TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

I Spent 24 Hours with GitHub Copilot Workspaces

136 点作者 dshipper大约 1 年前

23 条评论

extr大约 1 年前
I&#x27;ve noticed the same issue with AI coding, where you start to write requirements and then realize that you yourself don&#x27;t have a perfect idea of what exactly this feature should be, or how it should work. It&#x27;s easy to say the answer should be to simply think harder, or enter a dialogue with the AI about missing details, but if you try that you&#x27;ll find yourself supplying an enormous amount of context you didn&#x27;t expect to have to communicate. Context not even directly related to the code at hand, but about the broader business or industry, past lessons learned, something the CEO said to you last week about the feature, etc.<p>It&#x27;s this kind of thing that makes me think tackling big feature requests is still an AGI-complete problem. Perhaps if it gets good enough at pure coding you can iterate your way to success.
评论 #40249884 未加载
评论 #40250359 未加载
评论 #40249462 未加载
评论 #40250263 未加载
评论 #40249961 未加载
评论 #40249623 未加载
评论 #40249815 未加载
评论 #40250861 未加载
评论 #40250661 未加载
sottol大约 1 年前
The main thing that makes me skeptical is still what happens to a code base when you do this longer-term. And not just the code base but also the company when nobody understands the code any longer, but maybe neither are problems.<p>A couple questions:<p>* Will the codebase turn into a mess over time by having the AI apply changes over changes over changes? Do we even care? Or do we want a human to still be able to follow what is going on?<p>* Will you just be able ask the AI to refactor it all and clean it up? Then it wouldn&#x27;t be a problem I presume.<p>* Are product-based tech companies&#x2F;startups still defensible if anyone can basically recreate the product with some English?<p>* I don&#x27;t know Codepilot Workspaces - are the prompts that generate and change the code kept somewhere? Imo they&#x27;re part of the codebase now.
评论 #40250130 未加载
评论 #40249802 未加载
评论 #40249889 未加载
评论 #40249905 未加载
评论 #40250344 未加载
评论 #40249957 未加载
评论 #40250211 未加载
siliconc0w大约 1 年前
This debunking video(<a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=tNmgmwEtoWE" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=tNmgmwEtoWE</a>) of Devin really questioned the usefulness for me. It created a file in the repo and spent a lot of time debugging its own unnecessary code rather than reading the Read Me to understand that the code it needed to use already existed and just needed to be run with different inputs.<p>It&#x27;s not clear it we&#x27;re even near a point where it can independently and meaningfully contribute to an existing codebase rather these greenfield demos. Feels similar to the self-driving AI hype where level 5 is still pretty far from realized (Waymo is closest but AIUI still uses a lot of remote human intervention).
评论 #40250347 未加载
HanClinto大约 1 年前
When reading posts such as these, it occurs to me that AI is increasing the rate &#x2F; lowering the bar for developers to make the jump to leader &#x2F; architect.<p>Look at the lessons that the author has learned here:<p>* More specificity == better<p>* The importance of clear bulleted delivery items &#x2F; criteria-for-success<p>* Unspecified details around a general goal is a ripe area for disappointment<p>All of these are things that a product owner &#x2F; team leader learns in their first few projects (and so often must re-learn as the years go by).<p>AI is lowering barriers and promoting more developers to this role earlier. But everything that we learned about good Agile development in the past will still apply to the future.
评论 #40253918 未加载
frereit大约 1 年前
I&#x27;m honestly surprised at the relatively positive reception to this. While there isn&#x27;t any problem with the code shown, the same effect couldn&#x27;ve probably been achieved with a few well thought out shortcuts in any IDE (delete outerHTML of svg tag, add new tag, add attributes). The only &quot;more complex&quot; output that is shown is the specification that CW produces, which literally contains an error in the first line (&quot;Sp&lt;logo&gt;ral&quot;).<p>Moving on to the complex task, the author simply hand-waves &quot;this isn&#x27;t good yet but surely it will be&quot;. No evidence is given as to _why_ there should be any expectation of LLMs getting there.<p>And the perceived benefit of discovering that their idea of the more complex task was not thought out enough did not come from the LLM, it came from the author itself. They may as well have spoken to ELIZA or a rubber duck.<p>What am I missing?
评论 #40250202 未加载
评论 #40251034 未加载
throwaway71271大约 1 年前
Copilot is so strange for me, I use it, but it deeply conflicts with the way I code.<p>As I type the code I get a feeling if I like it, I also pretend to use it even when its unfinished, kind of like playing a game. Even if I spent a lot of time thinking about what I am going to write, until it exists and I play with the code, I don&#x27;t know if its good.<p>Now Copilot writes so much code, even if it exactly what I was going to type, I kind of lost the intuition, and I hate it.<p>So I just enable it when I do things that I don&#x27;t consider programming anymore.<p>I still think it is absolutely amazing tech though, and I know it will get better and better, and at some point it will be hard to not use it, but I really enjoy playing with the code as I write it.
anotherpaulg大约 1 年前
My open source tool aider [0] has long offered an &quot;AI pair programming&quot; workflow that is similar but not identical to Copilot Workspaces.<p>Aider is more of a collaborative chat, where you work with the LLM interactively asking for a sequence of changes to your git repo. The changes can be non-trivial, modifying a group of files in a coordinated way.<p>Workspaces seems more agentic. You need to do a bunch of up-front work to (fully) specify the requirements. Even with a perfectly formulated request, agents often go down wrong paths and waste a lot of time and token costs doing the wrong thing.<p>That&#x27;s also not how I code personally. My process is usually more iterative.<p>Another big difference compared to Workspaces is that aider is primarily a CLI tool. Although I just released an experimental browser UI [1] yesterday, making it more approachable for folks who are not fully comfortable on the command line.<p>[0] <a href="https:&#x2F;&#x2F;github.com&#x2F;paul-gauthier&#x2F;aider">https:&#x2F;&#x2F;github.com&#x2F;paul-gauthier&#x2F;aider</a><p>[1] <a href="https:&#x2F;&#x2F;aider.chat&#x2F;2024&#x2F;05&#x2F;02&#x2F;browser.html" rel="nofollow">https:&#x2F;&#x2F;aider.chat&#x2F;2024&#x2F;05&#x2F;02&#x2F;browser.html</a>
评论 #40254030 未加载
throwaway918274大约 1 年前
Nobody is running faster towards the cliff of their own destruction than programmers.
评论 #40250174 未加载
ike2792大约 1 年前
I might be a curmudgeon, but I think that even teaching CS in Python is too new-fangled and high-level for CS students. Learning the hard way with C&#x2F;C++ (or for a more modern flair Go or Rust) and understanding how to handle pointers and memory allocation makes it a lot easier to debug things when the higher level languages and frameworks have issues. A class or two on coding with AI would be great at the undergrad level, but not basing an entire curriculum on it.
评论 #40250985 未加载
tbeseda大约 1 年前
My experience was similar[0] and my conclusions line up with the author here. Summed up: thinking about the problem is the hard part. I can think faster than I can code, but I can code faster than I can write out (in a detailed enough way to achieve my goal with Copilot Workspace) the spec.<p>[0] <a href="https:&#x2F;&#x2F;tbeseda.com&#x2F;blog&#x2F;previewing-github-copilot-workspaces" rel="nofollow">https:&#x2F;&#x2F;tbeseda.com&#x2F;blog&#x2F;previewing-github-copilot-workspace...</a>
vundercind大约 1 年前
… am I wrong for thinking the actual play Workspaces is making is in corporate spyware, and the rest is mostly secondary as far as what may get businesses to pay for it?
评论 #40249398 未加载
kulor大约 1 年前
There was an impressive demo at AWS Summit London of their Code Whisperer and Q products taking a similar route to CW. Provide a user story and it&#x27;d create a PR.<p>I could see &quot;AI workspace driven development&quot; being the future of at the very least cutting through the smaller tickets of work and generally improving developer workflows.
评论 #40249472 未加载
Kon5ole大约 1 年前
I think AI copilots are great for coding. The IDE and compiler are a second source of truth so you can quickly eliminate AI generated nonsense and figure out what kind of problems it is good at solving.<p>To me the effect seems similar to going from assembly language to C or from C to Java or Visual Basic. It&#x27;s a new level of abstraction that saves massive amounts of time.<p>I think the amount of work for software developers will increase just like it did back then. Many software projects are never started because they will be too expensive. If they can be done by half the number of people in half the time using AI tools, they might get a &quot;go&quot; instead.
bengale大约 1 年前
I think the disconnect with these tools is that their endgame is not to be a developer tool, it’s to take them out of the loop.<p>This is a tool for product owners, it’s just too early for them to use it by itself.
aantix大约 1 年前
The author is a software engineer and his last name is &quot;Shipper&quot;.<p>Talk about high expectations!<p>This guy ships code.
ozten大约 1 年前
No mention of Cost for a task completed.<p>A similar system, CrewAI, I ran their hello world and it cost $4 against GPT-4.<p>There is a trade-off between my time and the cost of the feature against me just coding it up with LLM assistance which has a fixed cost of $20 per month.
Fin_Code大约 1 年前
I&#x27;m still not sure how this is different than the vs code plugin. It seems to function in about the same way. Just uses a bit of different context reference. But that scope can easily lead to incorrect code targeting.
评论 #40249438 未加载
justinclift大约 1 年前
&gt; CW took two to three minutes to return.<p>Hmmm, wonder if there&#x27;s cheaply sourced labour of the human variety in that loop then?
akiselev大约 1 年前
Any way to get access? All the AI product waitlists are killing me and I was stuck for months on the last GHNext waitlist.
andrewstuart大约 1 年前
I tried GitHub copilot in vscode. It was immensely frustrating.<p>The main problem was context. It didn’t seem to know what files to use for our discussion, didn’t listen when I told it, didn’t remember when I told it, had no effective way that I could bring files in and out of the discussion.<p>All this led to a deeply frustrating session of interaction and frankly I hated it. Easier to use ChatGPT web ui and copy and paste in and out.<p>GitHub copilot I found better in jetbrains ides. It seemed mostly to know what I was asking about though it’s very long was from being good at managing context.<p>It’s surprising that after the amount of development they’ve put into copilot it still is so bad at what I’d consider to be barest minimum functionality to integrate into an IDE.
intended大约 1 年前
ChatGPT will happily tell you how to build ocean liners in landlocked deserts, or how to ice skate up a hill.
marc_ranieri大约 1 年前
It&#x27;s pretty much having an assistant changing hieroglyphs to the alphabet...
ianbutler大约 1 年前
To answer the question of whether something like this is the future of programming posed at the end of the article: I think in a lot of ways yes. It reduces the iteration time for making a new feature and handles a lot of the project management too. As AI get&#x27;s smarter it makes sense to design workflows around how their capabilities can complement ours as developers and not just force them into existing workflows.<p>We&#x27;re working on something similar to workspaces: <a href="https:&#x2F;&#x2F;www.bismuthos.com" rel="nofollow">https:&#x2F;&#x2F;www.bismuthos.com</a><p>We provide a workspace to build Python backends. Chat on the left, code and visual editors on the right. However, we also handle deployments, data storage (we have a blob store), serving (we built a home grown function runtime) and logging.<p>The experience is tightly integrated with our copilot and the idea is to get ideas off the ground as quickly as possible with as little devops hassle. Right now the focus is on building something new, but we&#x27;re in the process of making it easier for existing projects to integrate with us too.<p>Feel free to drop by our (very) new discord too: <a href="https:&#x2F;&#x2F;discord.gg&#x2F;E5Yn3vaM" rel="nofollow">https:&#x2F;&#x2F;discord.gg&#x2F;E5Yn3vaM</a>