Despite all the “Apple is evil” or “Apple is behind” (because they don’t do evil). Well, what they made with the Foundation Model is great. The fact that they build a system within the Swift language that allows you to specify structured data models (structs) to be used like any other model in a modern programming language, and you actually get back generated data in that format is great. Unlike a lot of other AIs where you might get back a well formatted JSON after a carefully crafted request, but still you never can’t be sure and need to implement a bunch of safeguards. Obviously it’s still the beginning and other tools might do something similar. But as an iOS developer that makes the usage of AI so much simpler. Especially with the bridge to external AIs that still allows you to map back to the type safe structured Swift models. I try not to be a hater, every progress, even slow or underwhelming at first might lead to improvements everywhere else.

▲

0x457 11 hours ago | parent | next [-]

Guided generation is called "Structured Output" by other providers?

Well partially generated content streaming thing is great and I haven't seen it anywhere else.

▲

ApolloVonZ 11 hours ago | parent | next [-]

Sorry if I didn’t use the correct terms. Didn’t catch up on all the terminology coming from my native language. ;) But yes, I agree, the fact that parts, different parameters, of the model can be completed asynchronous by streaming the output of the model, is quite unique. Apple/swift was late with async/await, but putting it all together, it probably plays well with the ‘never’ (I know ) asynchronous and reactive coding.

▲

astrange 11 hours ago | parent | prev [-]

An issue with this is that model quality can get a lot lower when you force it into a structured form, because it's out of distribution for the model.

(I'm pretty sure this is actually what drove Microsoft Sydney insane.)

Reasoning models can do better at this, because they can write out a good freeform output and then do another pass to transform it.

▲

0x457 9 hours ago | parent [-]

I have this toy agent I'm writing, I always laugh that I, human, write a code that generates human-readable markdown, that I feed to llm where I ask it to produce a json, so I can parse (by code I, or it wrote) and output in a consistent human-readable form.

I'm thinking about let it output freeform and then use another model to use to force that into structured.

▲

astrange 9 hours ago | parent [-]

IIRC yaml is easier for models than json because you don't need as much recursive syntax.

	▲	t1amat 8 hours ago \| parent [-]
		I doubt this is true anymore, if ever. Both require string escaping, which is the real hurdle. And they are heavily trained on JSON for tool calling.

▲

lxgr 8 hours ago | parent | prev | next [-]

How do you think their implementation works under the hood? I'm almost certain it's also just a variant of "structured outputs", which many inference providers or LLM libraries have long supported.

▲

a_wild_dandan 10 hours ago | parent | prev | next [-]

Huh? Grammar-based sampling has been commonplace for years. It's a basic feature with guaranteed adherence. There is no "carefully crafting" anything, including safeguards.

▲

bigyabai 9 hours ago | parent | prev [-]

Apple is behind. People forget that Google was shipping mobile-scale transformer-based LLMs in 2019: https://github.com/google-research/bert

By the time Apple has an AI-native product ready, people will already associate it with dehumanization and fascism.