Foundation Models framework (developer.apple.com)
156 points by kermatt 7 hours ago
cj00 12 minutes ago
I actually think their CoreAI stuff is kind of flying under the radar. But they've got a repo at https://github.com/apple/coreai-models where they're adapting a ton of open weight models to their format to run natively with Swift.
btown 3 hours ago
> For those just getting started, developers who are enrolled in the App Store Small Business Program and have fewer than two million first-time App Store downloads can access the Apple Foundation Models running on Private Cloud Compute with no cloud API cost.*
https://developer.apple.com/private-cloud-compute/
> Where Apple Intelligence is available, eligible developers can use PCC in their apps distributed on the App Store, and test PCC features via TestFlight or ad hoc distribution. Installs during testing are not counted as first-time app downloads.
Is this free tokens? This sounds like free tokens?
nseggs an hour ago
Pretty much. You need an Organization developer account, not an Individual account to get the PCC entitlement, but after that it’s pretty easy. I’ve been using it in TestFlight and now a shipping app since WWDC and it’s pretty solid. A lot more performant than I had expected. Context windows could be a bit larger (though it’s much better than the on-device model). PCC usage is allotted to the end users Apple ID or iCloud account , not the app or my development account, which makes it possible to ship a lightweight app and not worry about my own server costs. Some of the background gotchas and PCC rate limiting behaviors are obnoxious but I’ll take what I can get. Some of it is just standard iOS behavior.
taneq 2 hours ago
This sounds like free samples of tokens.
MBCook 8 minutes ago
Not exactly. They’re not your tokens, they’re the user’s tokens. If those are different people.
Your app uses tokens when it goes to private cloud compute tied to the user’s iCloud account. I don’t think anyone knows what the limit is, we only know that higher iCloud plans bring higher limits.
It’s all very fuzzy right now as this is brand new and I think they’re just trying to incentivize development rather than risk strangling it out of the gate.
albertgoeswoof 6 hours ago
I’ve been using these in my terminal for correcting errors and suggesting commands https://github.com/paul-oms/prompt
Surprisingly capable on an m1 8gb (in my opinion this is the smallest machine that local ai needs to run on)
jshier 6 hours ago
Interesting. Have you had issues with the model safety restrictions at all? They seem rather aggressive for normal usage, I wonder if limiting to command line options keeps things safe enough they stay out of the way.
cj00 3 hours ago
Yeah I found the safety restrictions really aggressive. Enough that I just gave up and used Gemma instead.
zf00002 4 hours ago
I have my firewall events get reviewed by the local model on my mac studio. I had to stop sending the full event because the model would refuse some requests.
mcemilg 5 hours ago
I just realized that claude has also support App Attest for months [1]. Not sure if that is being used widely. Firebase was the most practicle option to call llms directly from ios apps without having fancy setups. I am surprised Anthropic not promoting this more.
[1] https://github.com/anthropics/ClaudeForFoundationModels#auth...
imagetic 6 hours ago
Why is this up front on HN? Did it get an update?
HelloUsername 6 hours ago
Discussed last year when it was announced https://news.ycombinator.com/item?id=44226978
michaelbuckbee 6 hours ago
There have been a few published rumors of Apple getting ready to release a new set of local models.
an0malous 4 hours ago
Where did you see these rumors?
_pdp_ 3 hours ago
I have been using Foundation Models in Noodle for a while and have liked working with it. One part I have not explored yet is Apple Private Cloud Compute but it is on my list. I think I need special entitlements that are only available to Siri desktop app for now - need to check.
This is the repo if you are interested https://github.com/pdparchitect/noodle
tasoeur 4 hours ago
Curious if it’s possible to use a non-API plan for Claude/ChatGPT with this? It could actually be pretty useful.
dvdplm 5 hours ago
Can the local model code at all? Eg as the predictor in Zed?
bobertdowney 3 hours ago
Even the stronger Private Cloud Compute model struggled with the coding task I gave it (build a web-based side-scrolling platformer). I used this and pointed Cursor at it to test: https://github.com/littlebobert/pcc-server-example
okaymac 16 minutes ago
Siri AI is very clever
okaymac 16 minutes ago
Siri AI is too clever!!!!!
amelius 6 hours ago
I'll ask my LLM to build me a framework, thank you.
steve1977 5 hours ago
Why would you do that, assuming that you're not coding yourself/using the framework?