Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Gemini 2.5 Pro vs. Claude 3.7 Sonnet: Coding Comparison

composio.dev

Post reply on HN
Print view View original

321–330 of 336 posts

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

#321

Post by lordswork »

HarHarVeryFunny wrote: post #147
lordswork wrote: post #140

Earlier quoted context omitted.

I'm at 3k LOC on a current Rust project I'm mostly vibe coding with my very limited free time. Will share when I hit 10k :)

Would you mind sharing what the project is, and which AI you are using? No sign so far of AI's usefulness slowing down as the complexity increases?

>Would you mind sharing what the project is

rust + wasm simulation of organisms in an ecosystem, with evolving neural networks and genes. super fun to build and watch.

>which AI you are using?

using chatgpt/claude/gemini with a custom tool i built similar to aider / claude code, except it's very interactive, like chatting with the AI as it suggests changes that I approve/decline.

>No sign so far of AI's usefulness slowing down as the complexity increases?

The AI is not perfect, there are some cases where it is unable so solve a challenging issue and i must help it solve the issue. this usually happens for big sweeping changes that touch all over the codebase. It introduces bugs, but it can also debug them easily, especially with the increased compile-time checking in rust. runtime bugs are harder, because i have to tell the ai the behavior i observe. iterating on UI design is clumsy and it's often faster for me to just iterate by making changes myself instead.

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

#322

Post by HarHarVeryFunny »

lordswork wrote: post #321
HarHarVeryFunny wrote: post #147

Earlier quoted context omitted.

Would you mind sharing what the project is, and which AI you are using? No sign so far of AI's usefulness slowing down as the complexity increases?

>Would you mind sharing what the project is rust + wasm simulation of organisms in an ecosystem, with evolving neural networks and genes. super fun to build and watch. >which AI you are using? using chatgpt/claude/gemini with a custom tool i built similar to aider / claude code, except it's very interactive, like chatting with the AI as it suggests changes that I approve/decline. >No sign so far of AI's usefulness sl…

Thanks - sounds like a fun project!

Given that you've built your own coding tool, I assume this is as much about testing what AI can do as it is about the project itself? Is it a clear win as far as productivity goes?

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

#323

Post by 3abiton »

jchw wrote: post #165
phkahler wrote: post #55

Here is a real coding problem that I might be willing to make a cash-prize contest for. We'd need to nail down some rules. I'd be shocked if any LLM can do this: https://github.com/solvespace/solvespace/issues/1414 Make a GTK 4 version of Solvespace. We have a single C++ file for each platform - Windows, Mac, and Linux-GTK3. There is also a QT version on an unmerged branch for reference. The GTK3 file is under 2KLOC.…

I suspect it probably won't work, although it's not necessarily because an LLM architecture could never perform this type of work, but rather because it works best when the training set contains inordinate sample data. I'm actually quite shocked at what they can do in TypeScript and JavaScript, but they're definitely a bit less "sharp" when it comes to stuff outside of that zone in my experience. The ridiculous amoun…

Imo they are still extremely limited compared to a senior coder. Take python, still most top ranking models struggle with our codebase, every now and then I try to test few, and handling complex part of the codebase to produce coherent features still fails. They require heavy handholding from our senior devs, which I am sure they use AI as assistants.

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

#324

Post by martin-t »

bitcrusher wrote: post #319
martin-t wrote: post #295

Earlier quoted context omitted.

Not necessarily confusing but very frustrating. This is probably the first time I encountered such a wide range of opinions and therefore such a wide range of uncertainty in a topic close to me. When a bunch of people very loudly and confidently say your profession, and something you're very good at, will become irrelevant in the next few years, it makes you pay attention. And when you then can't see what they claim…

Totally get that; I'm on the older side, so personally I've been down this road quite a few times. We're ALWAYS on the verge of our profession being rugged somehow. RAD tools, Outsourcing, In-sourcing, No-Code, AI/LLM... I used to be curious about why there was overwhelming pressure to eliminate "us", but gave up and just focus on doing good work.

The pressure is simple - money. Competent people are rare and we're not cheap. But it turns out, those cheaper less competent people can't replace us, no matter what tools you give them - there is fundamental complexity to the work we do which they can't handle.

However, I think this time is qualitatively different. This time the rich people who wanna get rid of us are not trying to replace us with other people. This time, they are trying to simulate _us_ using machines. To make "us" faster, cheaper and scalable.

I don't think LLMs will lead to actual AI and their benefit is debatable. But so much money is going into the research that somebody might just manage to build actual AI and then what?

Hopefully, in 10 years we'll all be laughing at how a bunch of billionaires went bankrupt by trying to convince the world that autocomplete was AI. But if not, a whole bunch of people will be competing for a much smaller pool of jobs, making us all much, much poorer, while they will capture all the value that would have normally been produced by us right into their pockets.

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

#325

Post by jcheng »

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…

I'm sympathetic in general, but in this case:

"You will need git, XCode tools, CMake and libomp. Git, CMake and libomp can be installed via Homebrew"

That really doesn't seem like much. Was there more to it than this?

Edit: I tried it myself and the cmake configure failed until I ran `brew link --force libomp`, after which it could start to build, but then failed again at:

    [ 55%] Building CXX object src/CMakeFiles/solvespace-core.dir/bsp.cpp.o
    c++: error: unknown argument: '-Xclang -fopenmp'

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

#326

Post by chrismorgan »

copperx wrote: post #309
chrismorgan wrote: post #195

Earlier quoted context omitted.

> It's not like people just one-shot a whole module of code, why would LLMs? For conversions between languages or libraries, you often do just one-shot it, writing or modifying code from start to end in order. I remember 15 years ago taking a 10,000 line Java code base and porting it to JavaScript mostly like this, with only a few areas requiring a bit more involved and non-sequential editing.

So, you didn't test it until the end? or did you have to build it in such a way that is was partially testable?

One of the nifty things about the target being JavaScript was that I didn’t have to finish it before I could run it—it was the sort of big library where typical code wouldn’t use most of the functionality. It was audio stuff, so there were a couple of core files that needed more careful porting (from whatever in Java to Mozilla’s Audio Data API, which was a fairly good match), and then the rest was fairly routine that could be done gradually, as I needed them or just when I didn’t have anything better to focus on. Honestly, one of the biggest problems was forgetting to prefix instance properties with `this.`

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

#327

Post by lordswork »

HarHarVeryFunny wrote: post #322
lordswork wrote: post #321

Earlier quoted context omitted.

>Would you mind sharing what the project is rust + wasm simulation of organisms in an ecosystem, with evolving neural networks and genes. super fun to build and watch. >which AI you are using? using chatgpt/claude/gemini with a custom tool i built similar to aider / claude code, except it's very interactive, like chatting with the AI as it suggests changes that I approve/decline. >No sign so far of AI's usefulness sl…

Thanks - sounds like a fun project! Given that you've built your own coding tool, I assume this is as much about testing what AI can do as it is about the project itself? Is it a clear win as far as productivity goes?

I'm most interested in building cool projects, and I have found AI to be a major multiplier to that effort. One of those cool projects was a custom coding tool, which I now use with all my projects, and continue to polish as I use it.

As far as productivity, it's hard for me to quantify, but most of these projects would not be feasible for me to pursue with my limited free time without the force multiplier of AI.

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

#328

Post by dietr1ch »

chrismorgan wrote: post #195
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?

> It's not like people just one-shot a whole module of code, why would LLMs? For conversions between languages or libraries, you often do just one-shot it, writing or modifying code from start to end in order. I remember 15 years ago taking a 10,000 line Java code base and porting it to JavaScript mostly like this, with only a few areas requiring a bit more involved and non-sequential editing.

I think this shows how the approach LLMs take is wrong. For us it's easy because we simply sort of iterate over every function with a simple prompt of doing a translation, but are yet careful enough taking notes of whatever may be relevant to do a higher level change if necessary.

Maybe the mistake is mistaking LLMs as capable people instead of a simple, but optimised neuron soup tuned for text.

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

#329

Post by larodi »

antirez wrote: post #311
larodi wrote: post #97

Earlier quoted context omitted.

Is this to say that you're writing the code manually and having the model verify for various errors, or also employing the model for actual code work. Do you instruct the code to write in "your" coding style?

For Vector Sets, I decided to write all the code myself, and I use the models very extensively for the following three goals: 1. Design chats: they help a lot as a counterpart to detect if there are flaws in your reasoning. However all the novel ideas in Vector Sets were consistently found by myself and not by the models, they are not there yet. 2. Writing tests. For the Python test code, I let the model write it, un…

Insightful

I personally tried long runs with say writing a plugin for QGIS, but then I found it is better to actually personally write some parts of the code, so to remember it. Also advancing with smaller chunks seems to result in less iterations.

Besides, indeed, the whole concept seems to not work so well with ingenious stuff. The model simply fails to understand unless lots of explaining.

The LLM assisted tech writing though seems to benefit a lot from the cursor/cline approach. Here, more than anywhere else, a careful review is also needed.

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

#330

Post by bitcrusher »

martin-t wrote: post #324
bitcrusher wrote: post #319

Earlier quoted context omitted.

Totally get that; I'm on the older side, so personally I've been down this road quite a few times. We're ALWAYS on the verge of our profession being rugged somehow. RAD tools, Outsourcing, In-sourcing, No-Code, AI/LLM... I used to be curious about why there was overwhelming pressure to eliminate "us", but gave up and just focus on doing good work.

The pressure is simple - money. Competent people are rare and we're not cheap. But it turns out, those cheaper less competent people can't replace us, no matter what tools you give them - there is fundamental complexity to the work we do which they can't handle. However, I think this time is qualitatively different. This time the rich people who wanna get rid of us are not trying to replace us with other people. This…

I agree; I wasn't clear in my previous post. I understand the economic underpinnings. I cannot understand the coupled animus and have stopped trying.
Post reply on HN