I have a project similar to this one, running on Windows 11 because I am not an Apple user. 3B model is actually OK for simple tasks and short contexts. And I strongly support completely local inference. I don't agree with some commentators that using cloud services is still fine.
Show HN: Apfel – The free AI already on your Mac
171–180 of 180 posts
Re: Show HN: Apfel – The free AI already on your Mac
#172interesting that they added mcp support. local model + tool calling with no cloud dependency is a nice setup
Re: Show HN: Apfel – The free AI already on your Mac
#173Earlier quoted context omitted.
It's only half of the solution though. If the models are trained in a closed way, they can prioritize values encoded during training even if that's not what you want (example: ask the open Chinese models about Tiananmen). It's not beyond imagining that these models would e.g. try to send your data to authorities or advertisers when their training says so, even if you run them locally. So the full solution would be mo…
All it would take is for one person to catch the model doing this and the reputation of the model and the company would be destroyed irrevocably.
Many Chinese models are being caught doing this (it's also required by law in China) but there was not much hassle.
Having said that Id easily trade some censorship about Chinese affairs I don't care about for the prudishness of American models. Though I generally get the abliterated versions of both.
Re: Show HN: Apfel – The free AI already on your Mac
#174[flagged]
Re: Show HN: Apfel – The free AI already on your Mac
#175I like the approach of running everything locally. I'm strongly of the opinion that the privacy angle for local models is going to keep getting stronger and more relevant. The amount of articles that come out about accidents happening because of people handing too much context to cloud models the more self reinforcing this will become.
It's only half of the solution though. If the models are trained in a closed way, they can prioritize values encoded during training even if that's not what you want (example: ask the open Chinese models about Tiananmen). It's not beyond imagining that these models would e.g. try to send your data to authorities or advertisers when their training says so, even if you run them locally. So the full solution would be mo…
The Tiananmen test only hits the model's internal knowledge.
What I'm more interested in is that if you give it a tool to access Wikipedia, will it censor its answer even then?
Re: Show HN: Apfel – The free AI already on your Mac
#176Earlier quoted context omitted.
Apparently the Overcast guy build a beowulf cluster of Mac minis to use the Apple transcription service. https://www.linkedin.com/posts/nathangathright_marco-arment-...
The ATP episode where he talked about this was incredibly fascinating. Marco is such a role model to me - he has a complete immunity to fads and trends, and just does things the way he wants to. He adopts the 'new and cool' things only when they have a real benefit.
ATP, also known as “Accidental Tech Podcast”.
Re: Show HN: Apfel – The free AI already on your Mac
#177Started using this earlier this week. I built a backtesting benchmark tool to compare a mix of frontier and open-source models on a fairly heavy data analysis workflow I’d been running in the cloud. The task is basically predicting pricing and costs. Apple’s model came out on top—best accuracy in 6 out of 10 cases in the backtest. That surprised me. It also looks like it might be fast enough to take over the whole jo…
I'm interested to hear what ends up happening. Going from thousands (is that dollars?) per month to something local is significant and I'm not sure the m4 can really make up the gap. Cloud can scale speed whereas you're limited to one computer.
If it works, can it compete in speed, performance AND accuracy? If it can, that would be a real game changer for local analytics when the entire dataset can be loaded onto a single computer.
Re: Show HN: Apfel – The free AI already on your Mac
#178What is going on in Vienna? First OpenClaw, now this tool. I see a lot of AI (Austrian Intelligence) recently.
Re: Show HN: Apfel – The free AI already on your Mac
#179Earlier quoted context omitted.
Yeah I don’t think the models are meaningfully differentiated outside of very specific edge cases. I suspect this was the thinking behind OpenAI and Facebook and all trying to lean hard into presenting their chatbots as friends and romantic partners. If they can’t maintain a technical moat they can try to cultivate an emotional one.
> very specific edge cases Mathematics is hardly an edge case, but SOTA models differ wildly in their ability to write proofs for unsolved problems. Models also differ wildly in tasks like decompilation for reverse engineering. Also, so far, the only model I've found which can competently write PTX for SM100 CUDA devices is GPT-5.4pro, but I'm willing to admit that this is more of an edge case than the aforementioned…
I mean, if the work is novel it’s almost definitionally an edge case is it not?
Re: Show HN: Apfel – The free AI already on your Mac
#180I like the approach of running everything locally. I'm strongly of the opinion that the privacy angle for local models is going to keep getting stronger and more relevant. The amount of articles that come out about accidents happening because of people handing too much context to cloud models the more self reinforcing this will become.
local is best for privacy, but i personally think you don't need to go local. anthropic, google, openai etc, decided that their consumer ai plans would not be private. partly to collect training data, the other half to employ moderators to review user activity for safety. we trust that human moderators will not review and flag our icloud docs, onedrive or gmail, or aggregate such documents into training data for llms…
[flagged]