I recently tried the X API to fetch the latest tweets about a given topic, and I spent ~1$ in one go just to retrieve them and some additional info about the users. This is ridiculously expensive.

So I can only be happy that such service exists (though if there was a better support for an API would be 10x better)

what's the benefit of UIs in the canvas with Rust, as opposed to HTML/CSS/JS?

For a lot of front end devs, CSS/JS are frowned upon. We use it because we have to. In fact, we typically avoid JS by having TypeScript transpiled to JS. Not to mention CSS is still very inconsistent across the various browsers.

Porting HTML/CSS/JS to native apps is another big problem, which is why we ended up with Electron/WebView. The amount of RAM it gobbles up just to run simple apps is pretty horrible.

Why Rust? It's a strongly typed application language across browser and native. It also has a massive ecosystem and this allows us access to all of it.

BTW canvas is only the renderer. There's a lot of engineering that went into making the canvas not a typical "canvas UI app". We have solved accessibility, touch gestures, direct/immediate draw etc.

There's more reasons behind this if you're keen, I've written up a more comprehensive doc https://dev.to/zionsati/html-javascript-css-should-have-died...

ts is superset of js, so I wouldn't say you avoid it. It's like saying you run to avoid walking.

On the web, I get that CSS is not straightforward, and HTML is not the coolest technology, but by using the canvas you also lose a lot stuff that you need to rebuild from scratch: accessibility and interactivity, responsiveness, etc. So the only argument that I'd buy is that it has lighter & more performant UIs, which I get it might, given that the canvas uses the GPU, but is it worth the effort? Like, is it THAT much better?

I get the argument of native apps though. I guess if you want to build one interface and serve it both as a web and native app, it could make sense.

Edit: thanks for the link - I'll look it up. Also I didn't mean to sound too annoying. I'm starting to see UIs built in Rust but I'm still struggling to see the hype.

Yeah all good. They're all good questions.

My point around ts is people want strongly typed languages these days.

The bigger problem with HTML/CSS is, when you're trying to do more sophisticated things (see the immediate drawing page on the demo), you'll find you need to use a canvas/HTML5. That then becomes a mini UI framework of its own...

For simple webpages, HTML/CSS is probably still the best way to go. But I wouldn't say the same for webapps?

Isn't using the auth of Claude subscription on another UI (that is not Anthropic's) not allowed and causing risk of ban?

There is a risk. However, users of the extension have not reported any account suspensions. There were suspensions earlier this year, but Anthropic later unlocked these accounts.

I don't know. I mean, "never argue" is not a good maxim, imo.

But sure, ultimately your role is to provide your opinion as an expert, but you should step aside if your manager decides otherwise after hearing you. I think it's also correct: you are responsible for the decisions you make (which is true for you and your manager too).

So I think the author should have softened the discussion rather than going for a full confrontation. The boss surely didn't react rationally, or didn't surface their reasoning properly.

But being able to argue with your superiors (and peers) "the right way" is one of the most important skills to have in the workplace imo.

Great article! One question: you talk about market size, but you don’t address the existing competition in the space. In my opinion, two equally sized markets can have very different levels of competitive pressure.

Is that something you factor into your playbook? Or do you simply not find it relevant to judge whether to enter a certain space?

(not the author, but here's how I think about it)

Assuming that you're not a commodity product, it all kinda nets out in the end. If you have a competitive market, you have proof that people want your product at a good price, else no one would be in the market. If you execute better than all of your competitors, then you can theoretically take every last penny of that market.

I don't think the competitive pressure changes the decision whether there's revenue to be made in a certain space, though it may change the personal decision if the operating tactics required in a competitive market are personally fun for you the human being.

I should add something about this, but if a market looks like a drunken bar fight, I'd probably not want to go there.

That said: A good market will become crowded quickly in either way.

Super interesting! How accurate is the local model to transcribe audio compared to other cloud services? E.g. Google Meet, Otter, Granola, etc.

A lot of the available models are Whisper or Faster-Whisper derived and shared across multiple apps. The tier names are often funny... "Tiny" "base" "small" "medium" "large" "large-v2" "large-v3" "large-v3-turbo" -en only variants, etc.

In my experience, medium is often the sweet spot for English accuracy vs speed, especially if following-up with a post-processing pass. The large options are all fine, but can severely slow it down. There are some speed checks on my website if you're curious (link not posted because I don't want to hijack another post's app).

so does Photoshop and thousand other visual editing tools. Hardly a reason to claim it to be a copy. Also "slopfork" seems harsh considering it seems limited, but well designed imo.

Maybe a little harsh yes. But compare these screenshots of the two products/features

https://imgur.com/a/41BybD1

I see a deep tree and a shallow tree in the two screenshots, representative of entirely different approaches.

What would it take for you to ever admit that you are wrong.

I recently started looking into hydroponics gardening. You can start very easily with a Kratky system and some herbs, and then take it a step at the time.

I’m quite at the beginning myself, but I like it so far! It’s a nice mix of science and craft.

Yep! I have a small setup with just some used food grade pickle buckets, and have been growing greens and things for a bit over a year. Going to get some more and expand them this year. It literally uses no power as pumps are not used, and water usage is very minimal. I live in the desert so low water usage is very important.

It's an interesting hobby, as you have to adapt it to the area you live, and where you grow the plants.

Unfortunately, I think Cursor is making progressively more difficult to use other AI provider via extension, mostly due to the fact that they are reserving the secondary sidebar for their own chat interface. This makes it super unpractical to use the Codex and Claude extension, as now they all need to share the primary sidebar. (Before it was not optimal, but it was at least possible.)

As many have pointed out, the cost of token via Cursor is prohibitive compared to having a CC or Codex subscription, so I think the new update brings little to current users, but reduces Cursor's usability.

I think Cursor should go in the direction of embracing other provider's extensions and go for a more integrated and customizable IDE, rather than a one-solution-fits-all kind of an approach. Today I opened VSC again after a log time.

I use Zed. Much less user hostile.

The premise of Zed is quite appealing, but I'm not sure I'm ready to switch due to the missing extension ecosystem of VSC. For example, at the moment I'm using the Playwright and Vite ones to quickly run and debug tests.

I wanted to like zed, but then I discovered it is limited to one concurrent agent tab and that is a dealbreaker..

It's open source, so you could try to have your agents patch it! You can also just load up agents in terminal tabs.

I don't use concurrent agents much though so I can't really relate.

Zed is incredible, such a relief

How does Zed compare to let's say vsc

Hard to say. I haven't launched VS Code or any of its derivatives since I first used Zed.

I mean it makes sense for them to be somewhat antagonistic towards these flows because every time you use a different agentic extension or tool inside of Cursor, Cursor loses your money and data.

They're also churning with enterprise customers because for lots of customers on next contract renewal their pricing is increasing like 4-8x (depending on usage patterns but this was what we calculated for most of our devs) because they are slowly moving enterprise customers to usage based only plus a surcharge per million tokens, which they already did with personal sub customers, and all of the latest models are becoming Max mode only. My company is currently going through this and we've committed to way less spend with Cursor for our renewal and are signing with Anthropic and telling devs to prefer using claude code instead. I wouldn't be surprised if next year we cancel altogether and tell all devs to go back to VSCode or some other preferred editor.

I don't see a world where Cursor continues to be viable for 5-10 more years. Lots of people were originally saying "the moat is not in being an model provider" for agentic tools and thats turning out to be very much false in my opinion at least if you care about being a business.

yeah good point. I think this is to be seen though. Right now AI tokens, especially via OpenAI/Anthropic subscriptions, are heavily subsidized. If token cost between the API and subscriptions should even out though, then I think Cursor might well be back in the race.

Can you share what approach you’re taking for this? I’ve tried engaging in a similar way but struggled to strike a balance between helping for the sake of helping (no return for me), and asking research-focused questions, with people not caring too much about to answer