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

GitHub Copilot is now available for free

github.com

Post reply on HN
Print view View original

371–380 of 412 posts

Re: GitHub Copilot is now available for free

#371

Post by thot_experiment »

ghthor wrote: post #369
thot_experiment wrote: post #156

Earlier quoted context omitted.

deepseek-1b, qwen2.5-coder:1.5b, and starcoder2-3b are all pretty fast on cpu due to their small size, you're not going to be able to have conversations with them or ask them to perform transformations on your code but autocomplete should work well

Starcoder3B works great in my second hand rtx2080. Can’t run 7B, just a hair too little Ram, but still great completions

You should definitely be able to run 7B at q6_k and that might be outperformed by 15b w/ a sub 4bpw imatrix quant, iQ3_M should fit into your vram. (i personally wouldn't bother with sub 4bpw quants on models Though if it all works great for you then no reason to mess with it, but if you want to tinker you can absolutely run larger models at smaller quant sizes, q6_k is basically indistinguishable from fp16 so there's no real downside.

Re: GitHub Copilot is now available for free

#373

Post by joshstrange »

pl-27 wrote: post #164
joshstrange wrote: post #50

Earlier quoted context omitted.

This is the main sticking point for me, I'm not leaving JetBrains anytime soon. GitHub Copilot + Aider handle my needs beautifully and while I wish Aider had deep IDE integration I can work around that (Yes, I know about the "AI!" command thing, it's a cool idea but sucks in practice). Aider in browser mode has pretty much replaced my back and forth to ChatGPT/Claude's web UI to the point that I'm considering going A…

I will also stick with JetBrains and am impressed by aider! I'm using this plugin to integrate aider into IntelliJ: https://plugins.jetbrains.com/plugin/25249-coding-aider Still in progress but already pretty useful

Wow! Thank you for calling out that plugin, I hadn't see it. It is very useful and I love the better integration. I feel like with just a little more QoL stuff this plugin will be amazing. I am getting a weird hang after Aider "completes", the dialog hangs and takes 20-30 sec before the IDE becomes usable again.

Features I'd love:

* Reproduce the web/browser chat UI in the IDE, this is an easy concept to interact with vs a dialog that goes away after each run

* Provide tabs for multiple chats (each chat can have different files/history/etc)

* Allow multiple Aider processes running at the same time

But this is still super slick as-is, thank you!

Re: GitHub Copilot is now available for free

#374

Post by fragmede »

_heimdall wrote: post #365
fragmede wrote: post #296

Earlier quoted context omitted.

"model available" would be my preferred term. Is Photoshop.exe "interpretable" by anybody with a copy (of windows)? How about a binary that's been heavily decompiled, like a Mario game?

Photoshop doesn't claim to be open source like llama does though, I'm not sure of the connection you're making. Don't get me wrong, llama is at least more open than OpenAI and that may be meaningful.

The license aside, the question is what can be done with a carefully arranged blob of binary? Without additional software (Windows) I can't really do anything with Photoshop.exe. Similarly, Llama.gguf is either useful, with Ollama.app, or not, standing alone. So (looking past the difference in license), would you consider Photoshop.exe similar in that it's a binary blob that's useless by itself, or is it a useful collection of bytes, and why is/is not an ML model available on hugging faces the same?

Re: GitHub Copilot is now available for free

#375

Post by k__ »

thot_experiment wrote: post #151
k__ wrote: post #140

Earlier quoted context omitted.

Sounds great. Does this run with VSCode and how hard is it to set this up?

yes, the vscode extension is a one click install, so is ollama which is a separate project that provides local inference you'll then have to download a model, which ollama makes very easy. choosing which one will depend on your hardware but the biggest QwenCoder2.5 you can fit is a very solid starting place. it's not ready for your grandma, but it's easy enough that I'd trust a junior dev to be able to get it done

What's the extension name?

Re: GitHub Copilot is now available for free

#377

Post by thot_experiment »

k__ wrote: post #375
thot_experiment wrote: post #151

Earlier quoted context omitted.

yes, the vscode extension is a one click install, so is ollama which is a separate project that provides local inference you'll then have to download a model, which ollama makes very easy. choosing which one will depend on your hardware but the biggest QwenCoder2.5 you can fit is a very solid starting place. it's not ready for your grandma, but it's easy enough that I'd trust a junior dev to be able to get it done

What's the extension name?

Continue, I talk about it at length in the gp post.

Re: GitHub Copilot is now available for free

#379

Post by HeavyStorm »

soco wrote: post #329
chmod775 wrote: post #284

Hilarious. The code "fix" Copilot suggests in their example[1] is wrong on some many levels. It's trying to use await in something that is not an async function. From the other examples it's clear this is likely React's useEffect. You could not even make that callback an async function if you wanted to - this naive fix for that leads to subtle bugs. And last but not least: The issue here - if there's any - can alread…

I've read enthusiastic reports about Cursor but my very short trial experience was quite similar to yours: refactoring by duplicating code, mixing up cases, server connection errors, to the point where I just gave up after one day. It might be me of course and my poor prompting skills but hey if it offers me "rename symbol" I kinda expect it to rename the symbol AND its occurences. Oh well. I'll check again in a year…

Oh no, cursor _is_ very nice. To be fair I've not used it for refactoring,ore for code generation, but it's great at applying changes to the code when it identifies patterns. Makes everything easier!

Re: GitHub Copilot is now available for free

#380

Post by _heimdall »

fragmede wrote: post #374
_heimdall wrote: post #365

Earlier quoted context omitted.

Photoshop doesn't claim to be open source like llama does though, I'm not sure of the connection you're making. Don't get me wrong, llama is at least more open than OpenAI and that may be meaningful.

The license aside, the question is what can be done with a carefully arranged blob of binary? Without additional software (Windows) I can't really do anything with Photoshop.exe. Similarly, Llama.gguf is either useful, with Ollama.app, or not, standing alone. So (looking past the difference in license), would you consider Photoshop.exe similar in that it's a binary blob that's useless by itself, or is it a useful col…

The license used isn't important in my opinion, when talking about open source the question is whether the source code is available to be modified and reviewed/interpreted.

Photoshop, or any compiled binary, isn't meant to be open source and the code isn't meant to be reviewable. Llama is called open source, though the most important part isn't publicly available for review. If llama didn't claim to be open source I don't think it would matter that the model itself and all the weights aren't available.

If your argument is just that most software is shipped as compiled and/or obfuscated code, sure that's how it is usually done. That isn't considered open source though, and the line with LLMs seems to be very gray - it can be "open source" if the source code for the training logic is available even though the actual code/model being run can't be reviewed or interpreted.

Post reply on HN