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

681–690 of 728 posts

Re: Gemini 2.5 Pro Preview

#681

Post by ArthurStacks »

nnnnnande wrote: post #662
numpad0 wrote: post #644

Earlier quoted context omitted.

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 tha…

Turning this into a moral discussion is besides the point, a point that both of you missed in your efforts to be based, although the moral discussion is also interesting—but I'll leave that be for now. It appears as if I stepped on ArthurStack's toes, but I'll give you the benefit of the doubt and reply. My point actually has everything to do with making money. Making money is not a viable differentiator in and of it…

> My problem is that directives such as "software developers need to use tool x" is an _input_ with, at best, a questionable causal relationship to outcome y.

Total drivel. It is beyond question that the use of the tools increases the capabilities and output of every single developer in the company in whatever task they are working on, once they understand how to use them. That is why there is the directive.

Re: Gemini 2.5 Pro Preview

#682

Post by WaltPurvis »

mvdtnz wrote: post #535
WaltPurvis wrote: post #434

Earlier quoted context omitted.

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…

Egads. That’s really bad. I’ve had a few boneheaded responses like that, although I don’t recall any as awful as this example. I’m still figuring out when it’s going to be quicker and better to do something myself rather than putting effort into composing a long prompt which the AI may not understand anyway. One thing I’ve learned is there’s no point in arguing with the AI. if it gets something wrong, I will maybe try one time to explain the error and see if it can correct, but if it doesn’t, then any further attempts are just going to lead to a pointless cycle of the AI regurgitating the exact same error, or making it even worse, until I start using abusive language and give up. That said, I have had many successful interactions, where a 2-minute prompt and 3-5 minutes of me reviewing the output nets perfectly serviceable code that would have taken me considerably longer to implement myself, and I’ve found it consistently useful for suggesting approaches and brainstorming solutions.

Re: Gemini 2.5 Pro Preview

#683

Post by numpad0 »

nnnnnande wrote: post #662
numpad0 wrote: post #644

Earlier quoted context omitted.

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 tha…

Turning this into a moral discussion is besides the point, a point that both of you missed in your efforts to be based, although the moral discussion is also interesting—but I'll leave that be for now. It appears as if I stepped on ArthurStack's toes, but I'll give you the benefit of the doubt and reply. My point actually has everything to do with making money. Making money is not a viable differentiator in and of it…

No, I think you're mistaking the host for the parasite - he's running a software and solutions company, which means, in a reductive sense, he is making money/scamming cash out of customers through means of software. The software is ultimately smoke and mirrors that can be anything so long it justify customer payments. Oh boy those software be additive to the world.

Everything between landing a contract and transferring deliverables, for someone like him, is already questionably related to revenues. There's everything in software engineering to tie developer paychecks to values created, and it's still as reliable as medical advice from LLM at best. Adding LLMs into it probably won't look so risky to him.

> No, there are other values besides maximizing utility.

True, but again, above his paygrade as a player in a free market capitalist economy which is mere part of a modern society, albeit not a tiny part.

----

OT and might be weird to say: I think a lot of businesses would appreciate vibe-coding going forward, relative to a team of competent engineers, solely because LLMs are more consistent(ly bad). Code quality doesn't matter but consistency do; McDonald's basically dominates Hamburger market with the worst burger ever that is also by far the most consistent. Nobody loves it, but it's what sells.

Re: Gemini 2.5 Pro Preview

#684

Post by ArthurStacks »

pmarreck wrote: post #670
ArthurStacks wrote: post #527

Earlier quoted context omitted.

[flagged]

What if I told you that a dev group with a sensibly-limited social-club flavor is where I arguably did my best and also had my happiest memories from? In the midst of SOME of the "socializing" (which, by the way, almost always STILL sticks to technical topics, even if they are merely adjacent to the task at hand) are brilliant ideas often born which sometimes end up contributing directly to bottom lines. Would you li…

> What if I told you that a dev group with a sensibly-limited social-club flavor is where I arguably did my best and also had my happiest memories from?

Maybe you did, and as a developer I am sure it is more fun, easier, and enjoyable to work in those places. That isnt what we offer though. We offer something very simple. The opportunity for a developer to come in, work hard, probably not enjoy themselves, produce what we ask, to the standard we ask, and in return they get paid.

Re: Gemini 2.5 Pro Preview

#685

Post by niteshpant »

My biggest frustration right now is just how much verbose the output is. Like a freshman aiming to hit that word count without substance, the model just spits out GenAI fluff.

Good thinking otherwise.

Re: Gemini 2.5 Pro Preview

#686

Post by skydhash »

sanderjd wrote: post #361
mynameisvlad wrote: post #317

Earlier quoted context omitted.

> "vibecoded" proofs of concept The fact that you called it out as a PoC is already many bars above what most vibe coders are doing. Which is considering a barely functioning web app as proof that vibe coding is a viable solution for coding in general. > I do worry about what the careers of entry level people will look like. It isn't obvious to me how they'll naturally develop any of these skills. Exactly. There isn'…

Yeah I think we largely agree. But I do know people, mostly experienced product managers, who are excited about "vibecoding" expressly as a prototyping / demo creation tool, which can be useful in conjunction with people who know how to turn the prototypes into real software. I'm sure lots of people aren't seeing it this way, but the point I was trying to make about this being a skill differentiator is that I think u…

If you're really prototyping a product, a simple mockup with a tool like Balsamiq can get you quite far for communication and ideation. But more often, when people want a live prototype, it's because they plan to spin some lies as "sales and marketing".

Re: Gemini 2.5 Pro Preview

#687

Post by skydhash »

froh wrote: post #395
dist-epoch wrote: post #364

Earlier quoted context omitted.

> Demystifying Gödel's Theorem: What It Actually Says > If you think his theorem limits human knowledge, think again https://www.youtube.com/watch?v=OH-ybecvuEo

thanks for the pointer. first, with Neil DeGrasse Tyson I feel in fairly ok company with my little pet peeve fallacy ;-) yah as I said, I both get it and don't ;-) And then the video escapes me saying statements about the brain "being a formal method" can't be made "because" the finite brain can't hold infinity. that's beyond me. although obviously the brain can't enumerate infinite possibilities, we're still fairly…

> My humble point is this: if we build "intelligence" as a formal system, like some silicon running some fancy pants LLM what have you, and we want rigor in it's construction, i.e. if we want to be able to tell "this is how it works", then we need to use a subset of our brain that's capable of formal and consistent thinking. And my claim is that _that subsystem_ can't capture "itself". So we have to use "more" of our brain than that subsystem. so either the "AI" that we understand is "less" than what we need and use to understand it. or we can't understand it.

I don't know if you've read Jacob Bronowski's The origins of knowledge and imagination, but the latter part of his argument are essentially this. Formal systems are nice for determining truth, but they're limited and there is always some situation that forces you to reinvent that formal system (edge cases, incorrect assumptions, rules limitation,...)

Re: Gemini 2.5 Pro Preview

#688

Post by tough »

ionwake wrote: post #412
tough wrote: post #234

Earlier quoted context omitted.

Cursor UI sucks, it tells me to use -auto mode- to be faster, but gemini 2.5 is way faster than any of the other free models, so just selecting that one is faster even if the UI says otherwise

yeah ive noticed this too, like wtf would I use Auto?

another thing i hate is the cmd+enter (Accept) and cmd+del (cancel) being on the same button with tiny ui text and that changes interchangeably depending if its a command or edit or tool call

Re: Gemini 2.5 Pro Preview

#689

Post by resize2996 »

ArthurStacks wrote: post #680
resize2996 wrote: post #678

Earlier quoted context omitted.

Your response to lower marginal cost of production is to decrease capital investment?

[flagged]

weird ad hominem, but you do you.

I'm trying to figure out this logical inconsistency: "AI has made my workers more productive, therefore my workers are worth less."

My general theory is that there is more than enough engineering work to go around

Re: Gemini 2.5 Pro Preview

#690

Post by AnIrishDuck »

Hauthorn wrote: post #627
AnIrishDuck wrote: post #521

Earlier quoted context omitted.

> 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…

This is in fact not how a chess engine works. It has an evaluation function that assigns a numerical value (score) based on a number of factors (material advantage, king "safety", pawn structure etc). These heuristics are certainly "good enough" that Stockfish is able to beat the strongest humans, but it's rarely possible for a chess engine to determine if a position results in mate. I guess the question is whether w…

An automated objective function is indeed core to how alphago, alphazero, and other RL + deep learning approaches work. Though it is obviously much more complex, and integrated into a larger system.

The core of these approaches are "self-play" which is where the "superhuman" qualities arise. The system plays billions of games against itself, and uses the data from those games to further refine itself. It seems that an automated "referee" (objective function) is an inescapable requirement for unsupervised self-play.

I would suggest that Stockfish and other older chess engines are not a good analogy for this discussion. Worth noting though that even Stockfish no longer uses a hand written objective function on extracted features like you describe. It instead uses a highly optimized neutral network trained on millions of positions from human games.

Post reply on HN