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

111–120 of 199 posts

Re: Discovering Cryptographic Weaknesses with Claude

#111

Post by himata4113 »

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…

AI is nowhere near the intelligence of a very educated person that has innate talent for problem solving. It does solve the problem of applying human intelligence on problems that truly need it. AI is also a great tool to see if there's something simple that we've missed or just haven't even attempted due to wrong assumptions.

Re: Discovering Cryptographic Weaknesses with Claude

#112

Post by Dylan16807 »

estearum wrote: post #110
Dylan16807 wrote: post #109

Earlier quoted context omitted.

How often I do it doesn't matter because it's such a trivial thing to switch. If you're gonna "try it for a few weeks" the part of you that has to learn the typing-specific parts of that method is about 1% of the difficulty. It's really easy to ignore typos. And the way you have to approach thinking and correcting is the same whether you're typing or voicing. If you can't just type the way you would just talk, and yo…

But it's literally not. You already correct yourself and revise your speech in an append-only rolling edit. You do it all day every day for decades. Versus never writing in this way. Have you tried the voice-based prompting, as I'm describing?

"never" schmever. I never ramble unrestrained either. Deciding not to edit at all is a skill either way. If you just want the equivalent of voice in a normal way, you remove backspace and that's it.

> Have you tried the voice-based prompting, as I'm describing?

I've never prompted a thing. I can just see your distinction is nonsense. If you think it's hard you're doing it wrong.

And wow I did that post without revising a thing. Wow.

Re: Discovering Cryptographic Weaknesses with Claude

#113

Post by glimshe »

alwa wrote: post #82
connorboyle wrote: post #78

Earlier quoted context omitted.

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,…

I think knowing what you want (and being able to articulate it with adequate specificity, and detecting when processes drift away from it) is a real skill/field of expertise. I just don't think it's specific to interfacing with "AI."

I agree. These skills apply to interacting with any coworker, or any person for that matter.

Re: Discovering Cryptographic Weaknesses with Claude

#114

Post by xp84 »

alwa wrote: post #82
connorboyle wrote: post #78

Earlier quoted context omitted.

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,…

I think knowing what you want (and being able to articulate it with adequate specificity, and detecting when processes drift away from it) is a real skill/field of expertise. I just don't think it's specific to interfacing with "AI."

Indeed. It sounds more like management (Minus the 'people skills' since you don't technically need Claude to like you... yet).

Re: Discovering Cryptographic Weaknesses with Claude

#115

Post by estearum »

Dylan16807 wrote: post #112
estearum wrote: post #110

Earlier quoted context omitted.

But it's literally not. You already correct yourself and revise your speech in an append-only rolling edit. You do it all day every day for decades. Versus never writing in this way. Have you tried the voice-based prompting, as I'm describing?

"never" schmever. I never ramble unrestrained either. Deciding not to edit at all is a skill either way. If you just want the equivalent of voice in a normal way, you remove backspace and that's it. > Have you tried the voice-based prompting, as I'm describing? I've never prompted a thing. I can just see your distinction is nonsense. If you think it's hard you're doing it wrong. And wow I did that post without revisi…

Right. So the crux of the issue here is you have no experience with what's being discussed, while I do.

Sheesh, imagine thinking you choose not to rewind time and "edit" the speech that has already come out of your mouth lmao.

Re: Discovering Cryptographic Weaknesses with Claude

#116

Post by Dylan16807 »

estearum wrote: post #115
Dylan16807 wrote: post #112

Earlier quoted context omitted.

"never" schmever. I never ramble unrestrained either. Deciding not to edit at all is a skill either way. If you just want the equivalent of voice in a normal way, you remove backspace and that's it. > Have you tried the voice-based prompting, as I'm describing? I've never prompted a thing. I can just see your distinction is nonsense. If you think it's hard you're doing it wrong. And wow I did that post without revisi…

Right. So the crux of the issue here is you have no experience with what's being discussed, while I do. Sheesh, imagine thinking you choose not to rewind time and "edit" the speech that has already come out of your mouth lmao.

I'm doing it right now you goober! Stop calling it hard!

What experience do you insist I'm lacking in something I'm doing right now?

Re: Discovering Cryptographic Weaknesses with Claude

#117

Post by ozozozd »

heaney-555 wrote: post #42
ecshafer wrote: post #17

Earlier quoted context omitted.

So $1-10k in Chinese model time, thus why we must ban them.

If a Chinese model can do it for $1-10K, then why hasn't one? Why have all the mathematical (and now cryptographic) breakthroughs come from OpenAI and Anthropic? Is it possibly because the Chinese models are so benchmaxxed they can't make novel discoveries?

“I haven’t seen X, therefore it doesn’t exist.”

Absence of evidence is not an evidence for absence of something.

Re: Discovering Cryptographic Weaknesses with Claude

#118

Post by noosphr »

axus wrote: post #5

I can already picture the faces of national security directors everywhere. "The attacks described in these two papers are the strongest attacks we have found to date. We are sharing them after a period of consultation with US government and industry leaders. But as we develop increasingly powerful cryptanalytic results, it would be prudent to consider how researchers should react if a language model were to discover…

We have reached the end of childhood for programming. Artisanal code written by hand is no longer acceptable and neither is slop code. We need formal methods and we need them 10 years ago.

Re: Discovering Cryptographic Weaknesses with Claude

#119

Post by ipgleg »

_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…

[flagged]

Re: Discovering Cryptographic Weaknesses with Claude

#120

Post by ipgleg »

impulser_ wrote: post #43
_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…

Yeah, in fact you can actually make the model perform worst. You should allow the model to "think for itself" instead of pushing your reasoning into the prompt. You should give it simple prompt and steer it along the way. Skills, CLAUDE.md/AGENTS.md should only ever be used if the model struggle at something or doesn't know how to use something. Vast majority of project should never need a skill or CLAUDE.md. If you…

[flagged]
Post reply on HN