it was fully tested over weeks for security and stability. Don't parrot what you read online that these systems are unable do this stuff. It's from the clueless or devs coping. Not only are they capable but theyre improving by the month.

Oh, they are definitely capable, I am using them every day, and build my own MCP servers. But you cannot test a distributed system "fully". The only test I believe in is understanding every single line of code myself, or knowing that somebody else does. At this point, I don't trust the AI for anything, although it makes a very valuable assistant.

Very soon our AI built software systems will break down in spectacular and never before seen ways, and I'll have the product to help with that.

Re: Gemini 2.5 Pro Preview

#540

Post by fullstackchris »

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…

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 to make productive input to the project. Even then, they are working with a markedly smaller scope of what the whole project is. How is this process translatable to an LLM? I'm not sure.
Post reply on HN