Hacker News: samweb3

New comment by samweb3 in "I made this to save my bookmarks to review later in an inbox-like view"

samweb3 — Wed, 21 Jan 2026 01:55:54 +0000

I made this https://cachetag.com to save my links, images, youtube videos, and PDFs for later viewing. I know there are many bookmark apps, but I wanted one that treated the bookmarks like a searchable inbox where I could mark read / unread. I still have the standard tiles display of course. Additionally, I wanted to be able to add shortcuts to important or frequently visited links and be able to quickly add links via a Chrome Plugin (which for now is self-installed). All links can be downloaded / backed up at anytime so you don't have to worry about the site losing your data. If you try it out, those advanced items are available in Settings. Any questions / feedback / feature suggestions welcome!

I made this to save my bookmarks to review later in an inbox-like view

samweb3 — Wed, 21 Jan 2026 01:55:54 +0000

Article URL: https://cachetag.com

Comments URL: https://news.ycombinator.com/item?id=46700256

Points: 3

# Comments: 1

New comment by samweb3 in "Show HN: I made a memory game to teach you to play piano by ear"

samweb3 — Fri, 09 Jan 2026 20:39:41 +0000

This is absolutely amazing! What a fantastic way to engage kids in particular. Big fan and will be telling anyone I can about it.

New comment by samweb3 in "Life After Work"

samweb3 — Thu, 30 Oct 2025 17:49:17 +0000

Is it telling that I used chatgpt to summarize this as 5 bullets for me?

Automation will collapse wages but raise living standards: As AI and robotics replace all labor, human wages will fall—but productivity and wealth will soar, leading to better health, abundance, and comfort.

Historical parallel—child labor’s decline: Just as industrial automation freed children from farm work and shifted society toward education, future automation will free adults from economic necessity, redefining “work.”

AI as the new labor force: Trillions of digital workers could multiply global GDP many times over, making each human comparably wealthy—like Qatari citizens supported by a huge migrant workforce.

Redistribution will likely spread prosperity: Past trends and political realities suggest wealth from full automation will be broadly, though unequally, shared through asset ownership and social programs.

Post-scarcity future: Humanity may enjoy radical technologies—mind uploading, fusion power, genome control, and disease reversal—ushering in an era of leisure, health, and creativity beyond today’s imagination.

New comment by samweb3 in "Demand for human radiologists is at an all-time high"

samweb3 — Thu, 25 Sep 2025 16:55:08 +0000

It's interesting to see people fighting so hard to preserve these jobs. Do people want to work that badly? If a magic wand can do everything radiologists can do, would we embrace it or invent reasons to occupy 40+ hours a week of time anyway? If a magic wand, might be on the horizon, shouldn't we all be fighting to find it and even finding ways to tweak our behaviors to maximize the amount of free time that could be generated?

New comment by samweb3 in "Ask HN: My friend says he has an AI optimized language"

samweb3 — Wed, 03 Sep 2025 17:59:54 +0000

Yes, helping to build it really through experimentation and looking for use cases that make sense. Thanks for the comment!

Ask HN: My friend says he has an AI optimized language

samweb3 — Wed, 03 Sep 2025 16:32:53 +0000

A friend built https://memelang.net/08/ which claims "Memelang is an AI-optimized query language that significantly reduces token count and model size for LLM RAG. Copy-and-paste the Python spec below into your LLM."

Is it possible that this language would make AI agents better at retrieving data either in terms of cost or accuracy? For example, might an AI Agent calling tools be more efficient than just using standard SQL or similar? How would you design a test or set of tests to figure out the benefits?

I would like to help him prove the cost or accuracy benefits. Thank you for any advice!

Comments URL: https://news.ycombinator.com/item?id=45117733

Points: 1

# Comments: 2

New comment by samweb3 in "LLM Memory"

samweb3 — Tue, 01 Jul 2025 11:59:22 +0000

Check out memelang.net which aims to solve much of these issues.

New comment by samweb3 in "Memelang spec for structuring information"

samweb3 — Tue, 03 Jun 2025 15:08:41 +0000

We created Memelang to help us structure and query data more effectively from LLMs. We're looking for feedback on additional practical applications or limitations based on unique use cases.

Memelang spec for structuring information

samweb3 — Tue, 03 Jun 2025 15:08:41 +0000

Article URL: https://memelang.net/07/

Comments URL: https://news.ycombinator.com/item?id=44170902

Points: 3

# Comments: 1

New comment by samweb3 in "I am rich and have no idea what to do"

samweb3 — Sat, 04 Jan 2025 00:20:22 +0000

One idea. Just a thought. You could find ways to help OTHER people succeed?

New comment by samweb3 in "AlphaProof's Greatest Hits"

samweb3 — Mon, 18 Nov 2024 02:03:08 +0000

I am building Memelang (memelang.net) to help with this as well. I'd love your thoughts if you have a moment!

Show HN: I made a demo of my Prolog-successor. Try it please

samweb3 — Fri, 15 Nov 2024 23:53:18 +0000

Article URL: http://demo.memelang.net

Comments URL: https://news.ycombinator.com/item?id=42152714

Points: 4

# Comments: 1

New comment by samweb3 in "I'm not mutable, I'm partially instantiated"

samweb3 — Thu, 07 Nov 2024 21:41:03 +0000

That's the goal, but please let me know if there's anything you find that you can't do.

New comment by samweb3 in "I'm not mutable, I'm partially instantiated"

samweb3 — Thu, 07 Nov 2024 14:45:36 +0000

I am actually working on a logical query language that's a successor to prolog here: https://memelang.net/02/. Any feedback appreciated!

New comment by samweb3 in "Writes and Write-Nots"

samweb3 — Sun, 27 Oct 2024 23:21:14 +0000

Is the ability to convince or prove a thesis more importan than the thesis itself?

New comment by samweb3 in "LLMs don't do formal reasoning"

samweb3 — Sun, 13 Oct 2024 14:34:45 +0000

But...when I test the example, I get the right answer from 4o. Seems like they can just extend the model to identify irrelevant information over time and get the correct results more generally for similar models. -------------------------------- Let's break it down:

Friday: Oliver picks 44 kiwis. Saturday: Oliver picks 58 kiwis. Sunday: He picks double the amount he picked on Friday: 44x2=88 44×2=88 kiwis. Now, we sum all the kiwis: 44+58+88=190 Since the size of five kiwis on Sunday doesn’t affect the total count, Oliver still has: 190 kiwis.

New comment by samweb3 in "Google Is Running Out of Cloud Storage"

samweb3 — Sun, 15 Sep 2024 02:32:07 +0000

What does this foreshadow for web payments and services?

Google Is Running Out of Cloud Storage

samweb3 — Sun, 15 Sep 2024 02:32:07 +0000

Article URL: https://cachetag.com/marcus/item/google-is-running-out-of?v=7CrzEB4BbMERSZ1joUMYYG

Comments URL: https://news.ycombinator.com/item?id=41544756

Points: 3

# Comments: 1

New comment by samweb3 in "Human Shader"

samweb3 — Fri, 21 Jul 2023 02:02:21 +0000

So this is just a way to get tons of handwriting samples and computation data right?