Hacker News: sipjca

New comment by sipjca in "Reimagining the mouse pointer for the AI era"

sipjca — Wed, 13 May 2026 00:40:28 +0000

thats incredible

New comment by sipjca in "Show HN: Gemma 4 Multimodal Fine-Tuner for Apple Silicon"

sipjca — Wed, 08 Apr 2026 09:57:08 +0000

Wondering similar. It certainly can run beyond 30 seconds but at some point I believe the output should degrade

Plus you could do actual batch inference instead. Or if you must carry forward the context you could still do it linearly, but the mem usage shouldn’t just explode

New comment by sipjca in "Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS"

sipjca — Tue, 07 Apr 2026 08:23:55 +0000

Thank you!!

New comment by sipjca in "Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS"

sipjca — Tue, 07 Apr 2026 06:15:50 +0000

I just don't have the bandwidth to run another project, maintaining Handy is hard enough on it's own, especially for free!

I didn't just dismiss for no reason, I am a human! I have needs and I can't just sleeplessly stay in front of the computer putting out code. If I had more time I would, but alas.

Someone could easily vibe code an iOS version in a few hours. I could do the same but I do not have time to support it.

New comment by sipjca in "Apple discontinues the Mac Pro"

sipjca — Fri, 27 Mar 2026 07:35:44 +0000

Of course they are! Both are important and will be around and used for different reasons

New comment by sipjca in "Apple discontinues the Mac Pro"

sipjca — Fri, 27 Mar 2026 03:47:50 +0000

I don’t think it’s about literally shrinking the models via quantization, but rather training smaller/more efficient models from scratch

Smaller models have gotten much more powerful the last 2 years. Qwen 3.5 is one example of this. The cost/compute requirements of running the same level intelligence is going down

New comment by sipjca in "“This is not the computer for you”"

sipjca — Fri, 13 Mar 2026 09:41:42 +0000

This is an argument, but it’s also fundamentally comparing a computer that works out of the box to one that doesn’t.

New comment by sipjca in "MacBook Neo"

sipjca — Fri, 06 Mar 2026 00:16:13 +0000

That wasn’t the point. You’re a person who runs arch, that means most likely your requirements for a computer are VERY different than the target for this Mac. There’s always some other computer you can buy, but most people will just buy the Mac

New comment by sipjca in "MacBook Neo"

sipjca — Thu, 05 Mar 2026 02:43:23 +0000

Yes

New comment by sipjca in "MacBook Neo"

sipjca — Thu, 05 Mar 2026 02:32:30 +0000

You literally just compared a laptop running arch to a mac. You’re not the target audience lmao

New comment by sipjca in "Lenovo’s new ThinkPads score 10/10 for repairability"

sipjca — Wed, 04 Mar 2026 03:21:10 +0000

Picked up a T14s in Shenzhen for ~$250 US and it’s a screamer. Best thing for sure

New comment by sipjca in "OpenAI raises $110B on $730B pre-money valuation"

sipjca — Fri, 27 Feb 2026 23:20:01 +0000

who was bought by openai

New comment by sipjca in "Show HN: Free alternative to Wispr Flow, Superwhisper, and Monologue"

sipjca — Tue, 17 Feb 2026 05:37:36 +0000

Great feedback :) also support for the v2 versions of the moonshine models should be out today!

New comment by sipjca in "Show HN: Free alternative to Wispr Flow, Superwhisper, and Monologue"

sipjca — Tue, 17 Feb 2026 02:53:02 +0000

There's an open PR in the repo which will be merged which adds this support. Post processing is an optional feature if you want to use it, and when using it, end to end latency can still be under 3 seconds easily

New comment by sipjca in "Rust implementation of Mistral's Voxtral Mini 4B Realtime runs in your browser"

sipjca — Tue, 10 Feb 2026 23:43:16 +0000

Not currently

New comment by sipjca in "Rust implementation of Mistral's Voxtral Mini 4B Realtime runs in your browser"

sipjca — Tue, 10 Feb 2026 10:23:35 +0000

okay... so I cannot get this to run on my mac. maybe something with the burn kernels for quantized?

will report a GitHub issue

New comment by sipjca in "Rust implementation of Mistral's Voxtral Mini 4B Realtime runs in your browser"

sipjca — Tue, 10 Feb 2026 09:00:29 +0000

I'm looking into porting this into transcribe-rs so handy can use it.

The first cut will probably not be a streaming implementation

New comment by sipjca in "Rust implementation of Mistral's Voxtral Mini 4B Realtime runs in your browser"

sipjca — Tue, 10 Feb 2026 09:00:03 +0000

thanks for your contribution :)

New comment by sipjca in "Discord will require a face scan or ID for full access next month"

sipjca — Tue, 10 Feb 2026 00:48:56 +0000

this is hilarious, person who barely uses service says he will leave the service, what a concept

New comment by sipjca in "Handy – Free open source speech-to-text app"

sipjca — Fri, 16 Jan 2026 00:36:32 +0000

I believe sensevoice, I’ll hopefully be implementing it soon enough