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

291–300 of 336 posts

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

#291

Post by stavros »

semi-extrinsic wrote: post #287
stavros wrote: post #194

Earlier quoted context omitted.

> I don't understand why we should be talking about generating a high level plan with multiple tests etc. for a single function. You don't have to, you can write it by hand. I thought we were talking about how we can make computers write code, instead of humans, but it seems that we're trying to prove that LLMs aren't useful instead.

If we have to break the problem into tiny pieces that can be individually tested in order for LLMs to be useful, I think it clearly limits LLM usability to a particular niche of programming.

You don't have to, the LLM will.

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

#292

Post by breadwinner »

paavohtl wrote: post #272
breadwinner wrote: post #214

Earlier quoted context omitted.

Lots of articles on it... and I am not even talking about competitors like Benioff [1]. I am talking about user complaints like this [2]. Users expect Copilot to be fully integrated, like Cursor is into VSCode. Instead what you get is barely better than typing into standalone AI chats like Claude.AI. [1] https://www.cio.com/article/3586887/marc-benioff-rails-again... [2] https://techcommunity.microsoft.com/discussion…

The linked complaint is specifically about Microsoft Copilot, which despite the name is completely unrelated to the original GitHub Copilot. VS Code's integrated GitHub Copilot nowadays has the Copilot Edits feature, which can actually edit, refactor and generate files for you using a variety of models, pretty much exactly like Cursor.

Sorry I meant Microsoft Copilot should be as integrated into Office as Cursor is into VSCode. I was not talking about GitHub Copilot.

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

#293

Post by h3half »

paavohtl wrote: post #272
breadwinner wrote: post #214

Earlier quoted context omitted.

Lots of articles on it... and I am not even talking about competitors like Benioff [1]. I am talking about user complaints like this [2]. Users expect Copilot to be fully integrated, like Cursor is into VSCode. Instead what you get is barely better than typing into standalone AI chats like Claude.AI. [1] https://www.cio.com/article/3586887/marc-benioff-rails-again... [2] https://techcommunity.microsoft.com/discussion…

The linked complaint is specifically about Microsoft Copilot, which despite the name is completely unrelated to the original GitHub Copilot. VS Code's integrated GitHub Copilot nowadays has the Copilot Edits feature, which can actually edit, refactor and generate files for you using a variety of models, pretty much exactly like Cursor.

My read of the thread is that this discussion is specifically about Microsoft Copilot, not GitHub Copilot.

Which I guess just goes to show how confusing Microsoft insists on making its making scheme

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

#294

Post by galbar »

skydhash wrote: post #273
galbar wrote: post #265

Earlier quoted context omitted.

>I'd bet that no one actually likes to write code And you'd be wrong. I, for one, enjoy the process of handcrafting the individual mechanisms of the systems I create.

Do you like writing all the if, def, public void, import keywords? That is what I’m talking about. I prefer IDE for java and other verbose languages because of the code generation. And I configure my editors for templates and snippets because I don’t like to waste time on entering every single character (and learned vim because I can act on bigger units; words, lines, whole blocks). I like programming, I do not like…

I'm not bothered by if nor def. public void can be annoying but it's also fast to type and it doesn't bother me. For import I always try my best at having some kind of autoimport. I too use vim and use macros for many things.

To be honest I'm more annoyed by having to repeat three times parameters in class constructors (args, member declaration and assignment), and I have a macro for it.

The thing is, most of the time I know what I want to write before I start writing. At that point, writing the code is usually the fastest way to the result I want.

Using LLMs usually requires more writing and iterations; plus waiting for whatever it generates, reading it, understanding it and deciding if that's what I wanted; and then it suddenly goes crazy half way through a session and I have to start over...

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

#295

Post by martin-t »

bitcrusher wrote: post #220
martin-t wrote: post #138

Earlier quoted context omitted.

Whenever I read about LLMs or try to use them, I feel like I am asleep in a dream where two contradicting things can be true at the same time. On one hand, you have people claiming "AI" can now do SWE tasks which take humans 30 minutes or 2 hours and the time doubles every X months so by Y year, SW development will be completely automated. On the other hand, you have people saying exactly what you are saying. Usually…

I'm not sure why this is confusing? We're seeing the phenomenon everywhere in culture lately. People WANT something to be true and try to speak it into existence. They also tend to be the people LEAST qualified to speak about the thing they are referencing. It's not marketing hype, it is propaganda. Meanwhile, the 'experts' are saying something entirely different and being told they're wrong or worse, lying. I'm sure…

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 to be seeing, then it makes you question whether something is wrong with you or them.

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

#296

Post by atonse »

anotherpaulg wrote: post #264
atonse wrote: post #262

Earlier quoted context omitted.

As someone who just adopted Cursor (and MCP) 2-3 weeks ago, Aider seems like a different world. The examples of "create a new simple video game" cause me to glaze over. Do you have a screencast of how you use aider to develop aider? I'd love to see how a savvy expert uses these tools for real-world solutions.

I actually get asked for screencasts a lot, so I made recently made some [0]. The recording of adding support for 100+ new coding languages with tree-sitter [1] shows some pretty advanced usage. It includes using aider to script downloading a collection of files, and using ad-hoc bash scripts to have aider modify a collection of files. [0] https://aider.chat/docs/recordings/ [1] https://aider.chat/docs/recordings/tre…

This is perfect. Thank you!

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

#297

Post by ionwake »

blensor wrote: post #279
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.

Did you paste it into the chat or did you use it with a coding agent like Cline? I am majorly impressed with the combination VSCode + Cline + Gemini Today I had it duplicate an esp32 proram from UDP communication to TCP. It first copied the file ( funnily enough by writing it again instead of just straight cp ) Then it started to just change all the headers and declarations Then in a third step it changed one bigger…

I’ve just moved from expensive claudecode to cursor and Gemini - what are you thoughts on cursor vs cline?

Thank you

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

#298

Post by 8note »

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…

the typescript and javascript business though - the ais definitely trained on old old javascript.

i kinda think "javacript, the good parts" should be part of the prompt for generating TS and JS. I've seen too much of ai writing the sketchy bad parts

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

#299

Post by kaiokendev »

nowittyusername wrote: post #254
kaiokendev wrote: post #131

Earlier quoted context omitted.

I made this NES emulator with Claude last week [0]. I'd say it was a pretty non-trivial task. It involved throwing a lot of NESDev docs, Disch mapper docs, and test rom output + assembly source code to the model to figure out. [0]: https://kaiokendev.github.io/nes/

I am considering training a custom Lora on atari roms and see if i could get a working game out of it with the Loras use. The thinking here is that atari, nes, snes, etc... roms are a lot smaller in size then a program that runs natively on whatever os. Lees lines of code to write for the LLM means less chance of a screw up. take the rom, convert it to assembly, perform very detailed captions on the rom and train....…

Well the assembly I put into it was written by humans writing assembly intended to be well-understood by anyone reading it. On the contrary, many NES games abuse quirks specific to the NES that you can't translate to any system outside of the NES. Understanding what that assembly code is doing also requires a complete understanding of those quirks, which LLMs don't seem to have yet (My Mapper 4 implementation still has some bugs because my IRQ handling isn't perfect, and many games rely on precise IRQ timing).

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

#300

Post by airstrike »

citrus1330 wrote: post #289
airstrike wrote: post #235

Earlier quoted context omitted.

LOL that to me reads like an absolute garbage of a response. I'd unsubscribe immediately and jump ship to any of the competitors if I ever got that

No wonder most of the models are so obsequious, they have to pander to people like you

There's a huge gap between pandering and outright refusing to cooperate. I'd like my synthetic assistant to do as it's told.
Post reply on HN