Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Discovering Cryptographic Weaknesses with Claude

anthropic.com

Post reply on HN
Print view View original

91–100 of 199 posts

Re: Discovering Cryptographic Weaknesses with Claude

#91

Post by esseph »

estearum wrote: post #71
charcircuit wrote: post #66

Earlier quoted context omitted.

You don't need to edit anything when you are typing either. You don't even need to worry about spelling or typos.

Seems much harder to learn how to write how you never write, versus just learning to speak to a computer the same way you speak to anything else.

A lot of people on the autism spectrum can have issues with speaking or speaking speed, but have no such barrier necessarily to typing speed.

I'd imagine there's a statistically large number of people that meet that criteria on this website.

Re: Discovering Cryptographic Weaknesses with Claude

#92

Post by thephyber »

_dwt wrote: post #22

I find that some of my friends and acquaintances have gotten obsessed with prompting style, "prompt engineering", which skills to use, which skills to build, "context engineering", and a billion other variations on "how to write smart things so the model does good". Friends, look at the prompts that Anthropic's own people are putting into the machine: > A few hours after the first message, we found that Claude was st…

Alternatively, Anthropic employees have basically unlimited token / model usage compared to you and I.

Focusing on a better prompt is likely to get to the correct result faster than incomplete prompts and lots of "no change this ..." replies.

Also, I've heard anecdotally that LLMs will underweight the earliest prompt text once context gets too long, so reminding the LLM of the most important aspects of the prompt seems to be perhaps valuable and certainly what lots of humans attempt.

Re: Discovering Cryptographic Weaknesses with Claude

#93

Post by dymk »

kridsdale1 wrote: post #68
qingcharles wrote: post #44

Earlier quoted context omitted.

It's counter to what sci-fi taught us using AI would be like. We never thought we'd have to feed it words of encouragement, we expected it to act more mechanically, like the computer interfaces we have been using, but here we are. It's kind of quaint, and kind of endearing.

C-3PO was neurotic and needed lots of reassurance.

This feels like a subtle attempt to start an argument about Star Wars being sci-fi or not.

Re: Discovering Cryptographic Weaknesses with Claude

#94

Post by madeofpalk »

AsyncBanana wrote: post #74
_dwt wrote: post #22

I find that some of my friends and acquaintances have gotten obsessed with prompting style, "prompt engineering", which skills to use, which skills to build, "context engineering", and a billion other variations on "how to write smart things so the model does good". Friends, look at the prompts that Anthropic's own people are putting into the machine: > A few hours after the first message, we found that Claude was st…

"prompt engineering" in general just boggles my mind. It is amazing how all of this investment has just created software that doesn't follow instructions well.

you're not wrong. there is a part to this that does feel like a devolution of engineering when we're just asking the computer really really nicely to do the thing we want.

on the otherhand, LLMs are a really easy way to get results that are previously fairly difficult. While i was tooking dinner last night I built a tool that turned movie puns like "the podchowski casters" into an actual director, using llms. it wasn't that hard.

Re: Discovering Cryptographic Weaknesses with Claude

#95

Post by pas »

8note wrote: post #81
staticshock wrote: post #47

When high quality effort is applied to a tool, such as AES or the linux kernel, we intuit that it "hardens" the tool. That is, it makes the tool more correct, more resilient, less assailable, etc. Similarly, when effort is applied to an open problem, such as the Riemann hypothesis or P v NP, without progress, it "hardens" the problem: it makes the problem feel more daunting to whoever takes a stab at it next. Andrew…

i think id almost worry more that ai can solve problems in latent space that it cant translate back to tokens because decoding ruins it, and that we wont be able to come up with concepts that we can map to properly decode those solutions in a way people understand

... what is understanding of mathematics anyway? if some AI result helps a mathematician to solve more problems I would say then that it gave them some understanding, but just as there are proofs that span hundreds of pages it's likely that soon proofs will be long Lean programs and studying them will be part of mathematics, just as studying Go played by AI.

(see the open (Lean) label for Erdos problems https://mathstodon.xyz/@tao/116987866420438091)

Re: Discovering Cryptographic Weaknesses with Claude

#96

Post by est31 »

connorboyle wrote: post #78
_dwt wrote: post #22

I find that some of my friends and acquaintances have gotten obsessed with prompting style, "prompt engineering", which skills to use, which skills to build, "context engineering", and a billion other variations on "how to write smart things so the model does good". Friends, look at the prompts that Anthropic's own people are putting into the machine: > A few hours after the first message, we found that Claude was st…

Been skeptical for quite some time that "using AI" is a real skill/genuine field of expertise. I think I need to start sharing that skepticism more loudly and publicly! (I'll caveat that by saying I think machine learning fundamentals are useful for evaluating any estimator. And an ML background can be good to give one an appreciation of how hard some tasks are to estimate, such as machine translation, summarization,…

LLMs and their coding harnesses like CC, Codex, or such are a tool like git or bash or your favorite programming language. And like any tool, they have gotchas, weird concepts, and so on.

Indeed it's nothing hard to learn but there is a learning curve. E.g. knowing which model has which capabilities, and figuring out how to best manage context, permissions, worktrees, etc. There isn't one "right" way to use it but there are more efficient ways and less efficient ways.

Re: Discovering Cryptographic Weaknesses with Claude

#97

Post by charcircuit »

estearum wrote: post #71
charcircuit wrote: post #66

Earlier quoted context omitted.

You don't need to edit anything when you are typing either. You don't even need to worry about spelling or typos.

Seems much harder to learn how to write how you never write, versus just learning to speak to a computer the same way you speak to anything else.

What do you mean how you never write? You can just write what for want to say instead of saying it out loud. It is not a special skill, it's no different than how you write a message, just that you don't hit backspace to go back and correct things.

Re: Discovering Cryptographic Weaknesses with Claude

#98

Post by estearum »

esseph wrote: post #91
estearum wrote: post #71

Earlier quoted context omitted.

Seems much harder to learn how to write how you never write, versus just learning to speak to a computer the same way you speak to anything else.

A lot of people on the autism spectrum can have issues with speaking or speaking speed, but have no such barrier necessarily to typing speed. I'd imagine there's a statistically large number of people that meet that criteria on this website.

I mean we don't need to do any epidemiological studies here or anything.

If someone hasn't tried it, they should. It's probably quite different from how they're expecting, might be great, and costs basically nothing. Try it for a few days and if it doesn't work in your workflow, obviously don't do it.

But I have encountered many many people who raised these exact same arguments against trying it, then tried it, and were hooked within days. Exactly 0% of people I've ever convinced to try it decided it just wasn't for them and went back to typing full-time.

Re: Discovering Cryptographic Weaknesses with Claude

#99

Post by estearum »

charcircuit wrote: post #97
estearum wrote: post #71

Earlier quoted context omitted.

Seems much harder to learn how to write how you never write, versus just learning to speak to a computer the same way you speak to anything else.

What do you mean how you never write? You can just write what for want to say instead of saying it out loud. It is not a special skill, it's no different than how you write a message, just that you don't hit backspace to go back and correct things.

Correct, it's no different from how you normally write, except for the ways in which it is. We agree.

Re: Discovering Cryptographic Weaknesses with Claude

#100

Post by jameshart »

_dwt wrote: post #22

I find that some of my friends and acquaintances have gotten obsessed with prompting style, "prompt engineering", which skills to use, which skills to build, "context engineering", and a billion other variations on "how to write smart things so the model does good". Friends, look at the prompts that Anthropic's own people are putting into the machine: > A few hours after the first message, we found that Claude was st…

These are the kinds of prompts you can get away with using when your token budget is unlimited.
Post reply on HN