Live data from Hacker News

GitHub Copilot Workspace: Technical Preview

github.blog

131–140 of 333 posts

Re: GitHub Copilot Workspace: Technical Preview

#131
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 :)

Re: GitHub Copilot Workspace: Technical Preview

#132

> At last count, Copilot had over 1.8 million paying individual and 50,000 enterprise customers. > Copilot loses an average of $20 a month per user, according to a Wall Street Journal report, with some customers costing GitHub as much as $80 a month. Presumably at some point they need to actually make money on this? That is a $432 million / yr loss just on individual users.

Despite being widely repeated they've publically denied this claim a few times (for e.g. https://x.com/natfriedman/status/1712140497127342404, https://x.com/simonw/status/1712165081327480892)

Re: GitHub Copilot Workspace: Technical Preview

#134
I think these types of tools will become really effective when they stop trying to target every single programming language and platform ever created and focus on one specific version of an integrated platform.

Most businesses don't actually need software to be in whatever flavor of the month the dev team happens to be interested in. They just want to be able customize their software.

By restricting the scope somewhat, you make it much more feasible to make sure the model has the training and/or knowledge ready for retrieval to fulfill tasks using a specific stack.

So I see this type of thing as quickly evolving into a tool for non-developers. And within a few years, these tools will cut into software engineering jobs. It will become part of the evolution of no-code and low-code.

Re: GitHub Copilot Workspace: Technical Preview

#135

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 can definitely echo the challenges of debugging non-trivial LLM apps, and making sure you have the right evals to validate progress. I spent many hours optimizing Copilot Workspace, and there is definitely both an art and a science to it :) That said, I’m optimistic that tool builders can take on a lot of that responsibility, and create abstractions that allow developer to focus solely on their code, and the proble…

I'm sure we'll share some of the strategies we used here in upcoming talks. It's, uh, "nontrivial". And it's not just "what text do you stick in the prompt".

Re: GitHub Copilot Workspace: Technical Preview

#136

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…

The hardest part of software development is not writing code, full stop. It never has been and it never will be. The hard part is designing, understanding, verifying, and repairing complex systems. LLMs do not do this, even a little bit.

or getting engineers to communicate properly with each other :)

Re: GitHub Copilot Workspace: Technical Preview

#137
post #133

I’m letting it sink in that GitHub thinks it would be a win if 10%+ of the world population is involved in creating software. I have no hope of hiring an electrician in that world.

You have succeeded at hiring an electrician in THIS world? What's their number? Do they actually show up when they say they will?!?!?!!1!one

Re: GitHub Copilot Workspace: Technical Preview

#138
post #134

I think these types of tools will become really effective when they stop trying to target every single programming language and platform ever created and focus on one specific version of an integrated platform. Most businesses don't actually need software to be in whatever flavor of the month the dev team happens to be interested in. They just want to be able customize their software. By restricting the scope somewha…

As long as it does the language that my business currently uses, I am all for that!

Jokes aside, I am not sure I buy the premise. I have read somewhere (citation required) that LLMs get better at other things after having learned how to code. And maybe they also get better at coding in one language after having learned a bunch.

Re: GitHub Copilot Workspace: Technical Preview

#140

Earlier quoted context omitted.

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…

People also forgets that coding is formal logic that describe algorithms to computer which is just a machine. And because it’s formal, it’s rigid and not prone to manipulation. Instead of using LLMs you’d better off studying a book and add some snippets to your editor. What I like about Laravel is their extensive use of generators. They know that part of the code will be boilerplate. The nice thing about Common Lisp…

You start by talking about apples and finish talking about cars.
Post reply on HN