I am going to chalk this up as another datapoint in the "Apple cannot retain talent" chart. I don't know what the heck they are doing, but everyone they've acquired seems to leave as soon as they can instead of staying.

Leave as soon as you can, along with millions and millions in cash that you got from the sale? Who wouldn't?! Why would you continue working for "the man" when you have FU-money?

Should probably quit and sell the same thing again with a different chart because FU money isn't enough.

The price is reasonable I guess, but also, you can just get weather for free? IDK...

I'd love to see some stats on this: people leaving to start something new (be it Apple or any other acquiring company) might be over-represent because there is not much news about people staying in their job

I fixed that in my own front-end: https://github.com/rcarmo/vibes.

Nice. It is actually very close to the experience I have via RSS on Reeder.

It’s my default. It is hands down the easiest to use modern CAD software today, and I’ve tried most of them. I too use it on the iPad and Mac, wish I could get it to install under WINE.

This. I just can’t bring myself to use FreeCAD for anything. It’s been almost a decade of occasional attempts during vacation breaks and it is still one of the worst, most counter-intuitive pieces of 3D software I’ve ever used (and I paid my way through college doing early multimedia work, some 30 years ago).

Nice. I should add notifications to https://github.com/rcarmo/webterm - I already have sparklines as a CPU usage indicator and live thumbnails, but a visual highlight should be easy to add.

If I were you, I'd just start always in what you call "dashboard mode". Its underwhelming to start it up and not see the "boxes" :)

Cool project! How are you liking ghostty-web so far?

I use it every day multiple hours a day and I forget it’s a web terminal until I hit Ctrl+W on Firefox :)

I only generate skills _after_ I've worked through a problem with the model - usually by asking it "what have you learned in this session?". I have no idea why people would think it can zero-shot a problem space without any guidance or actual experience...

> I only generate skills _after_ I've worked through a problem with the model.

This is the correct way vast majority of the time. There are exceptions. When I know for certain that the models do not have enough training material on a new library or one that isn't often used or an internal tool. In those cases I know I will have struggle on my hand if I don't start out with a skill that teaches the model the basics of what it does not know. I then update the skill with more polish as we discover additional ways it can be improved. Any errors the model makes are used to improve existing skills or create new ones.

Why would you expect it to generate more effective skills when you aren't even making a salt circle or lighting incense?

Not surprising if you've been paying attention on Twitter, but interesting to see nonetheless.

I used to play this game incessantly. Audio on Firefox on Linux is, sadly, very very garbled.

I don't think this is a good "benchmark" anymore. It's probably on everyone's training set by now.

I think it could still be an interesting benchmark. Like, assuming AI companies are genuinely trying to solve this pelican problem, how well do they solve it? That seems valid, and the assumption here is that the approach they take could generalize, which seems plausible.

The point of this benchmark is that making decent SVG art is actually useful. Simon has private image prompts he uses, since he didnt say gemini failed at those it is reasonable to assume those were also successful.