Hacker News: bryzaguy

New comment by bryzaguy in "Improper redaction reveals Google Data Center water and electricity usage"

bryzaguy — Sun, 04 Oct 2026 21:22:31 +0000

> Agate LLC reports expecting a refund of $55,822,472 from 2025 taxes. Fireball LLC is expecting a refund of $39,171,573.39 from 2025 taxes. Westwood Solutions LLC, the Google-owned data center in Omaha, is expecting a refund of $22,558,881 from 2025 taxes.

Wow!

New comment by bryzaguy in "Improper redaction reveals Google Data Center water and electricity usage"

bryzaguy — Sun, 04 Oct 2026 21:17:56 +0000

This feels like an important point! People comparing to leaks (or other distributed examples that aggregate similarly) are not thinking about how the amount of water used in a single location changes the scale.

New comment by bryzaguy in "I stopped reviewing my agents' code. Here's what I do instead"

bryzaguy — Sun, 04 Oct 2026 07:45:13 +0000

I truly empathize with this idea. It does feel like things are improving. I was scanning the code generated and felt the same way. Like, woah, maybe I'm in the clear and I can hand the reigns over. Do I even need to look at the code anymore?

Then I ran into a few bugs and, as I dug in, what initially looked like reasonable code suddenly seemed strange when looking closer. After some help from the agent to understand the intent, it became clear the design was poor, explained a few failures, and resulted in an order of magnitude more (reasonable looking) code to compensate which now I have to sift through.

To make matters worse, I could not get the agent to divorce itself from its wrong decisions, even with my explicit instruction detailing how the code should read. It would keep rewriting the same bad ideas then go into other distracting tangents which I'd have to correct. It felt just like how conversations in ChatGPT that would get stuck once it was in the context making me imagine we're still driving the same car but with a new paint job.

I finally wrote the code myself. It was more helpful after that. Hopefully, I'm able to resist the temptation and stay vigilant in my reviews. For context, I am using Codex Astra XHigh but maybe Opus 5.5 really is better?

New comment by bryzaguy in "10-year Treasury yield climbs above 5.3% to a level not seen in 24 years"

bryzaguy — Thu, 01 Oct 2026 02:33:46 +0000

Since Bill Clinton and Lyndon B Johnson were the only two presidents to see a balanced budget I can guess which party you mean.

New comment by bryzaguy in "S3 Is the Future, S3 Is the Past"

bryzaguy — Mon, 28 Sep 2026 02:50:54 +0000

S3 is dead, long live S3

New comment by bryzaguy in "iOS 27, iPadOS 27, and macOS 27"

bryzaguy — Tue, 15 Sep 2026 15:01:14 +0000

This feels like the kind of thing where the mismatching version numbers bugged some influential people internally. But I suppose a practical application could be recommending matching versions if customers run into issues since they are trying to integrate devices more.

New comment by bryzaguy in "When LLM judges agree, should we believe them?"

bryzaguy — Mon, 14 Sep 2026 18:07:26 +0000

They would all agree raspberry has two Rs

New comment by bryzaguy in "How AI text watermarking works"

bryzaguy — Fri, 14 Aug 2026 01:08:05 +0000

My guess would be to detect if their models are being distilled by other models.

New comment by bryzaguy in "AI is removing the middle class of software engineering?"

bryzaguy — Wed, 12 Aug 2026 14:50:16 +0000

What if the new entry level is what we consider senior today? Isn't it possible today to obtain entry/mid level skills with LLMs? I wonder if things will shift more in that direction.

New comment by bryzaguy in "Music Generation by a Composer, for Musicians"

bryzaguy — Wed, 12 Aug 2026 13:47:56 +0000

I'm a musician and I am not seeing why I would want this. If this is trying to help musicians that don't know theory, it should start from simple chords and expand those in different ways that demonstrate an improvement. Currently the examples are pretty simple and don't sound good to my ear.

New comment by bryzaguy in "Music Generation by a Composer, for Musicians"

bryzaguy — Wed, 12 Aug 2026 13:31:12 +0000

Below the tone wheel should be a "Synthesize Stems" button which generates a list of midi examples, each with an "Audition" button that plays the midi.

New comment by bryzaguy in "How I use LLMs to learn complex topics"

bryzaguy — Mon, 10 Aug 2026 15:59:29 +0000

Not sure how relevant my example will be but I built a spaced repetition language learning LLM wrapper app to learn Japanese and it worked really well. I went to great lengths, however, to craft prompts which resulted in more predictable and useful results. ChatGPT on its own couldn’t do this.

New comment by bryzaguy in "How I use LLMs to learn complex topics"

bryzaguy — Mon, 10 Aug 2026 15:50:26 +0000

Spaced repetition could address this, no? Also, the right example or metaphor can make a difficult concept both easier to understand and stickier in my mind which I think is different than something easy to learn.

New comment by bryzaguy in "Show HN: Wyzer Programming Language"

bryzaguy — Fri, 07 Aug 2026 16:55:23 +0000

This looks cool! Memory safety beyond Rust with simpler code is a strong claim. Something I'd love to see is examples that mimic issues Rust borrow checker would catch as well as ones only wyzer would catch.

New comment by bryzaguy in "Design is compromise"

bryzaguy — Thu, 30 Jul 2026 13:41:00 +0000

Design is an art and, as Rick Ruben says, success is not in your control. Also Rick says the audience comes last. You can find examples of strong choices that did not succeed but in your example it doesn’t sound like these mouse makers were designing for themselves first.

New comment by bryzaguy in "Design is compromise"

bryzaguy — Sun, 26 Jul 2026 20:38:27 +0000

I fundamentally disagree with the premise. Why are we attempting to change the meaning of the word compromise? “compromise” and “has trade-offs” are NOT synonymous. The antithesis of compromise is to make strong decisions that WILL alienate people, but will better target your intended audience. That, IMHO, is a great thing.

New comment by bryzaguy in "Jaron Lanier: there is no AI (2023)"

bryzaguy — Mon, 20 Jul 2026 16:56:04 +0000

> The closest we have come to a definition of privacy is probably “the right to be left alone,” but that seems quaint in an age when we are constantly dependent on digital services. In the context of A.I., “the right to not be manipulated by computation” seems almost correct

Maybe someone can enlighten me but I really don't understand how either of these description make any sense at all. How is it not better described as "the right to decide what data can be extracted"?

New comment by bryzaguy in "Claude Code May–July 2026 weekly limits promotion"

bryzaguy — Sun, 12 Jul 2026 18:27:48 +0000

Maybe that's on me for missing it. Either way, the improvement is not enough for me to justify the extra cost.

New comment by bryzaguy in "Claude Code May–July 2026 weekly limits promotion"

bryzaguy — Sun, 12 Jul 2026 18:21:44 +0000

I was hoping to switch to Claude but was waiting until they had a better model than Codex 5.5. When Fable came out I immediately bought the $100 plan. When the government shut it down they gave the option to cancel which I appreciated. I planned to subscribe again once it was back. However, removing it from the subscription once back has really soured me. I can't help feeling like it was a bait and switch. Even if they added it back, I'm not sure I trust it will stay. I now have no plans to switch back from Codex.

New comment by bryzaguy in "Ask HN: What are you working on? (June 2026)"

bryzaguy — Sun, 14 Jun 2026 18:40:01 +0000

This is awesome