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

You are being too optimistic:

That relationship is not true. It might be true at the efficiency frontier. Maybe. I don't know.

But it's very easy to compromise on convenience without gaining any security and vice versa.


Presumably he's using the native harness for each model? (The one their company recommends.)

DeepSeek's models are also worth a try, mostly because they are so cheap. If you can split up your tasks so that deepseek can handle them, you can save a lot of money. (You can ask a more capable model to help you with the split.)

This user is clearly not concerned with saving money, they’re looking for quality.

For comparison for chess, it didn't last that long.

Chess is very constrained, and doesn't require all sorts of knowledge about the broader context outside the game.

Once models are more hooked up to sources of information, their capabilities will improve. Currently, humans are a bottleneck for providing the information relative to specific problems.

"Take the human out of the loop" - I think there was a documentary about that, with Matthew Broderick.


A strange game! The only winning move is not to play

Only if you're in Zugzwang

Especially since that check might have further problems. The simpler you can make your code (and still solve the problem) the better.

I don't know if I'd count paving over the reality of what you're running with an abstraction layer as something simpler. If anything it demonstrably makes addressing issues like these harder.

I think you're right, but many people are running systems at large scale, with lots of hosts and all kinds of abstraction layers and stuff. Now this exploit shows up. What are they to do? It's just a practical thing they can do right now.

First we must stop the bleeding. After that, yes, it's worth figuring out if they should change how things are set up.

I've been in situations like this before. Sometimes the complications and abstractions were my fault, sometimes I inherited them. Either way, as responsible owners of the overall system or business, we've gotta be able to respond fast to issues.


You can use the kernel config to remove these things.

> I think only really smart people are going to be left in Security and Software.

I'm looking forward to eventually getting there. At the moment, there's so much low hanging fruit that even someone without a clue like me can just point a fuzzer at some random Linux kernel code and still discover problems.

(Most of the problems I found from that exercise are patched by now, if you use a recent enough kernel.)

I used Kimi to drive the fuzzer. The model didn't have to do anything smart, just do the tedious work of writing the glue code to make the fuzzing work. AFL++ did the 'smart' parts, and I had the idea to kick it off and oversaw the patches.


> And rust is no a no-no for a database project like this, because it is not ergonomic to do static allocation and arena allocators in rust.

I'm not sure ergonomics matter that much these days, when your agent can write the tedious bits?


Code being in a simple state also matters with the efficiency of agents ime.

It is not just ergonomics but the point of using rust is to have solid abstraction and a lot of high quality libraries to use.

If you are doing static allocation + arenas then you can't use nice abstraction, you can't use libraries, you have to write a ton of unsafe code because of these reasons. Then using rust is actually working against you so there is no point in using it.


> Markets are random walks so they exhibit a fairly fixed distribution of different sized crashes.

Market prices being unpredictable random walks doesn't mean that the volatility or shape needs to be constant. To make the notation more precise, you need to talk about (sub-) martingales.

> If they deviated, someone could notice that pattern and trade on it, returning the market back to a random walk.

This is true, but "fairly fixed distribution of different sized crashes." doesn't follow at all.


I'm not so sure about that.

If Claude can write formal mathematical proofs (that a machine can check), or it can write software that works, where's the head of the reader that imposes the meaning?


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

Search: