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

451–460 of 728 posts

Re: Gemini 2.5 Pro Preview

#451

Post by CooCooCaCha »

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.

I think you’re making a mistake assuming AI is similar to past automation. Sure in the short term, it might be comparable but long term AI is the ultimate automation.

Re: Gemini 2.5 Pro Preview

#452

Post by dankwizard »

artdigital wrote: post #449

Gemini 2.5 pro is great, but also VERY expensive with non opaque cost insights Just recently a lot of people (me included) got hit with a surprise bill, with some racking up $500 in cost for normal use I certainly got burnt and removed my API key from my tools to not accidentally use it again Example: https://x.com/pashmerepat/status/1918084120514900395?s=46

Just add to your prompt "DO NOT burn many tokens you are capped at $8.50 buddy" it works wonders for me.

Re: Gemini 2.5 Pro Preview

#453

Post by dankwizard »

kurtis_reed wrote: post #204
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.

> all the gang What does that mean?

This comment has been removed and replaced with a quote:

"Sometimes the big fish isn't only the fish"

Re: Gemini 2.5 Pro Preview

#454

Post by ssalazar »

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…

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 tell Claude/ChatGPT to clean up basic architectural and design defects. Theres no way I would trust this unsupervised.

Can you point to _any_ evidence to support that human software development abilities will be eclipsed by LLMs other than trying to predict which part of the S-curve we're on?

Re: Gemini 2.5 Pro Preview

#455

Post by ImaCake »

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 seem to be pretty good at inventing jobs both useful and pointless whenever this happens. We don't need armies of clarks to do basic word processing these days but somehow we still manage to find jobs for most people.

Re: Gemini 2.5 Pro Preview

#456

Post by codexon »

abletonlive wrote: post #333
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 feel like there are two realities right now where half the people say LLM doesn't do anything well and there is another half that's just using LLM to the max. Can everybody preface what stack they are using or what exactly they are doing so we can better determine why it's not working for you? Maybe even include what your expectations are? Maybe even tell us what models you're using? How are you prompting the model…

> I feel like there are two realities right now where half the people say LLM doesn't do anything well and there is another half that's just using LLM to the max. Can everybody preface what stack they are using or what exactly they are doing so we can better determine why it's not working for you? Maybe even include what your expectations are? Maybe even tell us what models you're using? How are you prompting the models exactly?

Just right now, I've been feeding o4-mini with high effort a C++ file with a deadlock in it.

It has failed to fix the problem after 3 times, and it introduced a double free bug in one of the attempts. It did not see the double free problem until I pointed it out.

Re: Gemini 2.5 Pro Preview

#457

Post by chr15m »

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-prompt it away.

Re: Gemini 2.5 Pro Preview

#458

Post by esperent »

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. (~…

Have you been using the Gemini 2.5 pro "Experimental" or "3-25" models in Cline? I've been using both over the last week and got quite a few diff errors, maybe 1/10 of edit so that 92% tracks for me.

Does this 2.5 pro "Preview" feel like an improvement if you had used the others?

Re: Gemini 2.5 Pro Preview

#459

Post by mark_l_watson »

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 have a suggestion for you: Create a Gemini Gem for a programming language and put context info for library resources, examples of your coding style, etc.

I just dropped version 0.1 of my Gemini book, and I have an example for making a Gem (really simple to do); read online link:

https://leanpub.com/solo-ai/read

Re: Gemini 2.5 Pro Preview

#460

Post by david-gpu »

ImaCake wrote: post #455
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 seem to be pretty good at inventing jobs both useful and pointless whenever this happens. We don't need armies of clarks to do basic word processing these days but somehow we still manage to find jobs for most people.

Most of those jobs have terrible pay and conditions, though. Software engineers have experienced a couple of decades of exceptional pay that now seems to be in danger. An argument can be made that they are automating themselves out of a job.
Post reply on HN