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

291–300 of 333 posts

Re: GitHub Copilot Workspace: Technical Preview

#291

Post by mnk47 »

heavyset_go wrote: post #213
studenthrow3831 wrote: post #28

Earlier quoted context omitted.

I guess my worst fear is not "no more jobs because AI can code" but "no more junior jobs because AI can code under the supervision of a senior". SWE jobs will exist, but only seniors will have them and juniors are never hired. Maybe the occasional "apprentice" will be brought on, but in nowhere near the same amount. Where my blind hope lies more specifically is in networking into one of those "apprentice" roles, or m…

> I guess my worst fear is not "no more jobs because AI can code" but "no more junior jobs because AI can code under the supervision of a senior You're posting under a thread where many seniors are discussing how they don't want this because it doesn't work. You cannot make a model understand anything. You can help a person understand something. You can accomplish that with a simple conversation with a junior enginee…

>You're posting under a thread where many seniors are discussing how they don't want this because it doesn't work.

Many artists and illustrators thought AI art would never threaten their livelihood because it did not understand form, it completely messed up perspective, it could never draw hands, etc. Look at the state of their industry now. It still doesn't "understand" hands but it can sure as hell draw them. We're even getting video generation that understands object permanence, something that didn't seem possible just over a year ago when the best we got were terrible low quality noisy GIFs with wild inconsistencies.

Many translators thought AI would never replace them, and then Duolingo fired their entire translation team.

I'm sure that GP isn't worried about being replaced by GPT-4. They're worried about having to compete with a potentially much better GPT-5 or 6 by the time they graduate.

Re: GitHub Copilot Workspace: Technical Preview

#292

Post by fragmede »

troupo wrote: post #283
fragmede wrote: post #208

Earlier quoted context omitted.

Yes it can. When the project is yet another javascript CRUD app, 80% isn't brand new, never existed before code, but almost-boilerplate that does exist on StackOverflow, on a heavily trodden path where the LLM will get you 80% of the way there.

You've literally repeated what I said

but with yes instead of no

Re: GitHub Copilot Workspace: Technical Preview

#293

Post by troupo »

fragmede wrote: post #292
troupo wrote: post #283

Earlier quoted context omitted.

You've literally repeated what I said

but with yes instead of no

Nothing changed in your description compared to what I wrote. It still remains "for a well-trodden path in a well-known language with SO-level solutions it will help you, for anything else, good luck"

Re: GitHub Copilot Workspace: Technical Preview

#295

Post by fragmede »

troupo wrote: post #293
fragmede wrote: post #292

Earlier quoted context omitted.

but with yes instead of no

Nothing changed in your description compared to what I wrote. It still remains "for a well-trodden path in a well-known language with SO-level solutions it will help you, for anything else, good luck"

I'm not contradicting what you're saying, no. I'm emphasizing that the well trodden path as being the majority of the work out there, as opposed to possibly being flippant about "anything else". if I'm reading you wrong, apologies.

Re: GitHub Copilot Workspace: Technical Preview

#296

Post by slavoglinsky »

singluere wrote: post #165
lostintangent wrote: post #125

Earlier quoted context omitted.

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…

For sure! As a user, I would love to be able to have some sort of debugger like behavior for debugging the LLM's output generation. Maybe some ability for the LLM to keep on running some tests until they pass? That sort of stuff would make me want to try this :)

see langtail app (I am not maker)

Re: GitHub Copilot Workspace: Technical Preview

#297

Post by Protostome »

idan wrote: post #118
Protostome wrote: post #76

Curious to see how it goes. For 20 years I have been working with Vim and recently added the Co-pilot plugin which is awesome. I can't however see myself using a different editor/IDE than the good'ol vim. It's not that I haven't tried, but all those IDEs tend to be bloated and consume tons of memory.

When video terminals first came out, everyone started out using line editors even though line editors make no sense when you can display arbitrary buffer. It took a while until editors changed to be "screen native". But they did change, meaningfully. When GUIs first came out, editors were just "terminal editors in a window". Took a while for the modern concept of an IDE to happen, with hovers, red squigglies, sidebar…

I mostly agree with all of your points. But IMHO, if (and that's a big if nowadays, with modern web and mobile dev) text editing is the core task of the app your'e using as your IDE, then all the graphics are just redundant. All the highlighting, hovers / etc can be done via much simpler graphics that is memory and CPU efficient. As a dev, I would like to IDE developers to invest in core functionality, rather than a fancy GUI.

Take the electron IDE for example. It embeds the chrome runtime which is a total waste, given that i just want to edit some text files.

Re: GitHub Copilot Workspace: Technical Preview

#299

Post by Sammi »

KeplerBoy wrote: post #288
esperent wrote: post #269

Earlier quoted context omitted.

The bits GPT4 always gets wrong - and as you say, more and more wrong the further I try to work with it to fix the mistakes - are exactly the bits I want it to do for me. Tedious nested loops that I need to calculate on paper in particular. What it's good for is high level overview and structuring of simple apps, which saves me a lot of googling, reviewing prior work, and some initial typing. After my last attempts t…

Copilot is a decent autocomplete saving you half a line here and there, that's about it.

I can regularly get it to autocomplete big chunks of code that are good. But specifically only when it's completely mind numbingly boring, repetitive and derivative code. Good for starting out a new view or controller that is very similar to something that already exists in the codebase. Anything remotely novel and it's useless.

Re: GitHub Copilot Workspace: Technical Preview

#300

Post by michaelmior »

troupo wrote: post #97
michaelmior wrote: post #67

Earlier quoted context omitted.

> arguably the languages closest to English Yes, but they're not English. All the concerns that you mention are ones that I think LLM development tools are aiming to eliminate from explicit consideration. Ideally, a user of such a tool shouldn't even have to have ever heard of recursion. I think we're a long way off from that future, but it does feel possible.

Have you ever actually tried getting proper non-contradictory requirements in pain natural language from anyone? Good luck

This is absolutely a skill in itself. It could well be the case that such a plain expression of requirements in natural language is a valuable skill that enables use of such tools in the future.
Post reply on HN