Gemini 2.5 Pro vs. Claude 3.7 Sonnet: Coding Comparison • Hacker News Board

Re: Gemini 2.5 Pro vs. Claude 3.7 Sonnet: Coding Comparison

#331

Post by heed » Wed, Apr 02, 2025, 7:54 PM UTC

neal_ wrote: post #223

heed wrote: post #183

Earlier quoted context omitted.

believe it or not, i had cursor in yolo mode just for fun recently and 3.7 rm -rf'd my home folder :(

thats crazy! I haven't heard of yolo mode?? dont they like restrict access to the project? but i guess the terminal is unrestricted? lol i wonder what it was trying to do

it had created a config file in my home dir and i asked it to move it to the project folder and apparently it thought deleting the entire home dir first was necessary? not sure because after my home folder was gone things started disappearing lol

Re: Gemini 2.5 Pro vs. Claude 3.7 Sonnet: Coding Comparison

#332

Post by codebra » Thu, Apr 03, 2025, 11:02 AM UTC

phkahler wrote: post #113

snickell wrote: post #96

Earlier quoted context omitted.

This is the smoothest tom sawyer move I've ever seen IRL, I wonder how many people are now grinding out your GTK4 port with our favorite LLM/system to see if it can. It'll be interesting to see if anyone gets something working with current-gen LLMs. UPDATE: naive (just fed it your description verbatim) cline + claude 3.7 was a total wipeout. It looked like it was making progress, then freaked out, deleted 3/4 of its…

>> This is the smoothest tom sawyer move I've ever seen IRL That made me laugh. True, but not really the motivation. I honestly don't think LLMs can code significant real-world things yet and I'm not sure how else to prove that since they can code some interesting things. All the talk about putting programmers out of work has me calling BS but also thinking "show me". This task seems like a good combination of simple…

Programmers who code interesting things likely shouldn’t worry. The legions who code voluminous but shallow corporate apps and glue might be more concerned.

Re: Gemini 2.5 Pro vs. Claude 3.7 Sonnet: Coding Comparison

#333

Post by phkahler » Thu, Apr 03, 2025, 3:44 PM UTC

ramesh31 wrote: post #260

phkahler wrote: post #240

Earlier quoted context omitted.

I'm a hater of complexity and build systems in general. Following the instructions for building solvespace on Linux worked for me out of the box with zero issues and is not difficult. Just copy some commands: https://github.com/solvespace/solvespace?tab=readme-ov-file#...

>I'm a hater of complexity and build systems in general. But you already have a complex cmake build system in place. Adding a standard Docker image with all the deps for devs to compile on would do nothing but make contributing easier, and would not affect your CI/CD/testing pipeline at all. I followed the readme and spent half an hour trying to get this to build for MacOS before giving up. If building your project f…

>> But you already have a complex cmake build system in place.

I didn't build it :-(

>> Adding a standard Docker image with all the deps for devs to compile on would do nothing but make contributing easier, and would not affect your CI/CD/testing pipeline at all.

I understand, but to me that's just more stuff to maintain and learn. Everyone wants to push their build setup upstream - snap packages, flatpak, now we need docker... And then you and I complain that the build system is complex, partly because it supports so many options. But it looks like the person taking up the AI challenge here is using Docker, so maybe we'll get that as a side effect :-)

Re: Gemini 2.5 Pro vs. Claude 3.7 Sonnet: Coding Comparison

#334

Post by overgard » Fri, Apr 04, 2025, 4:08 PM UTC

aiauthoritydev wrote: post #307

overgard wrote: post #156

I remember back in the day when I did Visual Basic in the 90s there were a lot of cool "New Project from Template" things in Visual Studio, especially when you installed new frameworks and SDKs and stuff like that. With a click of a button you had something that kind of looked like a professional app! Or even now, the various create-whatever-app tooling in npm and node keeps on that legacy. Anyway, AI "coding" makes…

Visual basic created a revolution in software world especially for poor countries like India. You will be surprised how many systems were automated and turned into software driven processes. It was just mindblowing. If AI driven software can do it on steroid it would be a massive impact on economy.

I see what you're saying, but even with visual basic you needed to understand the basics of coding to get anywhere. Vibe coding seems to be more about intentionally not understanding things. I just think that, if you can code it yourself, maybe AI saves you some time, if you can't code it yourself, AI gives you a fancy toy that you can't expand or change. And God help you if you make an online service..

Re: Gemini 2.5 Pro vs. Claude 3.7 Sonnet: Coding Comparison

#335

Post by fbernier » Sat, Apr 05, 2025, 3:00 AM UTC

stavros wrote: post #180

cluckindan wrote: post #160

Earlier quoted context omitted.

I agree. I tried something similar: a conversion of a simple PHP library from one system to another. It was only like 500 loc but Gemini 2.5 completely failed around line 300, and even then its output contained straight up hallucinations, half-brained additions, wrong namespaces for dependencies, badly indented code and other PSR style violations. Worse, it also changed working code and broke it.

Try asking it to generate a high-level plan of how it's going to do the conversion first, then to generate function definitions for the new functions, then have it generate tests for the new functions, then actually write them, while giving it the output of the tests. It's not like people just one-shot a whole module of code, why would LLMs?

Isn't that basically the process some "thinking" models try to do for you under the hood? Prompting itself to improve your prompt. I actually have no idea but this is what I guessed it did when using it.

Re: Gemini 2.5 Pro vs. Claude 3.7 Sonnet: Coding Comparison

#336

Post by stavros » Sat, Apr 05, 2025, 7:41 AM UTC

fbernier wrote: post #335

stavros wrote: post #180

Earlier quoted context omitted.

Try asking it to generate a high-level plan of how it's going to do the conversion first, then to generate function definitions for the new functions, then have it generate tests for the new functions, then actually write them, while giving it the output of the tests. It's not like people just one-shot a whole module of code, why would LLMs?

Isn't that basically the process some "thinking" models try to do for you under the hood? Prompting itself to improve your prompt. I actually have no idea but this is what I guessed it did when using it.

They do some variant of this, but this is more directed. They might not do this on their own, they might follow other lines of reasoning. Maybe more effective, maybe less.