There are moments where I have a 2 hour , 4 instances in separate Kitty/Ghost windows , Opus 5.5 hammering away on each - and only see a 1% increase on my Max x20. Then there are other days where 10 minutes of a single xH Opus doing 1/10th of the work will kill 2%.

Anthropic is super opaque with what inference costs at any given moment on the subscription and cache is just super inconsistent.

I wouldn't be surprised if they have some implementation of demand-based surge-pricing

Rust for-the-fuck-of-it rewrites have become the new Javascript because-we-can rewrites.

  "It’s Rust, compiled to WASM, running in your browser. Not a JavaScript rewrite. Just because we can. It’s Rust, dude. Try it."

Making the justification for this project's existence especially meta on so many levels.

Don't hide it, run with it

I have a Vision Pro (M2 original). At no point have I ever compared it to a Mac or MacOS. The experience is decidedly iPad/iPadOS like.

Did I miss something?

EDIT: You likely mean going with the M series instead of the A series. Got it.

This sounds like pure insecurity with a sprinkle of Dunning Kruger. Unless I'm missing the joke somewhere? Nurses don't mind needles is the only difference? I must be missing the joke.

Pluto and the modern day understanding of Neanderthals are probably Top 5 learning corrections in my lifetime.

What was it about Pluto?

Presumably that it’s now considered a dwarf planet and that there are multiple other d. planets in the system, of similar size such as Haumea (minor-planet number 136108), Eris, etc.

The dwarf planet is just a naming thing. I don't know if beyond oluto bodies are a new or recent thing. I was thinking someone discovered something completely different like totally new findings about its geology or something like that.

Pluto is Mickey Mouse's pet and is not anthropomorhic. Not to be confused with Goofy that is an anthropomorphic dog and Mickey's friend.

Here's the funny thing about cartoons and confusion. In the comic Popeye the antagonist is named "Bluto" but only sometimes. He was renamed as "Brutus" because of a misunderstanding of rights ownership.

https://en.wikipedia.org/wiki/Bluto#Bluto_vs._Brutus

However, because it was a misunderstanding, his "Bluto" moniker was later restored, and even retconned as the name of twin brothers.

Popeye has never been a Disney property. But the funny thing is that my father told me that they renamed "Bluto" so that he wasn't phonetically confused with "Pluto", who is obviously a different character in a different property. And that premise is the one that I grew up believing, until Wikipedia was invented.

And Minnie is a mouse and has a cat as a pet, Figaro.

You forgot the "2 = 5" one

What happens when my ADD riddled brain dumps 500 tasks that are either artifacts of procrastination or a new shiny problem that I want to solve but shouldn't be in this thing?

This is the best use case, you share all 500 things, and we manage them.

We do some organization for you (project creation, or sorting into projects you've already created), and each morning we go over all the open items, using the information you shared, any deadlines, urgency, and if you're waiting on a certain date to start. Then we rank them, and send you the three that come up, with the why, so you can reason over just those three, and correct us if we got it wrong.

And as for aspirational tasks? I had a "clean my office, this week" task that popped up as the third on my list, when the other two were taking me multiple days to do (actual tasks, not projects, just lots of trial and error so they took days), and after ignoring the task for two days, the app asked me if it was really important, and it was right, so I rescheduled it for after launch.

This app is meant to help you get things done, but it can't make you do them. So if you procrastinate, all it can do is read that signal, and offer what help it can (alternatives, reprioritization).

The gap between 2/2.5 to 3 was a lot longer than any gap between 3 and a theoretical 4.

Training data is filled with shortcuts, conveniences, bugs, hacks, hacks that fix other hacks, hot fixes, patches, mappings that map the hack to hack to a better solution and all types of other surprises.

That's the cost of trying to scale so quickly. You dont filter out the crap.

A nice side effect is that the best way to fix it is more AI.

It's a endless money loop.

From the article: "He was also at pains to point out that the reverts were not down to 'vibe coding' in development, as the technique was not available when most of the new features were written."

I wonder when people will finally feel comfortable not putting vibe coding in scare quotes. Maybe when it accounts for 50% of all new software, instead of only 10%.

Journalists are in general slower to do this kind of thing than technologists.

The article mentioned the exact opposite.

Why read the article when you can read the headline and make up your own?

I think these type of new techniques will ultimately create more jobs for humans. If we think the answer is just “AI” everyone will create their own Postgres with a lot more bugs and vulnerabilities.

Reminds me of the car they'd dress up to look like a Countach, the Fiero.

Looks like a Fiero