Recently I found out that the Translucent Blues album by Ray Manzarek and Roy Rogers isn't on any legal streaming platform. Only one full-album upload on YouTube. Made me sad.
I can understand where they come from. If most of the pull-requests were AI-coded, well, the maintainers are equally capable of prompting Claude Code themselves.
I think the whole game of software engineering, open source or not, has completely changed. A lump of code doesn't mean or imply the same thing as it did 2 years ago.
A few years ago, if I send a complex PR that compiles and passes tests, that implies a certain amount of time and cognitive investment on my part. It seems likely that I wouldn't invest that if I didn't also understand the codebase, the feature or bug I'm working on, etc.
Now, that understanding is roughly as expensive as before, but AI has vastly reduced the cost of generating the code that compiles and passes tests.
Probably-well-intentioned community members are happy to contribute the cheap thing( Claude Code tokens) but, because it's so cheap, it's not a good indicator they've contributed the expensive thing (human understanding).
"Writing Code vs. Shipping Code: Productivity Effects Across Generations of AI Coding Tools"
As the FT summarizes,
> They found an explosive impact at the top of this funnel — coders created or edited almost 300 per cent more files — but that boost was halved to 150 per cent by the time they got to the number of discrete pieces of work submitted for review, and that in turn shrunk fivefold to a roughly 30 per cent uplift in the number of full software releases.
So as I wrote, AI vastly improves labor productivity on _coding_, but not nearly as much on code _review_ or other parts of the release pipeline.
And, unfortunately, for many open source projects, it's easy for volunteers to send code for review, but hard for them to volunteer reviewing PRs, managing releases, etc.
I argue that it’s no longer proof of being invested in a project beyond whatever benefit one derives from the PR. It wasn’t fully to begin with, but now it definitely isn’t at all :)
> If most of the pull-requests were AI-coded, well, the maintainers are equally capable of prompting Claude Code themselves.
I see this position a bit: the notion that AI-generated code has no value. I think it's easy to generate zero-value code, but I don't agree that all AI-generated code is zero-value. I've been working on my side projects in OpenCode, and I spend quite a bit of time prompting, setting up the right files, descriptions of the product I'm trying to build, and the roadmap for it. I have a tight validation loop that lets me run through a bunch of automated checks after each change, and then I do a bunch of manual testing through edge cases that the generated feature might screw up, and then I iterate. It's a different kind of work, but I can make progress more quickly than I could coding by hand. Validation loops are the main critical component.
My experience doing this over the past months is that using AI to code is a skill, and I learn new techniques and get better at it as I try stuff. But that also suggests that, when done well, it can produce something of value.
All of this is to say: while I take issue with your first sentence, I completely agree with your second sentence. What we've lost is the ability to distinguish easily between something well-thought out and something generated thoughtlessly. Focusing on cheap validation would help here immensely, as well.
The code just isn’t the main effort of work anymore. Anyone can generate the implementation, so it makes more sense than ever to instead hammer out the what, why, and how that underlies any code change.
I see all projects moving this direction. Makes more sense to hash out a plan together.
Code was never the main effort of work, but it was a clear signal that someone has done the main effort, which is understanding the codebase, designing a new feature, or investigating a bug, and have the knowledge to write the code. By the time you get to review, you can expect a knowledgeable person on the other end.
It’s the same about published journal article. A lot of them are a few pages. That is mostly one hour of typing. But everyone knows that typing it is not the work.
Right, and all of that is what I consider to be the "code" effort:
Deep research in the codebase, deciding on the flavor of code to write that matches the project, deciding how you'll model the feature with types, how to architect it so that it's testable, writing the tests, foreseeing cases beyond the obvious path, etc.
What changed is that it can be automated. Or, just grant a world where AI is perfect at implementation.
Now our time/energy/attention is freed up to concentrate the work around planning what to build. And the interesting part is that it becomes the input into the AI implementor.
This is a good thing since we tended to skip the planning stage since it's hard in its own way. Or we start building something and then try to synthesize a high level direction from it, yet now since refactoring is so expensive, we're committed to a solution.
For anything but the most trivial change, a prompt is not enough though. There's a long iterative process of generating the right code, reviewing it, testing it, experimenting with UX or design for maintainability, fixing bugs... even a predominantly AI-generated PR can capture a lot of value. But apparently trying to distinguish those from the 'one-shot' vibe coded PRs is too much work for the Ladybird team.
> But apparently trying to distinguish those from the 'one-shot' vibe coded PRs is too much work
That is exactly the issue. Projects that are end-user applications - as opposed to libraries or development tools - probably see far more slop than actual work like you've described. The yields are too low for it to make any sense to try to figure out which is which, their time is better spent doing the work.
When I contribute to OSS with AI I’m essentially engaging in a donation matching scheme where Anthropic matches 1 to 20 the dollar value invested (usually I can get ~2k of value per month on the $100 plan) in the open source project.
So any project that doesn’t accept AI PRs is really missing out on significant investment
> the maintainers are equally capable of prompting Claude Code themselves
I'm 100% on the side of maintainers here, but this is BS. If you could "just prompt Claude yourself" the AI productivity boosts would be in hundreds if not thousands of percent, which is demonstrably and self-evidently not the case (at least as of June 2026).
Initially I thought AI would be great for FOSS because suddenly open source projects could get up to speed with paid options. UIs could get better (albeit boring/soulless) with Claude Design, etc.
But then I guess someone has to pay for all of those tokens. It's "easier" to devote your time but much harder to justify spending $300/mo on contributions to open source.
So maybe some people see this almost as a donation? Hey, I paid for tokens and generated a PR - be grateful for my donation!
And then they completely disregard the fact that reviewing the generated slop becomes way too much for the contributors. They would probably have appreciated a monetary donation more.
Some design stuff are quite bad like the Liquid Glass, but the rest is fine I think. The M series wouldn't have gone as well as it did if software side wasn't up for the task
Walking in noisy environments is most of the usage people get out of noise cancelling headphones. The other use case is noisy workspaces or coffee places.
The app reminds me of the boom of (IMO) cool Mac apps around 2010. It's a great idea as well, I wish I had thought of it. The price is out of reach for me though...
Is there a tool which eliminates the animation, also when switching between apps with cmd+tab? I almost never use ctrl+→, I just know what application I want to switch to.
All these apps that I tried only fix the ctrl+→, but not application switching
To me it's a little like the situation with charging the Mighty Mouse. It's become a meme to post a picture of it on its side being charged, but if you own one it doesn't really matter, as you charge it once a month for 15 minutes while you're at lunch.
There are things which definitely do bother me like the Liquid Glass, but the window corners really don't bother me. And I'm into design and constantly inspect parts of ui with Digital Color Meter app.
You have a truly Magic Mouse if yours charges in 15 minutes. In my experience, it is hours to charge from zero, which until I put an always-running monitor in the menu bar for the mouse battery level is what you are guaranteed to have since there is no other indicator of mouse battery level.
I used to roll my eyes at the complaints until I actually had one of these, and it is appallingly bad engineering. Especially since the previous design, which was functionally identical just needed a 10 second battery swap.
I don't understand how these type of projects are still tried and get any traction... anyone who has tried them will 100% know it won't go beyond a happy path demo. If they want to seriously use/publish the app beyond playing around, it'll require weeks of iteration via AI, which will cost you an arm and a leg in tokens.
Founder of Raycast here so obviously biased but you’ll be surprised. You get a working app one-shotted pretty much all the time. Sure if it is something more complex you might need a few more prompts. Just to give you some examples on what we’ve seen:
- Our support team runs on Glaze apps to review Raycast extensions. It connects to GitHub, checks out code locally, gets realtime updates and so on.
- The sound agency build a functioning synthesiser for the launch video. It works even with MIDI.
- We’re about to cancel a team-wide subscription and replace it with a Glaze app.
Not everything is possible yet and sure more complex things need more prompts but you’ll be surprised what Glaze is capable of already. It’s day one…
Sales are about distribution, they have a channel. This "moat" thing matters to unestablished start-ups a lot more. We should apply context while copy pasting arguments.
This just means that the existing sales channel would be their moat. Which can be a valid argument, though I don't remember having heard of Raycast before, so it isn't obvious to me. I was interested in hearing what they see as their moat here.
This sounds promising. If I may take advantage of you being here, what language does it write in? Does it build genuine native apps (Cocoa, WinAPI or WinUI, etc) or Electron?
The FAQ was light on technical details. But I am someone keen to read all the technical details :)
I assume there is an extensive set of rails for the agent to tie into. (Compare this to asking Claude to green fields an app. Do you use electron? How are notifications handled? Icons? Permissions?)
It springboard off Raycast’s teams feature so well it actually gives it a real reason to exist. You’re empowering the one systems thinker in the group to export their automations to the rest of the group in a way that’s proven to work: small apps that do one thing. (Big apps get complicated, become full time projects that distract from the task at hand)
Fig tried this but it was just for engineers, the value prop was missing, Glaze seems to get this right.
What kind of application are you thinking off? We build fairly complex applications in days for our clients, from presentation to launch. These are not trivial applications or landing pages; accountancy, payments (banking), erp, hrm backends, portals and mobile apps.
I haven't used v0 or replit before, I have the same feelings as you. But I've been thinking about building macOS apps for my personal use for a long time now. Also I'm a long time Raycast user. I have a bias here, so I've joined the waitlist, I can't be sure until I try, right?
Just build Mac apps then. Claude Code can help you whip up real native apps without any Glaze dependencies just fine. I’ve built 4 Mac and iOS apps in the last 6 months for my own use. I even have my own HN app for iOS and Mac.
Even if you don't like Electron, I was able to get Claude to build Electrobun and Tauri apps as well. I don't understand what benefit Glaze will bring outside of more lock-in?
100% agree. My default is also DuckDuckGo, but I know for a fact that if the search is anything other than finding the homepage of a company, I'm gonna struggle with duck. I still use it because I want to not use Google, but Google is 10000000% a superior product.
