After my brief read, one of the main reasons they’re using PCC to produce the signed JPEGs, instead of doing everything on device, is that it maintains your privacy.

If you were signing with the iPhone, an attacker could then correlate photos taken with the same device.

Apple certainly has the data that “this sensor, in this device, took this exact photo” in PCC at the time of signing, but they discard that data.

I’m curious if the lack of speaker identification is a privacy thing, or a technical limitation.

It looks like it uses PCC, so it may run into usage limits

It feels like such a stereotypical big corp misstep, but based on the reputation that google’s AI products have, I guess I’m not _that_ heartbroken. It’s mostly frustration that they forced the price increase on everyone, and I’m definitely not receiving the benefit.

What sorts of things are you doing with the local LLM? Anything interactive? Should I take another look?

Am I getting these results because I picked the wrong model? Or I need to improve my prompt? Or the tool just can’t do what I’m trying to do? How current are these model recommendations? Have they been superseded by something newer?

As a true beginner to AI at the time, even the sizes and bits were meaningless to me. And I don’t remember having any context as to what I should be attempting to run on my mac.

So I think you need to include steps 4, 5, and 6 of swapping between different models, quants, and prompts. And step 7 is probably wading through the complicated UI, full of jargon that most people don’t know.

Don’t get me wrong, I recognize that it’s a powerful tool, and the steep learning curve exists because it exposes quite a few power-user features. But for someone graduating from commercial AI image generators that take a text prompt and maybe a choice of couple models, it’s not easy.

I believe your flaky SD card is category 4, Disk Drive and Flash Memory Failures.

Also, the 3 Musketeers candy bars used to come with 3 flavors in the package: chocolate, strawberry, and vanilla. Cost cutting led to eliminating the 2 less popular flavors.

Stripe isn't keeping all of that "1.5% - 3.25% + 20p", they're paying the network some portion.

Additionally, instead of using the blended pricing model you quote, they do offer IC+ pricing to (at least some) businesses. I don't know the criteria. On IC+, you're explicitly paying "whatever the network costs" + "fixed Stripe fees"

https://stripe.com/resources/more/interchange-plus-pricing-e...

> Larger and fast-growing businesses often choose interchange plus pricing because it passes through the true cost of each transaction. At high volumes, its net cost is often lower than that of blended pricing. It also gives finance teams true oversight because it shows where all the money goes. That makes it easier to forecast costs, spot inefficiencies, and negotiate or shop around for the processor markup.

It could be fun to implement a scientific notation result display for answers that would otherwise overflow, although off the top of my head I'm not sure what the cleanest way to do that is.

> Now I delegate that work to AI.

> […]

> If one day passes and nobody on the team reviews the PR, we merge it

It’s not clear to me whether or not the author is reviewing the code their agent is committing on their behalf, so maybe I shouldn’t be surprised that they don’t seem to care whether or not their team is reviewing it either.

But I am surprised. The author says they used to spend quite a lot of time writing developer guides, hopefully by building consensus among their peers. It seems to me like a big shift if it’s now a workplace where they might not even read each other’s code changes.

Or maybe the dev guides were top-down directions on the way they want the team to do things, and now AI is super compliant and they’re living the dream.

It’s not the final word, since automation has other benefits: documenting the procedure’s steps, reducing human errors, increasing consistency, etc.

1: https://xkcd.com/1205/

> How often does a restaurant update a menu? Those that need to update frequently already solved that by having a chalk board.

One advantage of a digital ordering system: it can track inventory and mark a dish as unavailable after N have been ordered.

Some restaurants might have menu updates in the middle of service quite frequently, if they have a daily special with a fixed quantity. Most restaurants probably have an unavailable dish occasionally. Or if a beverage choice becomes unavailable, or a new beer is put on tap.

I don’t think ease of menu updates would be the deciding factor for any restaurant, I think it’s more likely to be based on the experience they want their customers to have