Not jumping to something controversial when doing predictive text isn't censorship. You can still type any of these things. When I swing my finger around wildly it's making a best guess; not jumping to a phrase that makes me look bad or get arrested (in some countries) isn't an awful design choice.
> you can now ship cross platform apps quickly, without electron.
The opposite is also true. My argument is that you can also ship Electron apps with more features more quickly with LLMs.
You still have a finite token budget. With native apps, you have to split those tokens across multiple platforms, whereas with Electron, you can reuse most of the code.
Big companies have been going back and forth between native and cross-platform approaches even before LLMs. They generally have the resources (humans, tokens, compute) that small and medium-sized companies don’t have. So I’d take their rationale with a grain of salt.
Because any kind of budget, resources are always finite? 2x the tokens roughly translates to 2x the cost. That’s a pretty big ask. Quality alone, unfortunately, isn’t always enough to justify it. There has to be business value too.
The ad Yahoo puts in this article is amazingly ironic
> Jeff Bezos backs a platform that lets anyone invest in rental homes for as little as $100 — 6 ways to build wealth like a landlord without actually being one
You could buy a share of VNQ for $96.23 as of market close today, and I'm sure Jeff Bezos at least has some exposure to it, so I guess it's factually true? Heh.
Yes! I got annoyed that I had to manually close old finder/preview windows, so I OSSd an app that closes any stale window. There have been commercial apps in this space a decade, but none worked how I wanted (per window not per app, config each app separately). So I just made it with Claude using some spare tokens at the end of the week. You can customize anything to be the way you like it now.
This particular item never been a problem for me because I incessantly close everything after I am done with it but it is super cool that we can ask AI to dig into the weeds for us now and fix our annoyances -- or even search repos online where someone else had and fixed this problem
Sometimes I am shocked by how blind Spotlight is. I will have something in my applications folder with a straightforward name -- say, Steam.app -- and it will keep picking the shortcut generated by CrossOver for the Windows version of Steam, that is nested inside a bunch of subfolders. Wtf? I ended up renaming the CrossOver version to WinSteam so it stops prefix-matching.
This is my goto SDK, it comes in multiple languages too. I'm going to be wrapping the Go ADK in CUE Nov/Dec, along with Dagger, and rebuild my personal harness from scratch which I worked on last Nov/Dec.
We started using the ADK before the go sdk was available and went pretty far with using the python one. I hated it in so far as dep management is still a nightmare in python for me. I'm sure I was just holding it wrong, but it was getting to me.
I threw Claude at it to migrate to go sdk finally and had it AB testing it all in a few days. Stuff like that would have taken me forever in the past.
Now to attack some stuff that's in niche as hell jvm languages.
It will largely be copy and paste effort, with cleanup. There are a ton of experiments in there I want to remove, mostly undocumented things.
It's mostly a rebranding (verdverm/veg), but also want to tighten things up in the process. Dagger and ADK have also stabilized their APIs on new major versions. CUE has some new features I would like to work in as well
Conceptually, and most of DX wise, it should be nearly the same.
So far it’s GPU accelerated (GPUI), cross platform, supports 95% of excel functions, supports charts, is about 40x faster than Numbers, and can render 240fps.
I thought I’d leave this process with a new appreciation for manual dev/details. I haven’t found that yet. I’m getting more into architecture details, writing more benchmarks, testing more. I know there are limits, but I’m still trying to find them.
It would be absolute garbage if I wasn’t already an engineer. It probably is absolute garbage in ways I don’t know because I haven’t read the code. But the app is… quite good. If someone invested into something like this full-time for 6 months it's hard to imagine what you'd need excel for.
reply