Foundation Models framework

imagetic | 2 hours ago

Why is this up front on HN? Did it get an update?

HelloUsername | 2 hours ago

Discussed last year when it was announced https://news.ycombinator.com/item?id=44226978

michaelbuckbee | 2 hours ago

There have been a few published rumors of Apple getting ready to release a new set of local models.

albertgoeswoof | an hour 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 | an hour 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.

zf00002 | 19 minutes 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.

amelius | an hour ago

I'll ask my LLM to build me a framework, thank you.

steve1977 | an hour ago

Why would you do that, assuming that you're not coding yourself/using the framework?

dvdplm | an hour ago

Can the local model code at all? Eg as the predictor in Zed?

mcemilg | an hour 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...

tasoeur | 9 minutes ago

Curious if it’s possible to use a non-API plan for Claude/ChatGPT with this? It could actually be pretty useful.