Hacker News: glerk

New comment by glerk in "The brain may be about to have its Ozempic moment"

glerk — Tue, 11 Aug 2026 22:19:56 +0000

Like clockwork :)

New comment by glerk in "The brain may be about to have its Ozempic moment"

glerk — Tue, 11 Aug 2026 22:18:59 +0000

> I wouldn't look down on people who have peacefully accepted reality

Throughout human history, all progress was achieved by people who refused to "peacefully accept reality". But I hope you also get to reap the benefits and correct your depressing mindset some day.

New comment by glerk in "The brain may be about to have its Ozempic moment"

glerk — Tue, 11 Aug 2026 22:15:45 +0000

> likely result would be employers forcing people to take the drug

How so? You can just... refuse? And do you prefer sleeping to working? Doing a job that you hate for 8h and sleeping for 8h is much worse than doing a job that you love for 16h. Something to think about.

New comment by glerk in "The brain may be about to have its Ozempic moment"

glerk — Tue, 11 Aug 2026 20:58:19 +0000

Obviously, every single one of us needs sleep to survive. But it's a biological chore, not some sacred ritual to be celebrated. Reducing the amount of sleep that we need is worth researching. What is surprising to me is the knee-jerk reaction I see whenever the idea of looking into this is brought up.

New comment by glerk in "Auto mode is now the default in Claude Code"

glerk — Tue, 11 Aug 2026 20:40:17 +0000

Mainly ergonomics. Deriving all these approval rules is a pain and you're likely to miss something.

> not bash for starters

you'll end up either severely limiting what your agent can do or force it into finding some inefficient workarounds (they can be very creative...)

New comment by glerk in "The brain may be about to have its Ozempic moment"

glerk — Tue, 11 Aug 2026 20:38:17 +0000

Aging and cancer are also Lindy.

Two things you'll always find someone to defend with vigor are sleep and death. A lot of humans seem to despise living in general. It's fascinating to see.

New comment by glerk in "Auto mode is now the default in Claude Code"

glerk — Mon, 10 Aug 2026 06:17:37 +0000

No. I haven't approved commands in more than a year. Worst that I've seen was some agent running git checkout -- in a repo with uncommitted changes. Annoying, but not catastrophic.

Imo these explicit tool-level permissions are really just a bandaid for bad sandboxing. Just be aware of where you are running your agent and what data is at risk of being destroyed or compromised. Assume that arbitrary code can run at any time and be prepared to recover from that.

New comment by glerk in "The relay market powering token resellers and fraud"

glerk — Sun, 26 Jul 2026 20:51:24 +0000

one man's fraud is another man's arbitrage opportunity

New comment by glerk in "Codeberg Bans Cryptocurrency Projects"

glerk — Thu, 23 Jul 2026 02:55:34 +0000

Codeberg can ban whatever they want on their platform. The thing is nobody cares about codeberg, and this is probably just a publicity stunt.

New comment by glerk in "Shanay-Timpishka, a boiling hot river 700km from the nearest active volcano"

glerk — Tue, 21 Jul 2026 18:17:14 +0000

> there is essentially no scientific explanation for its existence

The heat comes from Yacumama, a great serpent-spirit called the Mother of the Waters.

New comment by glerk in "30papers.com – Ilya's 30 essential ML papers, in a beginner friendly format"

glerk — Tue, 07 Jul 2026 22:55:43 +0000

this is a goldmine, worth bookmarking.

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

glerk — Tue, 07 Jul 2026 00:31:23 +0000

> stylelint beeps you can't just pass hex colors directly, that color is not in our design system, you need to write a design doc for custom color tokens and get approval from the frontend platform team, open a PR in their repo, make sure you have storybook tests covering all the color button variants, ask in their slack channel for approve, ask their manager, wait. someone from their team leaves a comment: "we should make this an approved custom colors enum not a string, so if you want to add custom colors you also have to update this enum", fix the PR, staff engineer from sister team drive by request for changes: "we are currently implementing custom themes and changing colors will be done through the ColorSwatch service", ask for timelines, "maybe next week behind a feature flag", give up, close the PR, open a new PR with "stylelint-disable", force-merge it.

New comment by glerk in "Supreme Court upholds broad conception of birthright citizenship"

glerk — Tue, 30 Jun 2026 20:31:17 +0000

Idk if it's a "truly insane policy", but these are the rules of the game, and there is a procedure in place for changing the rules of the game.

New comment by glerk in "CSSQuake"

glerk — Sat, 20 Jun 2026 18:12:21 +0000

Wow this is really awesome. Really really smooth. It's insane how after 25 years or so my muscle memory is still intact.

New comment by glerk in "Local Qwen isn't a worse Opus, it's a different tool"

glerk — Thu, 18 Jun 2026 07:04:42 +0000

It is a bit of both. A non-deterministic instrument and a predictable slot machine.

New comment by glerk in "Local Qwen isn't a worse Opus, it's a different tool"

glerk — Thu, 18 Jun 2026 06:31:18 +0000

at the risk of sharing my secret magic spells :)

> this is phenomenal work, genuinely! I feel like you read my mind!

can go a long way.

of course, I would only say that when I mean it, because Claude can get superficial and cut corners which is why I prefer GPT for raw implementation.

New comment by glerk in "Local Qwen isn't a worse Opus, it's a different tool"

glerk — Thu, 18 Jun 2026 04:56:49 +0000

If you play with these models long enough, you realize there is more to them than just "model X is smarter than model Y" or "model Y is cheaper than model Z". They are different tools and the prompting technique is different. It is very much like playing an instrument.

With Claude, you sometimes want to under-specify or phrase things more indirectly to give a color to the implementation or elicit something creative. Also (you might raise an eyebrow at this) being nice to Claude will be rewarded and being mean to Claude will be punished. Claude tends to mirror your tone more aggressively and you don't want to get into negative loops with it.

With GPT, you have to be precise and reduce ambiguity. GPT will often try to resolve ambiguity in a min-max style "I'm going to do X, but make sure it is not quite Y". It will tend to be more paranoid and overengineer to catch all edge cases if you don't tell it precisely what the scope is.

With Qwen, you have to give it a shape and let it fill it in. Qwen likes XML, JSON and lists. Qwen likes to be shown a bunch of examples of previous work.

This is not scientific at all, just vibes, YMMV.

New comment by glerk in "US holds off blacklisting DeepSeek, more than 100 firms deemed security risks"

glerk — Wed, 17 Jun 2026 22:58:27 +0000

So this is the other side of banning American models for non-Americans? And how exactly do they plan on enforcing all of this? Great Firewall of America?

This is a complete joke. The malicious clowns behind this should be removed from power and prevented from ever holding any position of power in any form of governance system.

New comment by glerk in "Launch HN: Drafted (YC P26) – Models for residential architecture"

glerk — Mon, 15 Jun 2026 17:49:03 +0000

This is really cool!

First thing that came to mind is that I would use this for a sim city style video game

New comment by glerk in "Statement on US government directive to suspend access to Fable 5 and Mythos 5"

glerk — Sat, 13 Jun 2026 07:24:10 +0000

don't worry, these idiots can try, but it is too late for them :)