HN user

rc1

30 karma
Posts1
Comments28
View on HN
CursorBench 3.1 21 days ago

I'm pretty baffled by their choice of axes

To put their own model out in front?

Available via XR engine binary only

Is on the binary available or is the source available? It is disingenuous to say it’s open source if that’s the case. How could this be supported into the future?

Hope I am wrong.

any time our instinct says "don't build that, it's not worth the time" fire off a prompt anyway, in an asynchronous agent session where the worst that can happen is you check ten minutes later and find that it wasn't worth the tokens.

They are right about new habits needed. And this is where everyone should start. Sometimes a quick prompt has killed 5 hours of meetings to discuss if it were worth it.

You missed my point. Electron apps are incongruent to native OS apps.

Electron apps look the same on each platform therefore they are consistent.

The meta point is the effort required to be consistent with the OS.

You listed MacOS only apps, emphasising the point.

To do a per OS consistent experience is N times the effort.

have inconsistent style

You mean incongruent styles? As in, incongruent to the host OS.

There is no doubt electron apps allow the style to be consistent across platforms.

Well put. What world are folks living in where it wouldn’t be the obvious choice.

Code is not the cost. Engineers are. Bugs come from hindsight not foresight. Let’s divide resources between OSs. Let all diverge.

They are often laggy or unresponsive. They don’t integrate well with OS features.

(These last two issues can be addressed by smart development and OS-specific code, but they rarely are. The benefits of Electron (one codebase, many platforms, it’s just web!) don’t incentivize optimizations outside of HTML/JS/CSS land

Give stats. Often, rarely. What apps? I’d say rarely, often. People code bad native UIs too, or get constrained in features.

Claude offer a CLI tool. Like what product manager would say no to electron in that situation.

This article makes no sense in context. The author surely gets that.

Cursor opened in config/ + HomeAssistant MCP is exceptionally good. I have blundered along with Home Assistant over the years, but it lit up with the above setup for me the other day.

For giggles, I had it set all the lights into a disco.

Next, we vibed a markdown file containing a to-do list of all my upstairs lights that are abstractly named by the different integrations. I put an x against a name and it turned the light off.

Once I identified it, I wrote a better name next to it. It updated the system.

We vibed dashboards and routines.

The problem with Home Assistant is that once it works, you don't touch it for a year and are back to square one with the layers of concepts. But I am left satisfied knowing I have backed up the conversation/context that we can pick up next year or whenever again.

A memorable computer experience.

If fairness to toon, the alternative json your giving doesn’t include hints on structure.

Not sure LLM are more “tuned” to JSON.

That said, your general point holds that toon maybe unnecessary. Especially in the examples given. But perhaps plan text would suffice. Toon could be useful when automating inputs with many different shapes.

I can think of a few reasons why it might be like that: to lead the reader into the article; to provide context of a library; to fit with the visual flow. Easy to criticise (especially on the grounds of efficiency) more interesting to critique... which is why many of these books are worth reading. Every wonder why the design of everyday computers are designed to keep us so stationary?