Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Apple just released a weirdly interesting coding language model

9to5mac.com

Post reply on HN
Print view View original

21–30 of 73 posts

Re: Apple just released a weirdly interesting coding language model

#21

Post by miroljub »

vessenes wrote: post #4

Short version: A Qwen-2.5 7b model that has been turned into a diffusion model. A couple notable things: first is that you can do this at all, (left to right model -> out of order diffusion via finetuning) which is really interesting. Second, the final version beats original by a small margin on some benchmarks. Third is that it’s in the ballpark of Gemini diffusion, although not competitive — to be expected for any…

When we look at the small models suitable for running locally, by far the best programming model is DeepSeek-R1-0528-Qwen3-8B. It is quite comparable in real world usage even to much bigger models.

Re: Apple just released a weirdly interesting coding language model

#22

Post by supriyo-biswas »

skylerwiernik wrote: post #8

Here's the paper that they wrote: https://arxiv.org/pdf/2506.20639 It's notable that this was an intern project.

Either this or https://huggingface.co/apple/DiffuCoder-7B-cpGRPO should be replaced with the current article.

Re: Apple just released a weirdly interesting coding language model

#23

Post by lxgr »

iwontberude wrote: post #6
vessenes wrote: post #4

Short version: A Qwen-2.5 7b model that has been turned into a diffusion model. A couple notable things: first is that you can do this at all, (left to right model -> out of order diffusion via finetuning) which is really interesting. Second, the final version beats original by a small margin on some benchmarks. Third is that it’s in the ballpark of Gemini diffusion, although not competitive — to be expected for any…

I think Apple will ultimately destroy the data center, I hope they succeed.

Maybe for compute, but not for storage.

Why can’t I backup an iOS device to a local NAS in the way I can use Time Machine, for example? (Rhetorical question; the answer is obviously that they want to sell more iCloud storage for that all-important services revenue).

Re: Apple just released a weirdly interesting coding language model

#24

Post by viraptor »

baobun wrote: post #14
vessenes wrote: post #4

Short version: A Qwen-2.5 7b model that has been turned into a diffusion model. A couple notable things: first is that you can do this at all, (left to right model -> out of order diffusion via finetuning) which is really interesting. Second, the final version beats original by a small margin on some benchmarks. Third is that it’s in the ballpark of Gemini diffusion, although not competitive — to be expected for any…

Without having tried it, what I keep getting surprised with is how apparently widely different architectures (and in other cases training data) lead to very similar outcomes. I'd expect results to vary a lot more.

It doesn't look like it got pushed that much unfortunately. The article says they only added 20k examples to fine tune at the end, but maybe the ceiling is much higher for diffusion?

But yeah, RWKV also ends up in a similar performance area with similar sizes - I wish someone started using it at scale finally...

Re: Apple just released a weirdly interesting coding language model

#25

Post by hiatus »

lxgr wrote: post #23
iwontberude wrote: post #6

Earlier quoted context omitted.

I think Apple will ultimately destroy the data center, I hope they succeed.

Maybe for compute, but not for storage. Why can’t I backup an iOS device to a local NAS in the way I can use Time Machine, for example? (Rhetorical question; the answer is obviously that they want to sell more iCloud storage for that all-important services revenue).

Synology supports exactly that, and I'm sure they're not the only one.

Re: Apple just released a weirdly interesting coding language model

#26

Post by dboreham »

jeswin wrote: post #10
vessenes wrote: post #4

Short version: A Qwen-2.5 7b model that has been turned into a diffusion model. A couple notable things: first is that you can do this at all, (left to right model -> out of order diffusion via finetuning) which is really interesting. Second, the final version beats original by a small margin on some benchmarks. Third is that it’s in the ballpark of Gemini diffusion, although not competitive — to be expected for any…

> to my mind the architecture is a better fit for coding We have to see if it produces better results. Humans have a planning phase, followed be a part-by-part implementation phase. This is reasonably well emulated by plan/architect + codegen tools.

It's delusional to think that most software projects can be planned in advance beyond "there will be a beginning, a middle, and an end". People do it, but their efforts are in my experience generally ignored once implementation get underway.

Re: Apple just released a weirdly interesting coding language model

#27

Post by IMTDb »

baobun wrote: post #14
vessenes wrote: post #4

Short version: A Qwen-2.5 7b model that has been turned into a diffusion model. A couple notable things: first is that you can do this at all, (left to right model -> out of order diffusion via finetuning) which is really interesting. Second, the final version beats original by a small margin on some benchmarks. Third is that it’s in the ballpark of Gemini diffusion, although not competitive — to be expected for any…

Without having tried it, what I keep getting surprised with is how apparently widely different architectures (and in other cases training data) lead to very similar outcomes. I'd expect results to vary a lot more.

I would expect a lot of attempts to fail and those tend to not be published, or gather less attention. So if we have reached a local optimum, any technique that gets close to the current benchmarks is worth publishing, as soon as results reach that point. All the one that are too distant are discarded. In the end all the paper you see are close to the current status quo.

It's possible that some of those new architecture / optimization would allow us to go beyond the current benchmark score, but probably with more training data, and money. But to get money you need to show results, which is what you see today. Scaling remains king; maybe one of these technique is 2025 "attention" paper, but even that one needed a lot of scaling to go from the 2017 version to ChatGPT.

Re: Apple just released a weirdly interesting coding language model

#28

Post by nsm »

infecto wrote: post #15
quaintdev wrote: post #9

Jetbrains has 100MB models of languages for their IDEs that can auto complete single lines. It's good but I think we can do better for local code auto complete. I hope Apple succeeds in their on device AI attempts.

Is any of the Jetbrains offerings even competitive. I jumped shipped from Pycharm and have tried their AI offerings a few times since release but was always wildly impressed at how far behind they were of the competition.

I've had good experiences with Junie and AI assistant at their bread and butter languages of Java and Kotlin. I haven't tried it in anger though.

Re: Apple just released a weirdly interesting coding language model

#29

Post by crappybird »

infecto wrote: post #15
quaintdev wrote: post #9

Jetbrains has 100MB models of languages for their IDEs that can auto complete single lines. It's good but I think we can do better for local code auto complete. I hope Apple succeeds in their on device AI attempts.

Is any of the Jetbrains offerings even competitive. I jumped shipped from Pycharm and have tried their AI offerings a few times since release but was always wildly impressed at how far behind they were of the competition.

Junie is so amazing. It burns through credits like hellfire, but I have only seen claude-code and opencode coming anywhere close to it.

Did you use the normal Jetbrains AI assistant, or was it junie?

Post reply on HN