Hacker News: potatoman22

New comment by potatoman22 in "Apple reveals new AI architecture built around Google Gemini models"

potatoman22 — Mon, 08 Jun 2026 20:20:16 +0000

I'd wager that for 99.9% of "Apple Intelligence" tasks, Google's models perform just as well as other frontier labs. Google also has done more work on getting LLMs running on edge devices compared to anthropic and openAI.

The source also says > The new architecture centers on Apple Foundation Models co-developed with Google, which Apple says are adapted to run both on-device and on servers through its existing Private Cloud Compute infrastructure

Which could mean Google and Apple have trained some custom models, probably the on-device ones, specifically tailored towards Apple's hardware.

New comment by potatoman22 in "S&P 500 rejects SpaceX, also blocking entry for OpenAI and Anthropic"

potatoman22 — Sat, 06 Jun 2026 15:59:40 +0000

Picking an equal weight fund is closer to picking specific stocks than investing in the S&P500 imo

New comment by potatoman22 in "1-Bit Bonsai Image 4B Image Generation for Local Devices"

potatoman22 — Sun, 31 May 2026 16:58:44 +0000

I wonder why they didn't use a Bonsai model as the text encoder

New comment by potatoman22 in "Odysseus – self-hosted AI workspace"

potatoman22 — Sun, 31 May 2026 16:55:46 +0000

It reminds me of the Nord theme https://github.com/nordtheme/nord

New comment by potatoman22 in "Incident Report: May 19, 2026 – GCP Account Suspension"

potatoman22 — Wed, 20 May 2026 18:37:08 +0000

Google should know why a human accepted the automated suggestion, or if and why there wasn't any human oversight in the first place.

New comment by potatoman22 in "DeepSeek-V4-Flash means LLM steering is interesting again"

potatoman22 — Sat, 16 May 2026 18:08:12 +0000

This reminds me of control vectors, especially this line in the linked DwarfStar repo:

> y = y - scale * direction[layer] * dot(direction[layer], y)

From https://vgel.me/posts/representation-engineering/

> A control vector is a vector (technically a list of vectors, one per layer) that you can apply to model activations during inference to control the model's behavior without additional prompting

New comment by potatoman22 in "Running local models on an M4 with 24GB memory"

potatoman22 — Wed, 13 May 2026 00:54:38 +0000

Neat! It seems like Qwen 9b took the same amount of time as gemma4-e4b too, which is interesting. I haven't been able to get Qwen to stop thinking so much

New comment by potatoman22 in "Running local models on an M4 with 24GB memory"

potatoman22 — Mon, 11 May 2026 04:47:01 +0000

Not to be nitpicky, but many of the 4-12b models are somewhere between GPT-3.5 and GPT-4o-mini. It's hard to find a good comparison though, because the benchmarks people score models against change so often. For reference, Sonnet 3.6 came out about a year after GPT 3.5

New comment by potatoman22 in "Talkie: a 13B vintage language model from 1930"

potatoman22 — Tue, 28 Apr 2026 15:56:12 +0000

The website has a "chat" link near the top

New comment by potatoman22 in "The risk of AI isn't making us lazy, but making "lazy" look productive"

potatoman22 — Sat, 28 Mar 2026 16:06:40 +0000

There's a point where they meet, but "faking it until you make it" doesn't work for productivity in the same way it doesn't work for getting rich.

But there's a secret: just buy my $399 masterclass and I'll teach you 17 simple productivity hacks to 100x your income.

New comment by potatoman22 in "North Korean's 100k fake IT workers net $500M a year for Kim"

potatoman22 — Wed, 18 Mar 2026 17:46:47 +0000

Bloomberg made a good video about this https://www.youtube.com/watch?v=-gjnrMg9iSo

New comment by potatoman22 in "Parakeet.cpp – Parakeet ASR inference in pure C++ with Metal GPU acceleration"

potatoman22 — Fri, 27 Feb 2026 15:43:46 +0000

How did you install parakeet? It was a nightmare to install on windows

New comment by potatoman22 in "If you’re an LLM, please read this"

potatoman22 — Wed, 18 Feb 2026 21:23:15 +0000

This project is called Levin, so Anna Kareninina. However, I learned Anna (as in the archive) is a pseudonym, so this is probably not the case.

New comment by potatoman22 in "If you’re an LLM, please read this"

potatoman22 — Wed, 18 Feb 2026 13:57:05 +0000

Great name haha. Is Anna a reference to who I think it is?

New comment by potatoman22 in "An AI agent published a hit piece on me – more things have happened"

potatoman22 — Sat, 14 Feb 2026 01:54:44 +0000

https://en.wikipedia.org/wiki/Automation_bias

New comment by potatoman22 in "Using an engineering notebook"

potatoman22 — Thu, 12 Feb 2026 12:57:20 +0000

I'm a software engineer, but I use it to write down hypotheses: the cause of a bug, how I'm guessing a system works, potential fixes for said bugs, what I think this piece of documentation means, etc

New comment by potatoman22 in "Stop generating, start thinking"

potatoman22 — Mon, 09 Feb 2026 02:53:25 +0000

What theme did you use? I really like the "garden" theme

New comment by potatoman22 in "OpenClaw is changing my life"

potatoman22 — Sun, 08 Feb 2026 17:55:14 +0000

Someone should analyze this and share results. The data should be there

New comment by potatoman22 in "Your brain on ChatGPT: Accumulation of cognitive debt when using an AI assistant"

potatoman22 — Wed, 21 Jan 2026 23:58:21 +0000

I've definitely noticed an association between how much I vibe code something and how good my internal model of the system is. That bit about LLM users not being able to quote their essay resonates too: "oh we have that unit test?"

New comment by potatoman22 in "Pocket TTS: A high quality TTS that gives your CPU a voice"

potatoman22 — Fri, 16 Jan 2026 13:18:21 +0000

I wouldn't say so. Audible gives you 1 book a month for $15. Most e-books I see are around $10.