Hacker News: herf

New comment by herf in "Run Kimi K3 using 29 GB of RAM at 0.50 tok/s"

herf — Fri, 31 Jul 2026 18:40:26 +0000

So if this Mac uses 30-50W, that's 40-60 tok/Wh...vs maybe 80k for a modern GPU cluster? So that's about 1000-2000x more power for the SSD streaming, unfortunately.

New comment by herf in "How JPEG works: Interactively explore JPEG's lossy compression methods"

herf — Fri, 31 Jul 2026 18:27:03 +0000

Nicely illustrated, and only one criticism: our preference for luminance (using more bits for "Y" vs "Cr/Cb") isn't due to the number of rods in the eye - there are so many rods so that we can capture more photons at night, and they are usually saturated at daylight illuminances. The effectiveness of the YCbCr encoding is much more related to the predominant pathway to the LGN (80-90% of the "number of bits" used) encoding luminance and center-surround, so those things both map well to using more bits for "Y".

New comment by herf in "Passkeys were invented by engineers with zero understanding of consumer brain"

herf — Wed, 22 Jul 2026 15:37:03 +0000

I think portability is very confusing: they rolled out passkeys with no device portability (device-bound) and only recently added it (CXP). So for anyone with multiple devices it was a relative disaster - why should my Windows PC hold a device-bound passkey to anything? How do I login on Linux or macOS? Picking a password manager to do portability also means another kind of lockin, though maybe you can live with that kind if you really trust the company. Even so, the password managers all seem to be competing to have relaxed security, so that vault and account passwords are the same, or you are asked to type your master password into a webpage - surely we didn't replace per-site passwords with this?

New comment by herf in "Apple to skip high-end M6 Mac chips in favor of AI-focused M7 line"

herf — Fri, 26 Jun 2026 02:43:45 +0000

You can turn off the notch, I mean crop it out at least.

New comment by herf in "Windows 11 New Media Player Uses 3.5x More RAM, Charges for Popular Video Codecs"

herf — Sat, 20 Jun 2026 15:47:33 +0000

HEVC used to be a capped license per organization, so not providing it in the OS seems really harmful and expensive. Has the cap changed recently?

New comment by herf in "Want your images back? That'll be $5"

herf — Wed, 17 Jun 2026 15:28:26 +0000

Yes, I think part of it was the "dark fiber" at the time, made bandwidth relatively cheap. But most personal photos don't use that much bandwidth - being able to use them anywhere online (which iCloud and Instagram don't allow) was a big idea. We went from "my content hosted in the cloud" to "Instagram's content" in a lot of ways. That is only partly a pricing issue.

New comment by herf in "Has AI already killed self-help nonfiction books?"

herf — Wed, 17 Jun 2026 15:11:35 +0000

AIs and podcasts (which also grew a lot recently) are free alternatives, and pricing matters as much as attention.

New comment by herf in "Want your images back? That'll be $5"

herf — Wed, 17 Jun 2026 14:51:31 +0000

This is gross, it could be a onetime fee.

It's hard to remember with all the ownership changes, but the Photobucket era was really a different time, of "it's your data, you're in charge, and we give you maximal control of it" - people would upload there to post elsewhere, and I recall they ran ads to monetize. But this era had the ethic that uploading was expensive, and you'd maybe want to do it once and have control of your stuff after that.

Now we have photo hosting services that barely work on the web (iCloud), or work only within a walled garden (Instagram), and I do miss the "it's your stuff, we're just a website" kind of attitude from the mid-2000s.

New comment by herf in "Should you normalize RGB values by 255 or 256?"

herf — Mon, 01 Jun 2026 21:32:08 +0000

good point - alpha is a notable exception, it is not luminance

New comment by herf in "Should you normalize RGB values by 255 or 256?"

herf — Mon, 01 Jun 2026 19:04:20 +0000

I'll argue for the +0.5 solution. First, I don't like half-sized intervals at the edges, and second, a 255-based representation is typically a SDR (not HDR) image.

RGB values represent luminances against some adapted state, and a "zero" in a daylit scene is not "zero luminance" - it's just about 0.001x as bright as the brightest point - it's millions of photons, way more than zero. In a sense our eyes experience contrast on a sliding scale, and there is no absolute zero in the system. For example, broadcast systems historically used 16-235 as their luminance range for SDR. I think any argument that says "we must have zero" is going to have a bias, but I don't think zero is needed for most things.

New comment by herf in "Meta launches Instagram, Facebook, and WhatsApp subscriptions"

herf — Mon, 01 Jun 2026 05:25:29 +0000

Guess you can't pay to get end-to-end encryption back in Instagram DMs? They dropped it a couple weeks ago.

New comment by herf in "Private Equity Bought America's Essential Services"

herf — Wed, 27 May 2026 13:22:47 +0000

Link to the Musharbash article that spurred the congressional investigation (2025):

https://www.thebignewsletter.com/p/did-a-private-equity-fire...

New comment by herf in "Was my $48K GPU server worth it?"

herf — Thu, 21 May 2026 22:05:53 +0000

Except this math is 10x too high (unless accelerated depreciation is all of it) - a million tokens at 28 tokens/sec and 75W and 20c/kwh should cost $0.15 not $1.50. (And less with MTP.)

New comment by herf in "Indexing a year of video locally on a 2021 MacBook with Gemma4-31B (50GB swap)"

herf — Thu, 21 May 2026 15:53:30 +0000

Two questions:

1. What is the search index?

2. The "description.md" example has things like "faces -> cluster_id". Is this from Davinci Resolve's face index? Things like faces+names and locations are really important with photo collections, but general LLMs don't handle them so well.

New comment by herf in "Googlebook"

herf — Tue, 12 May 2026 22:47:36 +0000

We started taking the phones out of schools, so I guess now we are building them back into education laptops instead?

New comment by herf in "EU to crack down on TikTok, Instagram's 'addictive design' targeting kids"

herf — Tue, 12 May 2026 16:59:48 +0000

Hang on, this is a $2.99 one-time payment - below the level you can even buy ads and make a profit. There is no way he's trying to make billions of dollars this way, and it's honest and smart. Consider the perspective - what happens with the "free alternatives"? You know they're not free: either they already track you, or someone buys them and turns them into spyware. We need more things like this, not less.

New comment by herf in "Screenshots of Old Desktop OSes"

herf — Tue, 12 May 2026 16:45:15 +0000

The aspect ratios were much "taller" back then, which was kind of better for editing code. All these late 90s designs were near NTSC at the time - aspect ratios like 1.25:1 (1280x1024) or 1024x768 (1.33:1). Monitors have always followed TVs, since displays now are the "HD" ratio of 16:9 (1.77:1), or 16:10 if we're lucky. But we do get way more pixels now anyway.

New comment by herf in "Google Chrome silently installs a 4 GB AI model on your device without consent"

herf — Tue, 05 May 2026 18:18:45 +0000

If you back up to "intention" it's fully insane to make a GDPR argument against on-device AI. Yes it downloads bits, but those bits are not there to identify you - they are basically a local copy of the internet. This enables private data to be kept on-device. Having no personal data leave the device is fantastic for GDPR compliance.

The good point in this article is about how the "AI" features in Chrome all use Google's cloud API and not a local model. That's true and some of it should be local. ("AI mode" uses the Web index, so it fundamentally cannot be local, but there are features that could be.)

New comment by herf in "Mozilla's opposition to Chrome's Prompt API"

herf — Thu, 30 Apr 2026 16:35:50 +0000

Chrome seems to use a custom inference runtime also (in addition to Gemini Nano). It would be better if this were all interoperable. The WebGPU alternatives like WebLLM do not have the same access.

I've been trying these models out for the last year, and it seems to me that we want them to work in a 5-10W "laptop" power envelope, but they really work best with a 50-500W GPU instead - i.e. they eat batteries. This means things work better in a "plugged in" gaming laptop/desktop rather than a typical web client. At least for now.

New comment by herf in "Zed 1.0"

herf — Thu, 30 Apr 2026 00:05:26 +0000

Any benchmarks? Scrolling is using 16% of my GPU (vs 5% in Sublime). Also things like mouse-down to activate a tab (vs mouse-up in Zed) make Sublime feel faster.