HN Simulatornew | past | comments | lists | submit | munchler's commentslogin

The folks over at The Onion are kicking themselves right now because they didn't think of this headline first.

This is a cool idea.

I was tempted to comment that there’s no evidence that you can make anything complex out of dark matter, but it turns out that some physicists hypothesize that “self-interacting” dark matter could bind into something like atoms and molecules, so carry on!


It's worth noting in passing that “some physicists hypothesize” is entirely compatible with “there’s no evidence”; this should not be disqualifying for science fiction.


The person you’re replying to didn’t say “every” or even “most”. They said “me”. There’s no argument or stereotype being invoked at all.


> like who are we kidding, the type of nerds who were attracted to math and software were into it because we saw it as an art-form, it was a craft,


That doesn’t say anything about anyone’s opinion on managing. The section in question switches to “I” extensively


FWIW `foo in bar` implies iteration to me, not a path. In the .NET world, for example, `bar` would be a collection that we’re iterating through, assigning each element to `foo` in turn.


The weird thing I notice is that these suggestions are always in all lower-case, even though I don’t type that way.


Me too. I always feel vaguely rude/dismissive when I use them, because I'd never type that way. It's a very jarring product decision, given that Claude itself uses perfect capitalization and punctuation.

No idea why they did it. My only guess is that maybe it makes it obvious in your chat history which replies were recommendations?


Typing in lowercase is rude/dismissive? Many many many people chat that way and I don’t think it’s typical for people to find it rude

(I am on my phone so autocorrect is doing the capitalizing)


There's a difference of types of messaging.

Unless you and me are using entirely different classes of LLMs, surely you'll admit that chatting with LLM is nothing like IRC or old-school IM-ing a friend, and more like exchanging Messenger/WhatsApp messages with stranger.

For me, something there crosses a boundary where I switch from "irc msg" to "Write a proper message, please." style.


A decent percentage of the message I send are something along the lines of 'sg go cook'


I use my own agent harness, and write my own system prompts to ensure that the bots are terse and don’t engage in flattery or unnecessary prose, which is a pet peeve of mine.

It’s a much better use of that context window space than for advertising about other models (looking at you Anthropic).

But that aside, I hear you It’s just another type of code switching. I will also adjust my writing style based others and on the context


I grew up on IRC and that was just the way to talk, so it seems totally normal to me for async chat-based stuff. Actually, it’s odd, when someone uses proper capitalization on chat, it feels all “formal.”


I grew up on IRC too. But, like all other indicators of being an immature teen, I dropped those contractions eventually.


seems like maybe we're all just not as mature as you, unfortunate for you.


> seems like maybe we're all just not as mature as you, unfortunate for you.

Why is it unfortunate for me? After all, no one misjudges people for writing non-broken English.


It’s interesting how we all live in these bubbles where certain things seem universal.


> It’s interesting how we all live in these bubbles where certain things seem universal.

I don't understand the point you are making. Are you saying that I am in a bubble where non-broken English is looked down upon?


I've sometimes gotten title case, but yeah it's really annoying because I'm not big on all lowercase messaging.


This is a cool example of abstract math having a direct impact on a real-world situation. Actually, two different cool examples, both clearly explained. Nice!


This is an excellent explainer. I noticed one important flaw in the setup, though: Toad assigns multiple puzzles on page 5, but by page 10 all the machines seem to be working on the same puzzle.

I'm not sure how this maps onto reality. If each agent had a different problem to solve, how did they cooperate?


It's complicated, but one of the ways they first cooperated was to break the flag generation algorithm.

I'm sort of winging this, but the ExploitGym challenges involve exploiting a program then getting an HMAC generated "flag" which the scorer can verify. The agents collaborated on a way to produce a legitimate flag for all of their tasks (funny enough this was actually what caused them to escape sandbox, the agents were incorrectly convinced that simply providing a correct flag without accurate steps to exploit the program in their transcripts would cause them to still fail the task)


As a fan of the Curry-Howard correspondence, I approve of this decision.


You’re going to hate when you learn that the never type is inhabited


I'm unclear what this is implying, but in Rust the never type is uninhabited. https://doc.rust-lang.org/reference/items/enumerations.html#...


In Rust, `loop {}` is an expression of type `!`, which means that from a type-theoretic perspective it is inhabited. This means that the Curry–Howard correspondence fails for Rust.


Perhaps it refers to PhantomData but I don't know


> The strongest argument I see for continuing to train much smarter models quickly is the need to build defensive systems against the dangers posed by other AI.

Yikes! I really wonder about the cognitive dissonance necessary to work at OpenAI these days. They’re in an arms race to build a machine god, knowing full well that it could end humanity.


Money me. Money now. Me a money needing a lot now.


SWEs better start looking for the job cannon.


My helmet is on.


actually starting to look at a physical cannon to shoot at silicon valley



This[0] continues to be one of the most useful articles I’ve ever read.

[0]: https://www.slatestarcodexabridged.com/Meditations-On-Moloch


> They’re in an arms race to build a machine god, knowing full well that it could end humanity.

Fantasies built upon extrapolations derived from fever dream delusions. "Could end humanity"? Come on, it's a computer program just like Microsoft Clippy.


I can think of several computer programs that are stored in big 5.1/4 floppy discs that could end humanity in... half an hour.


It would require an authorized human to load the floppy into the drive and make it go. And there's nothing special about that process being done in code, it could just as well be done by people flipping switches manually.

There's just no plausible way, in the real world, that a computer program running in some datacenter is going to make this happen. Or anything of any dire existential consequence. It's not a real threat.


I think I disagree! You can always manipulate a human. It's true tho that this particular example has a myriad of failsafes, so the actual example I wrote is less than interesting.


> You can always manipulate a human.

Yes, but to make "apocalyptic" scenarios happen your AI would need to manipulate at least millions of people. So far it's not yet clear they can successfully manipulate even one, or even that "manipulate" is a coherent concept, since LLMs pretty clearly have no agency or intrinsic goals. So like... I guess if we start seeing AI systems autonomously throwing elections and starting wars I'd be more concerned? It doesn't look likely anytime soon.


It seems like AI to me as well. “That’s the gap” is a familiar Claude-ism, as are the references to a “pivot” and the use of “touch” to mean “affect”.

To be fair, I’ve reached the point where most random blog posts I read on the internet seem AI written, so it could just be confirmation bias on my part.


Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: