One must imagine Mark happy, living in his metaverse.

i kinda wish he would do that and then forget this reality. it did dawn on me that when he was talking about how great it would be to meet AI friends that this guy is just desperately trying to escape a world he feels rejected/hated at large in and get to one where he can feel beloved and accepted. All of these billionaires seem to have a similar weirdly sad story where they just want to haul everyone off to follow some dumb idea of a new world, buncha broken people.

I always wondered what happens if police forcibly enter someone's flat in these places. Do they ram the doors and then politely take off their shoes before entering? I see a comedy potential.

It's a great story teller. Not really a good expert though.

It's the opposite feeling for me.

Not sure about other brands but pretty much any ThinkPad I use, the touchpad just feels right. Whereas on Macbooks it's just off, at least ever since the first Retina generation (my first contact with it).

Macbooks' touchpads are usually also way too big and, sadly, even Lenovo follows this bad trend in some of their models.

Then again, EU citizens would find it questionable how in the UK recruiters are asking about your ethnicity, disability status etc.

UK also arrests you for boomer facebook memes. Then again maybe parts of EU too.

For me, showing the time, calendar notifications and turn-by-turn navigation with Google Maps is all the smartwatch has to offer. Sleep tracking is a good extra. That's it.

Pebble was great at providing that, with crazy good battery life.

I think they were joking...

What problems are there with appimages?

Yet I have to install a not very famous, maybe unmaintained daemon to get basic system integration

It is already pre installed in most distrosk

Or at least our public pension systems.

You just need a very strong frontier model to do triage of your tasks.

/s

That's not necessarily a joke; the article proposes exactly that.

It's funny how codex itself can't do Sol orchestrator / Luna implementor out of the box.

That's surprising. Does it have no sub agent support at all or does it just use the same agent as the parent?

They do have subagents, released v2 of that feature with the launch of 5.6 model series in fact. It's just... very poorly executed, is a significant regression from subagents v1 and thousands of miles behind subagents of Claude code.

- Models that can be launched as subagents are hardcoded (can only be another Sol or Terra, but not Luna). Most of the time it'll just launch same model as parent anyway.

- They encrypt initial task delegation from root agent to subagent, for whatever reason

- You can't switch into subagent view at all, despite the fact that apart from initial root>subagent task handoff, all session is visible in transcript.

Which is why I use CLI subprocesses as subagents... Codex in 2026 is still nowhere near where CC was in summer of 2025...

With Claude you can have "use a lower tier subagent when appropriate" in CLAUDE.md and it'll just work. The "smart" agent goes in a busy loop observing the subagent(s) and will confirm their work afterwards.

(also you need to gate it with "tell the subagent it's a subagent" and "if you are a subagent, don't spawn subagents" or you'll get a matroshka doll of sonnets all the way down =P )

Codex kinda sorta can launch a subagent, but that's about it.

I mean, yeah. Alternatively I’ve seen the approach of starter with the cheaper/faster model but give it a tool to handoff or talk to a strong model if it gets stuck.

*Maria Skłodowska-Curie

Yeah, that's precisely one of the reasons why there shouldn't be faces on bank notes. Shame on the nationalists that managed to make dreck out of it.