jannyfer

Agreed, I used to think this but now enjoy taking quick selfies, and my phone will dig them up and remind me of fond memories later on.

GP conflates selfies with posed photos.

Sometimes when I'm in the CLI and don't have a code editor open, I do this. Yes, it's lazy. But I also trust the model to check and update related things (tests, etc., while applying some judgement).

It's not unlike some managers who tell their teams to do something trivially easy that they could have done themselves.

(I'm not saying this is ideal and I'm not defending my laziness. It's just the current state of things.)

Thank you, my eyes glazed over when I saw the article was written with AI.

I'm user 7xx,xxx but I also believe I created a Github account while working on Rails projects (basically copying Ryan Bates and assembling things together. haha good times)

I’m not sure that it’s O(N) with caching but this illustrates the N^2 part:

https://blog.exe.dev/expensively-quadratic

Adding a tangential anecdote.

I asked GPT-5.4 High to draw up an architecture diagram in SVG and left it running. It took over an hour to generate something and had some spacing wrong, things overlapping, etc. I thought it was stuck, but it actually came back with the output.

Then I asked it to make it with HTML and CSS instead, and it made a better output in five seconds (no arrows/lines though).

SVG looks similar to the XML format of spreadsheets. I wonder if LLMs struggle with that?

Interesting and amazing presentation.

I also liked that it didn't explicitly say how it decides when to play a note.

All the subway routes are normalized to 15 seconds long from beginning to end. The app then plays all 15 second routes together, playing the instrument assigned to the route when there's a train there.

Neat commentary on the instruments that were assigned to the route when you mouse over it.

Isn’t it the opposite?

I have a pet theory that the uptick in normal cybersecurity PRs you mention as a trend in your blog were done with Claude Code’s stealth mode and Mythos.

Aside from FDIC’s insurance, nothing.

And if banks get hacked and money gets wired out - maybe we’ll come up with ways to roll back the damage.

Who knows - this is new territory.

What kind of code do you work on, and what model & harness do you use? Genuinely curious so I can calibrate my understanding.

I work on enterprise web apps for a few dozen people with Codex CLI and GPT-5.4, and haven't really run in to those issues.

Ooooh very interesting idea.

I also have nothing to back it up, but it fits my mental models. When juggling multiple things as humans, it eats up your context window (working memory). After a long day, your coherence degrades and your context window needs flushing (sleeping) and you need to start a new session (new day, or post-nap afternoon).

At the bottom of the page it says he is CEO of Tailscale.

There is another possibility. “Source?” is a low effort comment, but GP’s is not.

According to the blog post, it should be also great at drawing pelicans riding a bicycle.

GP does use a lot of "it's not this, it's that" pairs. :)

I’ve noticed since iOS 7-ish that some sliding animations have such a long tail-end easing of the animation that it blocks the touch input of the user. Like if you accidentally scroll to the side instead of down, you have to let go and wait for the side scroll to completely stop.

Then I watched Tim Cook have trouble with tapping the screen multiple times for one action at one of the older WWDCs pre-COVID.

I felt validated and exasperated. Does Tim just put up with this?

> What Apple does best lies at the combination of hardware, software, physical materials, and human-computer interface design.

This was true maybe a decade ago, but not so now (under the watch of Tim Cook).

You listed Mac hardware becoming popular in the age of AI as examples of "unexpected wins". Maybe that's true (I don't know if it is) - but Macs were only 8% of Apple's 2025 revenue. Apple has become an iPhone company (50% of revenue) that sells services (26% of revenue).

And AI can eat away at both. If Siri sucks so hard that people switch away, that would also reduce Services revenue from lost App Store revenue cuts. If Google bundles Gemini with YouTube and Google Photos storage, people might cancel their iCloud subscriptions.

I think the parent comment was making the point that Tim Cook's Apple has missed the boat and it doesn't show signs that it's going to catch the next wave.

I have an iPhone 16 and I'm locked in because of all my photos being on my iCloud subscription. But in 2030, if my colleague can use their Pixel phone to record a work meeting, have it diarized, send out minutes, grab relevant info and surface it before the next relevant meeting, and Siri can still only set a timer for 5 minutes, then I might actually switch.

I agree with you and I definitely noticed the “it’s not just X, it’s Y” pattern.

But I find your comment funny because it ironically has the same “not that, this” pattern in a more verbose and less polished & less formulaic pattern.

You must share that game. I don’t even know what it is and I want to play it!

This post has zero nutritional value.

Do you actually do this? I’ve thought about this but don’t have the space for it.

I lost interest when I got to the email address box to subscribe. Interrupts the flow and makes me skim the rest.

My company blocked the new URL as "games" but the old link works.

Were you born in 1997? If so, it’s possible you just weren’t senior enough to see the 80% meeting workday prior to COVID.

That would be a bad design for an A/B study (and NYC congestion pricing is not a “study” anyway), because cities are few and not alike and have an enormous list of other things that are different. What NYC equivalent would you pick?

In any case, not every policy change needs to be an academic exercise.

Maybe 10 years, because $45M is per month.

It reads like a Memorandum of Understanding.

https://en.wikipedia.org/wiki/Memorandum_of_understanding

In my experience, when you’re within 24 hours or so of an upcoming renewal, you have to contact support to stop the renewal. And there isn’t a prominent way to contact support, because the contact form is hidden until you view a past order. That’s not really an edge case…

On another note, an actual edge case that happened to me is that I was in a different country when my Uber One was about to renew, but I had no way to cancel because the app kept geolocating me and displayed a UI specific to my visiting country. I got no Uber One benefits in that country anyway. So I had to send an email to stop renewal, and while I was waiting for a reply, I got charged. Support said they can’t refund me, and I ended up having to do a chargeback.

I just asked ChatGPT with a lazy prompt: "Come up with a formula to impose reciprocal tariffs that will reduce America's trade deficit to zero" and it came up with basically the same formula.

Oh man if people in the White House are just using ChatGPT...

https://chatgpt.com/share/67ee890e-b400-800b-ac83-90a6147d32...

(edit: fixed link)