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

151–160 of 333 posts

Re: GitHub Copilot Workspace: Technical Preview

#151

Post by lelandbatey »

sixhobbits wrote: post #20
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…

Accountants thought spreadsheets would kill their profession, instead demand for them exploded. Compilers made it much easier to code compared to writing everything in Assembly. Python made it much easier to code than writing C. Both increased the demand for coders. Code is a liability, not an asset. The fact that less technical people and people who are not trained engineers can now make useful apps by generating mi…

I've seen it already. A small business owner (one man show) friend of mine with zero developer experience was able to solve his problem (very custom business specific data -> calendar management) in a rough way using ChatGPT. But it got past about 300 lines long and really started to get bad. He'd put dozens of hours of time on his weekend to getting it to where it was by using ChatGPT over and over, but eventually it stopped being able to make the highly specific changes he needed as he used it more and more. He came to me for some help and I was able to work through it a bit as a friend, but the code quality was bad and I had to say "to really do this, I'd need to consult, and there's probably a better person to hire for that."

He's muddling along but is looking for low cost devs to contract with on it now that he's getting value out of it though. And I suspect that kind of story will continue quite a bit as the tech matures.

Re: GitHub Copilot Workspace: Technical Preview

#152

Post by odiroot »

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.

Maybe AI can at least help with the deluge of Dependabot PRs ;)

Re: GitHub Copilot Workspace: Technical Preview

#153

Post by 015a »

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…

I haven't seen any evidence that these systems are capable of structuring and executing large-scale changes in entire repositories; but given you're still a student, your definition of large might be different.

The middle of an S-curve looks like an asymptote, which is where we're at right now. There's no guarantee that we'll see the same kind of exponential growth we saw over the past three years again. In fact, there's a ton of reason to believe that we won't: models are becoming exponentially more expensive to train; the internet has been functionally depleted of virgin training tokens; and chinks in the armor of AI's capabilities are starting to dampen desire for investment in the space.

Everyone says "this is the worst they'll be"; stated as a fact. Imagine its 2011 and you're running Windows 7. You state: "This is the worst Windows will ever be". Software is pretty unpredictable. It does not only get better. In fact, software (which absolutely includes AI models) has this really strange behavior of fighting for its life to get worse and worse unless an extreme amount of craft, effort, and money is put into grabbing the reins and pulling it from the brink, day in, day out. Most companies barely manage to keep the quality at a constant level, let alone increase it.

And that's traditional software. We don't have any capability to truly judge the quality of AI models. We basically just give each new one the SAT and see the score go up. We can't say for certain that they're actually getting better at the full scope of everything people use them for; a feat we can barely accomplish for any traditionally observable software system. One thing we can observe about AI systems very consistently, however, is their cost: And you can bet that decision makers at Microsoft, Anthropic, Meta, whoever, obsess about that just as much if not more than capability.

Re: GitHub Copilot Workspace: Technical Preview

#154

Post by rahulpandita »

Bnjoroge wrote: post #144
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.

GitHubNext Dev here: We have a terminal feature that allows you to connect to sandbox in the cloud for you to validate these changes before pushing them out to your repo

Re: GitHub Copilot Workspace: Technical Preview

#155

Post by amiantos »

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…

I've been working on the same product for 6 years now, on a team of people who have been working on it for 8 years. It is ridiculous how hard it is for us to design a new feature for the product that doesn't end up requiring the entirety of the deep knowledge we have about how existing features in the product interact with each other. That's not even getting into the complex interplay between the client and the backend API, and differences in how features are described and behave between the client and server. It's, in some ways, a relatively straightforward product. But the devil is in the details, and I find it hard to believe LLMs will be able to build and possess that kind of knowledge. The human brain is hard to beat deep down, and I think it betrays a pessimism about our overall capability when people think LLMs can really replace all the things we do.

Re: GitHub Copilot Workspace: Technical Preview

#156

Post by colemannerd »

I wish there were fixes to devcontainers before doing adding copilot. I really want declarative, repeatable builds that are easily used in both Codespaces AND Actions. I know all of the functionality is theoretically there in devcontainers.json, it is so manual to configure and confusing, that anytime I've done it, I use it for 2 weeks and then just go back to developing on local because I don't have time to keep that up. ESPECIALLY if you're deploying to AWS cloud and also, want to use alternative package managers like poetry, uv, yarn, jsr, etc.

Re: GitHub Copilot Workspace: Technical Preview

#157

Post by nojvek »

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…

I have yet to see an LLM build and debug something complex. Barely stringing TODO apps, sure.

Still need a competent human to oversee. Hallucination are a serious problem. Without symbolic reasoning, LLMs quickly start to fall apart due to context limits and being able to know what exactly is wrong and needs to be changed.

Re: GitHub Copilot Workspace: Technical Preview

#158

Post by nojvek »

I use Github co-pilot but 55% productive is a bullshit number. Perhaps 1% may be. Most of co-pilot suggestions are either simple pattern matches or subtle hallucinations where I have to catch and fix silly bugs.

Github Chat is not very useful at understanding what the code is doing. Tried it once or twice and gave up.

The hype will help with Microsoft Stock though. Seems like bean counter management is taking over.

Re: GitHub Copilot Workspace: Technical Preview

#159

Post by greatwhitenorth »

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…

Give an example of "structuring and executing large-scale changes in entire repositories". Let's see the complexity of the repository along with what it structured and executed.

Re: GitHub Copilot Workspace: Technical Preview

#160

Post by padthai »

lispisok wrote: post #147
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…

A thousands of small cuts, almost everything comes first to VSCode before other editors, even mainstream things are underrepresented in most other editors (Jupyter, commercial integrations, etc…).

Although that was true about Atom too though?

Post reply on HN