Hacker News: thrwthsnw

New comment by thrwthsnw in "Generative AI runs on gambling addiction – just one more prompt, bro"

thrwthsnw — Fri, 06 Jun 2025 20:42:47 +0000

This is a severely out of touch take.

New comment by thrwthsnw in "A deep dive into self-improving AI and the Darwin-Gödel Machine"

thrwthsnw — Wed, 04 Jun 2025 16:11:33 +0000

What is this? Genetics for ants?

New comment by thrwthsnw in "Claude Code Is My Computer"

thrwthsnw — Tue, 03 Jun 2025 16:32:09 +0000

Try reading a manuscript copy of a book before it’s been edited. Yes I know some people do this out of interest but for most people it’s not the type of writing they are interested in reading or would get the most out of.

New comment by thrwthsnw in "The rise of judgement over technical skill"

thrwthsnw — Mon, 02 Jun 2025 12:35:41 +0000

Just move up an abstraction level and put that flow into planning the features and decomposing them into well defined tasks that can be assigned to agents. Could also write really polished example code to communicate the style and architectural patterns and add full test coverage for it.

I do notice the same lack of flow when using an agent since you have to wait for it to finish but as others have suggested if you set up a few worktrees and have a really good implementation plan you can use that time to get another agent started or review the code of a separate run and that might lend itself to a type of flow where you’re keeping the whole design of the project in your head and rapidly iterating on it.

New comment by thrwthsnw in "Isaac Asimov describes how AI will liberate humans and their creativity (1992)"

thrwthsnw — Thu, 10 Apr 2025 20:09:16 +0000

Why do we give awards to Directors then?

New comment by thrwthsnw in "Claude can now search the web"

thrwthsnw — Fri, 21 Mar 2025 20:22:15 +0000

every token contributes to the output

New comment by thrwthsnw in "With AI you need to think bigger"

thrwthsnw — Mon, 10 Mar 2025 20:03:05 +0000

For category #2 it’s very useful as well and ties in with the theme of the article in that it reduces the activation energy required to almost zero. I’ve been using AI relentlessly to pursue all kinds of ideas that I would otherwise simply write down and file for later. When they involve some technology or theory I know little about I can get to a working demo in less than an hour and once I have that in hand I begin exploring the concepts I’m unfamiliar with by simply asking about them: what is this part of the code doing? Why is this needed? What other options are there? What are some existing projects that do something similar? What is the theory behind this? And then also making modifications or asking for changes or features. It allows for much wider and faster exploration and let’s you build things from scratch instead of reaching for another library so you end up learning how things work at a lower level. The code does get messy but AI is also a great tool for refactoring and debugging, you just have to adjust to the faster pace of development and remember to take more frequent pauses to clean up or rebuild from a better starting point and understanding of the problem.

New comment by thrwthsnw in "A Year of Telepathy"

thrwthsnw — Wed, 12 Feb 2025 23:15:09 +0000

Listen to an interview with Noland to find out why. Unfortunately the patient with ALS can’t give an interview because he can no longer speak.

New comment by thrwthsnw in "Why the WHO has recommended switching to a healthier salt alternative"

thrwthsnw — Tue, 04 Feb 2025 20:41:38 +0000

Probably because you’ll die if you eat too much.

New comment by thrwthsnw in "Why the WHO has recommended switching to a healthier salt alternative"

thrwthsnw — Tue, 04 Feb 2025 20:40:24 +0000

This is absurd, too much potassium is much more dangerous than too much salt.

New comment by thrwthsnw in "GitHub reveals how software engineers are purging federal databases"

thrwthsnw — Tue, 04 Feb 2025 20:37:22 +0000

It’s kind of lame that these guys are blacklisting words based on some master list. Normally these things get grandfathered in but I guess they’re just blindly following orders after getting sold down the river. It seems like an insane waste of manpower if you ask me. I’d hate to be the low man on the totem pole slaving away at this kind of bitchwork and getting ragged on by the bossman if I missed a word.

New comment by thrwthsnw in "LLMs: Harmful to Technical Innovation?"

thrwthsnw — Sun, 02 Feb 2025 15:02:59 +0000

Good documentation and examples help both the community and LLMs. My suggestion to any aspiring language or framework developers is to spend time creating both. If you really want to turbocharge adoption you could create a tool that automatically translates code examples from popular languages into your own language (and tests that they work) and then publish them online with some helpful comments.

New comment by thrwthsnw in "OpenAI O3-Mini"

thrwthsnw — Sat, 01 Feb 2025 13:30:30 +0000

Who determines who gets access to what information? The OpenAI board? Sam? What qualifies as dangerous information? Maybe it’s dangerous to allow the model to answer questions about a person. What happens when limiting information becomes a service you can sell? For the right price anything can become too dangerous for the average person to know about.

New comment by thrwthsnw in "Starship Flight 7"

thrwthsnw — Fri, 17 Jan 2025 13:09:40 +0000

The history of rocketry goes much further back than the space shuttle. The shuttle was supposed to be a step towards reusability but didn’t succeed or progress the way they thought it would. Starship is continuing that dream of full reusability and their approach is working. You can’t plan everything on paper when it comes to hardware especially when attempting things that have never been done before, you just don’t have the data in that case. You have to build prototypes and test them to destruction. All manufacturers do this.

New comment by thrwthsnw in "TikTok preparing for U.S. shut-off on Sunday"

thrwthsnw — Thu, 16 Jan 2025 01:55:55 +0000

Is this supposed to be good?

New comment by thrwthsnw in "Casual Viewing – Why Netflix looks like that"

thrwthsnw — Sat, 28 Dec 2024 12:21:34 +0000

If people aren’t watching the show why not just make it a radio play?

New comment by thrwthsnw in "Casual Viewing – Why Netflix looks like that"

thrwthsnw — Sat, 28 Dec 2024 12:17:58 +0000

We should just get rid of the ratings. They’re a stupid system that hasn’t worked anyways.

New comment by thrwthsnw in "Casual Viewing – Why Netflix looks like that"

thrwthsnw — Sat, 28 Dec 2024 12:12:36 +0000

The shorter article is better.

New comment by thrwthsnw in "Ask HN: Predictions for 2025?"

thrwthsnw — Mon, 23 Dec 2024 16:12:31 +0000

Wouldn’t solve anything, social media would just fragment even more. People will move to unregulated sites. Full on dictatorships can’t even prevent people from using the internet so how does anyone think this would work?

New comment by thrwthsnw in "Infinigen: Infinite Photorealistic Worlds Using Procedural Generation"

thrwthsnw — Mon, 23 Dec 2024 11:21:33 +0000

He’s asking if anyone is training using data created from a system like this, not if this uses AI.