It doesn't, as it is run through an Oblivious HTTP relay run by a third party before getting to Apple's servers. So it has no IP information, and the requests use anonymous access tokens.
It is probably possible for an entity to break it, but it would require live access to both Apple and the third party (Likely Cloudflare) servers. And that is assuming there is only one third party routing OHTTP requests, otherwise you would need to monitor all of them, in real time, since the requests are transient.
> So, if compelled, Apple could theoretically tell someone if two images came from the same camera.
No they couldn't.
If you generate two SSH key pairs on your laptop, there's no way to confirm they were created on the same machine.
There's no device identifying data in a reference image, which is the point. The factory signature, the image sensor key, the Secure Enclave Processor key and all of the signing that takes place on PCC are all device-agnostic.
The reference image is processed and eventually signed by Private Cloud Compute's post-quantum signature using a hybrid MLDSA87-RSA-3072-PSS-SHA512 scheme.
So… it's not possible for Apple to know if two images came from the same iPhone.
I am not sure I follow. The private keys in the image sensor and the SEP are static, so you can see that two images are signed with the same private key. Apple 'decorrelates' this by letting PCC verify the signature and then replacing it by their own signature:
When the user initiates developing a reference image, the device uploads the secure digital negative to Private Cloud Compute. PCC recomputes the digest embedded in the frame and verifies the sensor's signature over the pixels and that digest, verifying the certificate chain back to the sensor CA. PCC also verifies the SEP signature and chains it to the BAA CA, and it verifies the signature on the device manifest and chains it to the CA that signs device manifests at the factory. It then confirms that the sensor and SEP named in those chains belong to the same device. [...] If these checks pass, PCC then submits the commitment to our signing service, which signs it with a composite post-quantum signature using a hybrid MLDSA87-RSA-3072-PSS-SHA512 scheme. The signature is embedded in the JPEG, and the reference image is returned to the device, which associates it with the main photo from the original capture.
After the secure digital negative is successfully developed, it's automatically moved to the deleted photos folder."
So in the end it all depends on how much you trust Apple's cloud and PCC nodes. If there is a weakness in their services, Apple could record both the original signatures and their signature, and could prove whether two photos were made using the same lens/device and they could even trace it back to a specific device (by looking up the original signature + signing identity given their signature).
I stand corrected. If it’s truly only the signatures and zero other identifying info, then yes you’re as secure as the underlying algorithm. I think they implied there are multiple device-originated signatures for different parts of the data, this may open some possibilities for cryptanalysis
This is what a lot of people miss. People think, "Oh we won't need software soon, AI can just build interfaces when we need them" but in reality, the software was built to solve a problem, usually by people invested in solving that problem. Saying "Build me a todo app" will give you the sum of averages, a completely average todo app that works fine, but it isn't great in any measure.
The details are what separates the slop from the craft.
I agree with your first part, that software is built to solve a problem. But I think you sort of sidestep what makes AI exciting to non-software people with your second part. The people who are excited about this aren't excited because they can ask for a todo app but because they can solve the problem the todo app was supposed to be soling for them without needing to find and learn a todo app.
AI is the new "excel spreadsheet with ridiculous formulas on top of VB script on top of pivot tables" for the non-programmers. Yes, the AI might not do it efficiently or even always give the right answers, but the spreadsheets didn't either. For non-programmers, the computer has always been a black box, data goes in, data comes out. Usually it's right, sometimes it's wrong and the users mostly had no idea why or how. But now they don't need the middleware app. They don't need to take their data and split it up into very specially structured files, and put just the right pieces of information on just the right lines and in the right spaces. They don't need to remember to do "(foo and (bar or baz))" to get the right answer, as opposed to "(foo and bar or baz)" and get the wrong one. AI for non-programmers is the closest we've ever come to "natural language programming" for people to use. It doesn't matter that it gets things wrong sometimes, or does it inefficiently or makes something unmaintainable unless you use the AI again. What matters to them is they can say "take all this data here and swizzle the frobs" in their native language instead of learning a specific programming syntax and system. And they can point it at some arbitrary data in whatever format they happen to have the data in, and they have a halfway decent chance of getting something that does what they want.
It's not going to be pretty, it's not going to be perfect and it's probably going to break in subtle and unexpected ways. But as long as most of the time its mostly good enough, people will still use it enthusiastically. We're effectively looking at "worse is better" for the modern age and for people that aren't and never were going to be programmers.
> AI is the new "excel spreadsheet with ridiculous formulas on top of VB script on top of pivot tables" for the non-programmers.
This is exactly it. Moving all those abominations to bespoke applications at least lets us (Actual programmers) provide them with the tools to make their solutions a bit less bad. Linters, unit tests, code formatters etc. will make even the crappiest "this would've been a complex excel spreadsheet in the past" solution at least manageable.
And if a company doesn't have a workflow for supporting these, they'll either have a whole ass problem with people doing it without telling anyone or should get on it immediately.
Sometimes I don’t need my todo app to be “great” or revolutionary in any way. I just need it to work, and bog standard average is perfectly fine for a lot of things.
This frees me up to spend more time at the design level, solving harder or more novel problems.
Flight Control was one of my favorite iOS games of all time. Simple, polished, quick to play. Sucks that there is no way to play it on iOS again, seems it is still available for purchase on Steam, but it was really well suited to the phone format, not really something I'd sit down to play at a desktop.
Planes? Trains? If you haven't used these motion dots, they actually do work wonders. My wife gets motion sickness and could barely ever look at her phone when riding as a passenger in the car, even just to type in directions. With the motion dots she does just fine.
I always wanted a pixelbook as I loved the hardware design and the taller aspect ratio screen, it was just too expensive for me to spend on a chromebook only laptop. IMO it looked nicer than the Macbook Pro's of the time.
The Mac Studio's disappearance is related to the fact that people now want them for the purpose of running local models. Supply and demand. That plus Apple doesn't shift prices for released products, and it essentially became underpriced when large RAM quantities exploded in price. For the price of 512GB of RAM alone you could get an M3 Ultra with 512GB of unified memory in a nice, quiet, and power efficient package. With the RAM you still need to spend a few thousand more on CPU/GPU, power supplies, storage and case.
Also the fact that an M5 version will be coming, and they likely know they are going to sell out on day one (I expect we'll see a price correction from Apple for higher end configs of M5 studios, base price will probably stay the same), so they need to build up stock reserves.
I think reading is the difference. People didn’t whip out a newspaper when they had less than 30 seconds available. The smartphone has filled these gaps with an infinite amount of content.
Also, community. In a doctors office reading a paper - it is the same thing your neighbor is reading so you can talk about it. With smartphones, this is lost unless there is a pressing global event.
Yeah - similar thing for me as well. A lot of times there would be something I want to work on that would be boilerplate/repetitive/laborious work and I would just procrastinate it for as long as possible, working on other things, until I'd finally get around to doing it. Now those are just immediately completed with a simple prompt and instead of going with the initial implementation, I have the bandwidth to tweak and refine details that I would have skipped over before just to ship.
Just anecdotal, but I was using Claude Code for everything a few months ago, and it seemed great. Now, it is making a ton of mistakes, doing the wrong thing, misunderstanding context, and just generally being unusable.
I now have been using Codex and everything has been great (I still swap back and forth but generally to check things out.)
My theory is just that the models are great after release to get people switching, then they cut them back in capabilities slowly over time until the next major release to increase the hype cycle.
Is it the models themselves or the tools around them? There's that patch[1] that floats around for Claude Code that's supposed to solve a lot of these problems by adjusting its tool-level prompts. Also, if it were the models themselves, wouldn't Cursor users have the same complaints (do they? I haven't heard anything but the only Cursor users I talk to are coworkers)?
I think it's more likely they're trying to optimize the Claude Code prompts to reduce load on their system and have overcorrected at the cost of quality.
Yeah, shorter time frame but I've been noticing that too. Just the other day I was experimenting with some workflow stuff. "Do x and y and run tests and then merge into develop."
Duly runs, and finishes. "All merged into develop".
I do some other work, don't see any of this, double check myself, I'm working off of develop.
"Hey, where is this work?"
"It is in this branch and this worktree, as you would expect, you will need to merge into develop."
"I'm confused, I asked you to do that and you said it was done."
"You're right and I did say that but I didn't do it. Shall I do it now?"
There's like this really weird balancing act between managing usage, but making people burn more tokens...
People keep saying this, but I’m not sure I buy it.
I was using both Codex and Claude Code heavily on some projects this weekend.
In one project Codex was screwing everything up and in another one absolutely killing it. I’ve seen the same from Claude.
In the bad Codex example it had the wrong idea and kept trying to figure out how to accomplish the same thing no matter how many times I attempt to correct it. Undoing the recent changes where it went down the wrong path was the only way to get things back on track.
I wonder if context poisoning is a bigger problem than people realize.
Interestingly, Apple's newest and cheapest laptop (the Neo) is super repairable. And even the keyboard is finally replaceable without having to replace the entire top case. Hopefully the trend is continued in the next redesigns of the Air and Pro which are due soon.
Next year all consumer devices are required to have user replaceable batteries in the EU. Apple has noticeably been making massive design changes on many products to get closer in line with these laws.
It is probably possible for an entity to break it, but it would require live access to both Apple and the third party (Likely Cloudflare) servers. And that is assuming there is only one third party routing OHTTP requests, otherwise you would need to monitor all of them, in real time, since the requests are transient.
reply