chris_st

Thanks, I enjoyed that explanation quite a bit (didn't understand everything, but enough to get a major clue).

I think of focus-follows-mouse as a different thing. FFM raises the window under the mouse, but doesn’t move the text insertion point (at least on X and Windows, the only two places I can remember using it). But the Apollo’s window manager was different - moving the mouse moved the insertion point along with it.

> the fact there are two pointers on the screen -- one for the mouse and one for the keyboard -- if you slide the mouse pointer to a specific point and press a keyboard key, the new key will not appear where the arrow is, it will appear where the text cursor is.

I remember using an (early?) Apollo computer that worked that way... I was warned by the person showing me, and a bit later he accidentally bumped the mouse while I was typing! Letters all over...

I believe this was in the era before X windows took off for unix boxes. I miss SunTools - it was nice and simple.

I had personal subscriptions to WebStorm and GoLand and cancelled them not long after getting Windsurf. Just don't need the IDE abilities like I used to... Still use 'go to definition' but that's pretty much it.

As a resident of an independent living facility, I live among a lot of people who use various makes and models of powered chairs. And a great many who have the joystick dislike it immensely, and would prefer to have the handlebars-style navigation. But it's kind of the only way to have the "chair" style, nothing in front of you design. Some of the more scooter-style have rotating chairs, so you can park parallel to a table and turn, but that depends on lower limb mobility, so no easy solutions here.

The "climb a 13° slope, clear a 2-inch curb and cross a 4.7-inch gap" is quite impressive.

You might want to look at Simon Willison's showboat [0] tool, which generates walkthroughs of code to explain changes.

[0]: https://simonwillison.net/guides/agentic-engineering-pattern...

Cool, thanks!

Just curious, why the 'sudo tee {file} > /dev/null'?

A few that I looked at are annotated, "It is linearly stable (largest Floquet multiplier 1.000), so a small nudge only makes it wobble." Doesn't define "small nudge", alas...

I use it, and have been happy with it for the most part. Like sibling, I use it for GPT-5.6-Sol and Opus work, and use their free models (GLM 5.2 for the past few months, trying SWE-2 now).

Wow, so beautiful (and I say this as a tea drinker :-)

You'll find that those goalposts are very movable.

I'll check that out - I loved his "The Code Book: The Science of Secrecy from Ancient Egypt to Quantum Cryptography". Excellent introduction to cryptography.

I really liked her "Uncharted with Hannah Fry" podcast, sorry it ended.

FWIW, Cognition has all the Sonnet/Opus/Fable models, and all the GPT ones, as well as GLM, Kimi, and Gemini.

What "non-house" harnesses have you found to work best?

Interesting to see (roughly!) what percent of each car is engine.

I have this setup, roughly, with UTM rather than orbstack. I think I have it set up safely, curious how you see it has the wrong permissions?

Another way I'm "going slower" is to have the AI implement individual sub-steps of the current task, and review each one. It's slower than having it yolo out the whole thing, but it's much smaller incremental bits to review, so my brain doesn't glaze over in a huge review, like I had if I had it do the whole task.

I'm following an Ideas -> PRD -> Issues -> Tasks methodology, where each task has a bunch of sub-tasks. I have it just do one (or a few, I'm having it do Red/Green/Refactor as separate sub-steps, so I review the Red case, and then once that's good, do the Green and Refactor steps, and review those).

Yup, just like people!

Good!

Nope, not better quality if you don't like the smell of cigarettes.

Please add support for the Windsurf editor as well. Thanks!

Awesome, stealing that!

And they're clearly marked as `unsafe`, so easy to find, which gives them a nice list of issues to address.

I asked Claude to tell me why something was implemented the way it was, and got an excellent response. One data point, would love to hear more examples.

...it came as a surprise that [leaving a Petri dish out with a window open] would end up with interesting [molds] (called [penicillin]). _It was not planned at all_.

Well, to be fair, people cheat by remembering what they did last time. I think the idea here is to run the models from a "clean slate" and see how often they succeed/fail.

They are, like people, non-deterministic, so giving them several "fair" trials makes sense to me.

Possibly because they just haven't been able to manufacture enough of them yet to be a viable business to others? They're fighting everyone else for foundry space and time.

But it's pretty cool that LLM bug hunting is pretty cheap... the 1-person projects can do it themselves, don't have to contract out to some huge security company.