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

GitHub Copilot Workspace: Technical Preview

github.blog

Post reply on HN
Print view View original

141–150 of 333 posts

Re: GitHub Copilot Workspace: Technical Preview

#141

Post by dgb23 »

alfalfasprout wrote: post #87
sdesol wrote: post #84

Interesting. I don't think the AI code generation will live up to developer expectations, but I do see the value in "project management for developers". The value I see with workspace is not the code generation, but the ability to help developers organize their thoughts.

The real problem is a large part of the enormous hype train is investors thinking they can replace talented engineers w/ AI. That's fundamentally doomed for failure. What AI can really do well is take an already competent engineer and suddenly get rid of a lot of the annoying tedium they had to deal with. Whether it's writing boilerplate, doing basic project management, organizing brain dumps/brainstorming, etc.

It’s pretty good at completing relatively simple code. If you already know what exactly you write and have a consistent and simple coding style it will typically recognize what you are doing and complete whole blocks.

It takes an experienced eye to fix the code after, but overall it makes you a bit faster at those kinds of tasks.

But if you’re in thinking and exploration mode then turn it off. It’s a massive distraction then.

Re: GitHub Copilot Workspace: Technical Preview

#142

Post by no_wizard »

studenthrow3831 wrote: post #3

Student here: I legitimately cannot understand how senior developers can dismiss these LLM tools when they've gone from barely stringing together a TODO app to structuring and executing large-scale changes in entire repositories in 3 years. I'm not a singulatarian, but this seems like a brutal S-curve we're heading into. I also have a hard time believing that there is enough software need to make such an extreme prod…

A simple allegory to this: Cloud Computing.

Cloud computing boomed, and is by some measure continuing to do so, the last ~15 years, from AWS to Firebase to VPS providers like Linode.

The promise, in part, was that it would replace the need for certain roles, namely system administrators and - depending on what technologies you adopted - you could replace good chunks of backend engineers.

Yet, what happened was roles shifted. System Administration became DevOps, and backend engineers learned to leverage the tools to move faster but provide value elsewhere - namely in designing systems that are stable and well interconnected between different systems, and developing efficient schema representations of data models, among other things.

The reality today, is I can buy an entire backend, I can even buy a backend that will automatically stand up API endpoints in GraphQL or REST, (or both!). Even though this is true, the demand for backend engineers hasn't shrunken dramatically (if anything, it seemingly increased).

Technologies enable things in unforseen ways all the time, and whether LLMs will displace alot of tech workers will be up for debate, and the reality is - for some at least - it will, but overall, if we take the closest situations possible from the past, it will overall increase the demand for software engineers over time, as LLMs paired with humans have thus far shown that it works best that way and I foresee that continuing to the case, much like accountants + excel is better than accountants - excel.

Re: GitHub Copilot Workspace: Technical Preview

#143

Post by goncalo-r »

sdesol wrote: post #84

Interesting. I don't think the AI code generation will live up to developer expectations, but I do see the value in "project management for developers". The value I see with workspace is not the code generation, but the ability to help developers organize their thoughts.

Imagine if AI could update my Jira ticket status.. I would pay big money for that.

Re: GitHub Copilot Workspace: Technical Preview

#144

Post by Bnjoroge »

danenania wrote: post #95

For anyone who might be interested in an open source, terminal-based approach to using AI on larger tasks and real-world projects, I'm building Plandex: https://github.com/plandex-ai/plandex I've tried to create a very tight feedback loop between the developer and the LLM. I wanted something that feels similar to git. Apart from the planning and code generation itself, Plandex is also strongly focused on version cont…

just played with it. pretty solid! questions for me, how do you validate the new changes will work without any issues after applying them? the biggest issue I have with most code generators is the feedback loop from suggested code -> testing it out -> failing, doing it again. would be great if this was more seamless. additionally, would be helpful to control the code generation process in real-time.

Re: GitHub Copilot Workspace: Technical Preview

#145

Post by 015a »

paradite wrote: post #123
singluere wrote: post #112

While I've not used this product, I've created somewhat similar setup using open source LLMs that runs locally. After having used it for about three months, I can say that debugging LLM prompts was far more annoying than debugging code. Ultimately, I ended up abandoning my setup and going in favor of writing code the good old fashioned way. YMMV

Locally running LLMs in Apr 2024 are no where close to GPT-4 in terms of coding capabilities.

And GPT-4 is nowhere close to the human brain in terms of coding capabilities, and model advancements appear to be hitting an asymptote. So...

Re: GitHub Copilot Workspace: Technical Preview

#146

Post by specproc »

paradite wrote: post #123
singluere wrote: post #112

While I've not used this product, I've created somewhat similar setup using open source LLMs that runs locally. After having used it for about three months, I can say that debugging LLM prompts was far more annoying than debugging code. Ultimately, I ended up abandoning my setup and going in favor of writing code the good old fashioned way. YMMV

Locally running LLMs in Apr 2024 are no where close to GPT-4 in terms of coding capabilities.

Depends what for, I find AI tools best for boilerplate or as a substitute for stackoverflow. For complex logic, even GPT-4 ends up sending me down the garden path more often than not.

I got Llama 3 8B down over the weekend and it's alright. Not plugged it in to VSCode yet, but I could see it (or code specific derivatives) handling those first two use cases fine. I'd say close enough to be useful.

Re: GitHub Copilot Workspace: Technical Preview

#147

Post by lispisok »

msoad wrote: post #78

This should've been done in VSCode. Most developers don't want to write code in a browser. Once VSCode extension is built they could generalize it to other editors. I'm sure they are thinking of VSCode integration and I am hopping for that to be available soon

I wonder if AI tools is going to kill editor diversity. Every one of these tools VS Code is the first class citizen and other editors are an afterthought. Sure people can write their own Emacs package but that's only if the tool developers enable it and the experience is usually not as good as the official VS Code version. I can also see the future where not using VS Code is a signal you are less reliant on AI tools to code

Re: GitHub Copilot Workspace: Technical Preview

#148

Post by frontalier »

smrtinsert wrote: post #111
Lucasoato wrote: post #85

Am I the only one disappointed by Github copilot quality lately? I get much better responses by copying and pasting on ChatGPT, rather than the suggestions in the vscode plugin.

I'm pretty sure they toggle between gpt 3 and 4 depending on how much traffic they're getting in order to make sure they can meet all suggestions.

the machines were not supposed to get tired

Re: GitHub Copilot Workspace: Technical Preview

#149

Post by idan »

Yenrabbit wrote: post #131
idan wrote: post #8

Hi All! GitHub Next here, happy to answer questions about Copilot Workspace and Next in general <3

Looks extremely cool. Have you shared / do you plan to share examples of this in practice? I would be great to read some case studies or even just browse some actual PRs rather than trying to judge from the catchy video :)

GitHub Stars have had access to this since last week, and a few of them have made in-use videos:

- https://www.youtube.com/watch?v=FARf9emEPjI by Dev Leonardo - https://www.youtube.com/watch?v=XItuTFn4PWU by Ahmad Awais

And keep an eye on https://x.com/githubnext, we'll be sharing / linking to more in-action things.

Any PR created with Workspace will have a link to a readonly copy of the workspace so you can see how it happened. We expect those to start circulating as people get access!

Re: GitHub Copilot Workspace: Technical Preview

#150

Post by candiddevmike »

singluere wrote: post #112

While I've not used this product, I've created somewhat similar setup using open source LLMs that runs locally. After having used it for about three months, I can say that debugging LLM prompts was far more annoying than debugging code. Ultimately, I ended up abandoning my setup and going in favor of writing code the good old fashioned way. YMMV

I had ChatGPT output an algorithm implementation in Go (Shamir Secret Sharing) that I didn't want to figure out. It kinda worked, but everytime I pointed out a problem with the code it seemed more bugs were added (and I ended up hating the "Good catch!" text responses...)

Eventually, figuring out why it didn't work made me have to read the algorithm spec and basically write the code from scratch, throwing away all of the ChatGPT work. Definitely took more time than doing it the "hard way".

Post reply on HN