Hacker News: wrs

New comment by wrs in "Reverse centaurs are the answer to the AI paradox"

wrs — Sat, 11 Jul 2026 19:52:27 +0000

People say this about everyone who calls something a bubble, right up until it pops.

New comment by wrs in "Reverse centaurs are the answer to the AI paradox"

wrs — Sat, 11 Jul 2026 19:49:11 +0000

That is what he said.

>When the AI bubble bursts, there will be stellar bargains on GPUs…

>these standalone models can do amazing things

>The things these open source standalone models can do will only expand, and they will become a given for our computing applications.

I think of the “big” foundation models as the “fossil fuel” of AI. Once the bubble pops and we can’t afford to train any more of them, we’ll be distilling and remixing the ones we managed to make during this weird period where they were feasible.

New comment by wrs in "Why it's so difficult to produce American-made medical gloves"

wrs — Sat, 11 Jul 2026 16:12:47 +0000

Also, the stakeholders decided the epidemic was a hoax in the first place.

New comment by wrs in "Write code like a human will maintain it"

wrs — Fri, 10 Jul 2026 16:00:40 +0000

Claude Code and Opus 4.8 love to describe changes in comments (perhaps because that’s what’s on its “mind” at the time), like “this used to do A but that did a bad thing so now it does B”. I’ve almost convinced it that changes go in the commit message, not the comments.

New comment by wrs in "GPT-5.6"

wrs — Thu, 09 Jul 2026 21:35:55 +0000

> could "break" a lot of things for developers who didn't know to make prompt changes after upgrading to 5.6.

How does this differ from the other changes in behavior in 5.6 that will also break things? New models always break things.

New comment by wrs in "Postgres rewritten in Rust, now passing 100% of the Postgres regression tests"

wrs — Thu, 09 Jul 2026 21:17:45 +0000

Some of this post reminds me of a story I heard long ago from someone who had worked at a HW/SW company. They’d transferred an engineer from the ASIC design team to the OS kernel team, though he’d never been on a software team before. After a while the manager called him in for the following conversation:

Manager: You’re doing amazing work — zero bugs in production! I’d like you to mentor the other SWEs on how to get their bug count down too.

Engineer: We’re allowed to have bugs?

New comment by wrs in "How to Follow a Drummer"

wrs — Thu, 09 Jul 2026 21:00:23 +0000

I’m curious if you compared this against Ableton’s “Tempo Follower” and had any algorithmic (or subjective) observations.

New comment by wrs in "Buried Apple feature turns an iPhone into the perfect kids' dumb phone"

wrs — Thu, 09 Jul 2026 18:48:38 +0000

When my friend's kids were totally obsessed with League of Legends, I offered to set up a home firewall with increasingly difficult workarounds, so by the time they graduated high school they'd at least have a cybersecurity certificate and possibly a Ph.D in networking.

New comment by wrs in "Suspecting AI cheating, Ivy League prof ordered in-person final; scores fell 50%"

wrs — Thu, 09 Jul 2026 00:28:59 +0000

What's even worse than so many students cheating with AI is that I suspect a substantial portion of them don't even think that's "cheating".

New comment by wrs in "Fable turned reMarkable into Tom Riddle's diary from Harry Potter"

wrs — Tue, 07 Jul 2026 00:17:49 +0000

I really don't think this project was meant to be taken seriously.

New comment by wrs in "Full Writeup of the Windows GDID"

wrs — Mon, 06 Jul 2026 22:50:27 +0000

No relation. GUID is just a format for a 128-bit unique number, used throughout the software industry. This is a specific 64-bit number assigned to your Windows device.

New comment by wrs in "Leaking YouTube creators' private videos"

wrs — Sun, 05 Jul 2026 17:02:03 +0000

I suspect when those 10-digit wire transfers start arriving in your bank account, your attitude changes rapidly.

New comment by wrs in "Leaking YouTube creators' private videos"

wrs — Sat, 04 Jul 2026 17:15:06 +0000

>Comments should be passed to the model with clear role boundaries that prevent them from being interpreted as system-level directives.

Well, such clear boundaries would solve lots of problems. But those don’t exist, do they?

New comment by wrs in "New serious vulnerabilities spiked around release of Claude Mythos Preview"

wrs — Sat, 04 Jul 2026 06:21:27 +0000

I thought the point was not that Mythos finds more vulnerabilities, but that it can exploit them much more successfully. I thought the report showed it didn’t find much more than Opus 4.8. (Or did I misread?)

New comment by wrs in "Memorizing session transcripts isn't useful"

wrs — Fri, 03 Jul 2026 19:36:02 +0000

My current technique, which seems to have improved maintainability, is to guide Claude to write commit messages specifically focused on "why this was done", "what changed in the theory of operation", and "what changed in the code". Then just reviewing the commits for a file or dir gives it a ton of useful context distilled from the sessions that produced them. Also, making a docs dir with concise .md files explaining the theory of operation and updating them with every commit.

New comment by wrs in "I Wasn't Allowed Prompting ChatGPT During My Chalk Talk: This Is Discrimination (2025)"

wrs — Fri, 03 Jul 2026 18:55:55 +0000

Replace science with software development and this just reads like half of HN right now.

New comment by wrs in "Show HN: ctx – Search the coding agent history already on your machine"

wrs — Fri, 03 Jul 2026 00:30:04 +0000

I often tell Claude Code to look at previous sessions in ~/.claude and it’s happy to jq/grep its way through them with no special tool. But being more efficient is always good.

New comment by wrs in "No LLM Code in Dependencies"

wrs — Thu, 02 Jul 2026 19:41:33 +0000

Apparently, though not very carefully. The "particularly large LLM generated code churn" in the ram library, for example, is the LLM being used to simply git-revert a change that was not originally done by an LLM.

New comment by wrs in "Is One Layer Enough? A Single Transformer Layer Matches Full-Parameter RL Train"

wrs — Thu, 02 Jul 2026 16:32:03 +0000

The manifold is in the middle (“small input space is expanded onto a big manifold and contracted again”) so f(manifold) would need to be in the middle too.

New comment by wrs in "Since Linux 6.9, LUKS suspend stopped wiping disk-encryption keys from memory"

wrs — Thu, 02 Jul 2026 16:23:38 +0000

Obviously your distro isn’t using cryptsetup-luksSuspend.