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

211–220 of 336 posts

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

#211

Post by Fr3ck »

pests wrote: post #91
bratao wrote: post #5

From my use case, the Gemini 2.5 is terrible. I have a complex Cython code in a single file (1500 lines) for a Sequence Labeling. Claude and o3 are very good in improving this code and following the commands. The Gemini always try to do unrelated changes. For example, I asked, separately, for small changes such as remove this unused function, or cache the arrays indexes. Every time it completely refactored the code a…

> The Gemini always try to do unrelated changes. For example, I asked, separately, for small changes such as remove this unused function For anything like this, I don’t understand trying to invoke AI. Just open the file and delete the lines yourself. What is AI going to do here for you? It’s like you are relying 100% on AI when it’s a tool in your toolset.

I like to code with an LLMs help making iterative changes. First do this, then once that code is a good place, then do this, etc. If I ask it to make one change, I want it to make one change only.

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

#212

Post by ZeWaka »

breadwinner wrote: post #190

The loser in the AI model competition appears to be... Microsoft. When ChatGPT was the only game in town Microsoft was seen as a leader, thanks to their wise investment in Open AI. They relied on Open AI's model and didn't develop their own. As a result Microsoft has no interesting AI products. Copilot is a flop. Bing failed to take advantage of AI, Perplexity ate their lunch. Satya Nadella last year: “Google should…

I don't think the Copilot product is a flop - they're doing quite well selling it along with GitHub and Visual Studio (Code).

The best part about it, coding-wise, is that you can choose between 7 different models.

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

#213

Post by disgruntledphd2 »

semi-extrinsic wrote: post #184
ramesh31 wrote: post #84

Earlier quoted context omitted.

You guys really need a Docker build. This dependency chain with submodules is a nightmare.

Alternative perspective: you kids with your Docker builds need to roll up your sleeves and learn how to actually compile a semi-complicated project if you expect to be able to contribute back to said project.

I can see both perspectives! But honestly, making a project easier to build is almost always a good use of time if you'd like new people to contribute.

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

#214

Post by breadwinner »

gnatolf wrote: post #204
breadwinner wrote: post #190

The loser in the AI model competition appears to be... Microsoft. When ChatGPT was the only game in town Microsoft was seen as a leader, thanks to their wise investment in Open AI. They relied on Open AI's model and didn't develop their own. As a result Microsoft has no interesting AI products. Copilot is a flop. Bing failed to take advantage of AI, Perplexity ate their lunch. Satya Nadella last year: “Google should…

Any way you can back up that Copilot is a flop?

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/discussions/microsoft365...

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

#215

Post by ZeroTalent »

tempoponet wrote: post #51
kingkongjaffa wrote: post #9

Is there a less biased discussion? The OP link is a thinly veiled and biased advert for something called composio and really a biased and overly flowery view of Gemini 2.5 pro. Example: “Everyone’s talking about this model on Twitter (X) and YouTube. It’s trending everywhere, like seriously. The first model from Google to receive such fanfare. And it is #1 in the LMArena just like that. But what does this mean? It me…

I don't see it. Composio is a tool to help integration of LLM tool calling / MCPs. It really helped me streamline setting up some MCPs with Claude desktop. I don't see how pushing Gemini would help their business beyond encouraging people to play with the latest and greatest models. There's a 1 sentence call-to-action at the end which is pretty tame for a company blog. The examples don't even require you to use Compo…

I believe their point was that they are writing about what people want to read (a new AI breakthrough), possibly embellishing or cherry-picking results, although we can't prove/disprove it easily.

This approach yields more upvotes and views on their website, which ultimately leads to increased conversions for their tool.

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

#216

Post by airstrike »

ZeWaka wrote: post #212
breadwinner wrote: post #190

The loser in the AI model competition appears to be... Microsoft. When ChatGPT was the only game in town Microsoft was seen as a leader, thanks to their wise investment in Open AI. They relied on Open AI's model and didn't develop their own. As a result Microsoft has no interesting AI products. Copilot is a flop. Bing failed to take advantage of AI, Perplexity ate their lunch. Satya Nadella last year: “Google should…

I don't think the Copilot product is a flop - they're doing quite well selling it along with GitHub and Visual Studio (Code). The best part about it, coding-wise, is that you can choose between 7 different models.

I think he's talking about Microsoft Copilot 365, not the coding assistant.

Makes one wonder how much they are offering to the owner of www.copilot.com and why on God's green earth they would abandon the very strong brand name "Office" and www.office.com

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

#217

Post by ZeroTalent »

archeantus wrote: post #202
raffkede wrote: post #198

I had huge success letting Gemini 2.5 oneshot whole codebases in a single text file format and then split it up with a script. It's putting in work for like 5 minutes and spits out a working codebase, I also asked it to show of a little bit and it almost one shotted a java cloud service to generate pdf invoices from API calls, (made some minor mistakes but after feeding them back it fixed them) I basically use two sc…

Can you please expound on this? You’re using this approach to turn an existing codebase into a single file and then asking Gemini to make changes/enhancements? Does it also handle breaking the files back out? Would love more info!

There is a better way that I'm using:

1. Cursor Pro with Sonnet to implement things the Cursor way.

2. Install the Gemini Code extension in Cursor.

3. Install the Gemini Coder Connector Chrome extension: https://chromewebstore.google.com/detail/gemini-coder-connec...

4. Get the free aistudio.google.com Gemini API and connect the extensions.

5. Feed your codebase or select files via the Cursor extension and get the implementation from aistudio.google.com.

I prefer having Sonnet implement it via Cursor rather than Gemini because it can automatically go through all the linting/testing loops without my extra input, run the server, and check if there are no errors.

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

#218

Post by orange_puff »

redox99 wrote: post #171
HarHarVeryFunny wrote: post #119

I'd like to see an honest attempt by someone to use one of these SOTA models to code an entire non-trivial app. Not a "vibe coding" flappy bird clone or minimal ioS app (call API to count calories in photo), but something real - say 10K LOC type of complexity, using best practices to give the AI all the context and guidance necessary. I'm not expecting the AI to replace the programmer - just to be a useful productivi…

I use cursor agent mode with claude on my NextJS frontend and Typescript GraphQL backend. It's a real, reasonably sized, production app that's a few years old (pre-ChatGPT). I vibe code the vast majority features nowadays. I generally don't need to write a single line of code. It often makes some mistakes but the agent figures out that the tests fail, or it doesn't build, fixes it, and basically "one shots" it after…

When you say "vibe code" do you mean the true definition of that term, which is to blindly accept any code generated by the AI, see if it works (maybe agent mode does this) and move on to the next feature? Or do you mean prompt driven development, where although you are basically writing none of the code, you are still reading every line and maintain high involvement in the code base?

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

#219

Post by vasergen »

pera wrote: post #112
gavinray wrote: post #69

Earlier quoted context omitted.

Convert the GTK 3 and GTK 4 API documentation into a single `.txt` file each. Upload one of your platform-specific C++ file's source, along with the doc `.txt` into your LLM of choice. Either ask it for a conversion function-by-function, or separate it some other way logically such that the output doesn't get truncated. Would be surprised if this didn't work, to be honest.

Do you really need to provide the docs? I would have imagined that those docs are included in their training sets. There is even a guide on how to migrate from GTK3 to GTK4, so this seems to be a low-hanging fruit job for an LLM iff they are okay for coding.

The training set is huge and model "forgets" some of the stuff, providing docs in context makes sense, plus docs could be up to date comparing to training set.

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

#220

Post by bitcrusher »

martin-t wrote: post #138
neal_ wrote: post #29

I was using gemini 2.5 pro yesterday and it does seem decent. I still think claude 3.5 is better at following instruction then the new 3.7 model which just goes ham messing stuff up. Really disappointed by Cursor and the Claude CLI tool, for me they create more problems then fix. I cant figure out how to use them on any of my projects with out them ruining the project and creating terrible tech debt. I really like th…

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 you've seen it before, but this propaganda, in particular, is the holy grail of 'business people'. The ones who "have a great idea, just need you to do all the work" types. This has been going on since the late 70s, early 80s.

Post reply on HN