Hacker Newsnew | past | comments | ask | show | jobs | submit | franze's commentslogin

my claw controls my old M2 mac, mostly my claw uses Claude code to code

So you're using a different llm to control claude code to get around the Anthropic TOS about openclaw usage?

At this point I'm personally lost, unless GP's comment wasn't some sort of satire (which would be valid, this being a topic about AI).

Thx. Good point. Done.

4mb download, after install about 15mb, model is already on your mac with mac os x tahoe

no. the on device foundationmodels framework that apfel uses does not have access to personal information from the apple account. the model is a bare language model with no built in personal data access.

apple does have an on device rag pipeline called the semantic index that feeds personal data like contacts emails calendar and photos into the model context but this is only available to apples own first party features like siri and system summaries.

it is not exposed through the foundationmodels api.


thx for the report - a totally valid attack vector i was not aware of before, should be fixed https://github.com/Arthur-Ficial/apfel/releases/tag/v0.6.23 - see also new https://github.com/Arthur-Ficial/apfel/blob/main/docs/server...

project started with

trying to run openclaw with it in ultra token saving mode, did totally not work.

great for shell scripts though (my major use case now)


the 2 hard limits of Appel Intelligence Foundation Model and therefor apfel is the 4k token context window and the super hard guardrails (the model prefers to tell you nothing before it tells you something wrong ie ask it to describe a color)

parsing logfiles line by line, sure

parsing a whole logfile, well it must be tiny, logfile hardly ever are


the model prefers to tell you nothing before it tells you something wrong

If all LLMs did this, people would trust them more.


I created "apfel" https://github.com/Arthur-Ficial/apfel a CLI for the apple on-device local foundation model (Apple intelligence) yeah its super limited with its 4k context window and super common false positives guardrails (just ask it to describe a color) ... bit still ... using it in bash scripts that just work without calling home / out or incurring extra costs feels super powerful.

Neat! I’ve actually been building with AFM, including training some LoRA adapters to help steer the model. With the right feedback mechanisms and guardrails, you can even use it for code generation! Hopefully I’ll have a few apps and tools out soon using AFM. I think embedded AI is the future, and in the next few years more platforms will come around to AI as a local API call, not an authorized HTTP request. That said, AFM is still incredibly premature and I’m experimenting with newer models that perform much better.

this is great! Incredibly fast and is working pretty well running loads on my m4 max studio.

Weirdly though I'm getting things like this: Apple FM is fast and free but has a hard limitation — it can't process prompts with Spanish/non-English words, which is a dealbreaker for California and Southwest real estate where half the street names are Spanish.


Dieser apfel ist sehr lecker!

This is quite interesting. I wonder if AFM is smart enough to do spam classification.

this is real neat. I'll give it a spin.

Honestly I can't believe Apple put that foundation model product out the door. I was so excited about it, but when I tried it, it was such a disappointment. Glad to hear you calling that out so I know it wasn't just me.

Looks like they have pivoted completely over to Gemini, thank god.


yeah, it is super limited but also you can now do

  cmd(){ local x c r a; while [[ $1 == -* ]]; do case $1 in -x)x=1;shift;; -c)c=1;shift;; *)break;; esac; done; r=$(apfel -q -s 'Output only a shell command.' "$*" | sed '/^```/d;/^#/d;s/^[[:space:]]*//;/^$/d' | head -1); [[ $r ]] || { echo "no command generated"; return 1; }; printf '\e[32m$\e[0m %s\n' "$r"; [[ $c ]] && printf %s "$r" | pbcopy && echo "(copied)"; [[ $x ]] && { printf 'Run? [y/N] '; read -r a; [[ $a == y ]] && eval "$r"; }; return 0; } 
cmd find all swift files larger than 1MB

cmd -c show disk usage sorted by size

cmd -x what process is using port 3000

cmd list all git branches merged into main

cmd count lines of code by language

without calling home or downloading extra local models

and well, maybe one day they get their local models .... more powerful, "less afraid" and way more context window.


This really makes me think of A Deepness in the Sky by Vernor Vinge. A loose prequel to A Fire Upon The Deep, and IMO actually the superior story. It plays in the far future of humanity.

In part of it, one group tries to take control of a huge ship from another group. They in part do this by trying to bypass all the cybersecurity. But in those far future days, you don't interface with all the aeons of layers of command protocols anymore, you just query an AI who does it for you. So, this group has a few tech guys that try the bypass by using the old command protocols directly (in a way the same thing like the iOS exploit that used a vulnerability in a PostScript font library from 90s).

Imagine being used to LLM prompting + responses, and suddenly you have to deal with something like

  sed '/^```/d;/^#/d;s/^[[:space:]]\*//;/^$/d' | head -1); [[ $r ]]
and generally obtuse terminal output and man pages.

:)

(offtopic: name your variables, don't do local x c r a;. Readability is king, and a few hundred thousand years from now some poor Qeng Ho fellow might thank his lucky stars you did).


That would be pretty cool if the model was a little more useful, but it isn't very good. And the guardrails are hilariously bad.

     cmd print first and last line from stdin
    $ echo -n | tail -n 2


     cmd print first and last line from stdin using sed
    error: [guardrail] The request was blocked by Apple's safety guardrails. Try rephrasing.
    no command generated

What is the AI doing here? Or is this just like being cheeky?

The pile of shell and sed is cleaning up the ai output and then running it in the shell.

The instruction to the AI was to create _a_ shell command. So it's a random shell command generator (maybe).


that part is the system prompt, the script is a function that takes a prompt describing a shell command as an argument

But it's gotta be just a joke right? Which is why all the examples are just classic things you do with bash/unix utilities?

I'll just say, if not a joke, the bit is appreciated either way!

"AI change to the home directory. Make it snappy!"


mv /Users/beepbooptheory /Users/snappy

In Apple’s defense, they did make it do something borderline useful while targeting a baseline of M1 Macs with 8 GB of RAM (and even less in phones).

nice project, thanks for sharing.

any plans for providing it through brew for easy installation?


There's a very similar afm CLI that can be installed via Homebrew.

https://github.com/scouzi1966/maclocal-api


done

  brew tap Arthur-Ficial/tap
  brew install Arthur-Ficial/tap/apfel

No need for the extra tap step, this works fine alone:

    brew install Arthur-Ficial/tap/apfel

Looks like they just added homebrew tap to the instructions

good idea

…is it a reference to apfelwein?

just german for apple, cause reasons

I thought it was a reference to Wine, the Linux Wine, and then thought of apfelwein. Nvm!

.... so what? the technology exists, the models exist. Even when the bubble bursts things will not go to the state "before AI". Even if model development would stop today (not the worst thing to happen) it would still be the most impactful invention since the printing press

Yes, that’s what the author wrote in the second sentence of the post: "AI is here to stay."

I guess the point is that without the hype subsiding it enshitification will ensue.

Super Cool, Love it.

I love new clock designs, here is my try https://triclock.franzai.com/


This is really cool, even better than the post, IMO (sorry OP!)

One question: when the second hand resets from 60->0, it visually jerks as the triangle moves. After the smooth movement, gradients, the cool multicolour fill, it feels very odd. Any way of smoothing that one out? Animating the flip back to zero? I do understand it's a one-way line not a circle...


Love the look of that! Really cool

I love your clock btw.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: