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

171–180 of 199 posts

Re: Discovering Cryptographic Weaknesses with Claude

#171

Post by jstanley »

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?

> You already correct yourself and revise your speech in an append-only rolling edit.

No, I think before I speak and say what I planned to say. What do you do, sir?

Re: Discovering Cryptographic Weaknesses with Claude

#172

Post by estearum »

esseph wrote: post #139
estearum wrote: post #98

Earlier quoted context omitted.

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 w…

The thought of talking drives me insane but you do you, boo-boo :)

Yes virtually every person I've ever talked to about this had the same initial reaction

Re: Discovering Cryptographic Weaknesses with Claude

#173

Post by estearum »

jstanley wrote: post #171
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?

> You already correct yourself and revise your speech in an append-only rolling edit. No, I think before I speak and say what I planned to say. What do you do, sir?

Cute snark but no you don't, nor does anyone else who speaks to you. People self-repair their speech in 10% to nearly 40% of speech turns. The upper end is for cognitively demanding communication but the lower bound is very normal.

Good evidence of my point though on how natural this is. People literally don't even notice it as either the listener or the speaker.

Even when a listener is told specifically to listen for and detect errors or self-repairs in speech, listeners will not even detect 50% to 80% of minor repairs. Your brain literally doesn't even perceive them.

Re: Discovering Cryptographic Weaknesses with Claude

#174

Post by Lord-Jobo »

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,…

It can be a skill, but a very soft skill like keeping control of and educating 30 kindergarten students. It’s a skill, hard earned and nebulous. you can recognize it clearly when you see it, but it’s very hard to define/measure numerically and will never achieve anything close to “perfect” results.

Until these models become many factors more deterministic, at least. That’s sort of the hard barrier here, and given the underlying tech it’s a really tough one to overcome

Re: Discovering Cryptographic Weaknesses with Claude

#176

Post by wglb »

somenameforme wrote: post #154
xp84 wrote: post #114

Earlier quoted context omitted.

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

I'm curious if there has been any study on the output quality of LLMs after actively antagonizing them. It's easy to forget that at the most basic level these are just auto-complete machines, and humans tend to not respond so well after antagonized. It stands to reason that the same should follow for an auto-complete system trained on human interaction.

In fact there has: https://arxiv.org/abs/2510.04950: Mind Your Tone: Investigating How Prompt Politeness Affects LLM Accuracy (short paper)

Re: Discovering Cryptographic Weaknesses with Claude

#177

Post by jrflo »

ericpauley wrote: post #140
jrflo wrote: post #18

Earlier quoted context omitted.

That's not really that ridiculous. Looking at my ChatGPT stats my biggest day of token usage was 1B tokens (seeing how far Sol Ultra could go on a difficult problem with a quantitative goal and eval harness that it could run on it's own that allowed it to keep going until it succeeded). I blew through my $100 subscription usage in that one day, but with a 80/20 token blend that's $10k in API billing. So, $70k in a we…

Is that including cache reads? It seems improbable that (a) you actually filled 1000 1M contexts and (b) OpenAI allowed that in a $100 subscription window.

I don't know, codex does not disclose that information, it just says "1.1B Tokens". OpenAI recently got rid of their 5-hour usage window, so you can burn the entire week in one go, which is what I did.

Re: Discovering Cryptographic Weaknesses with Claude

#178

Post by jrflo »

gbalduzzi wrote: post #70
jrflo wrote: post #18

Earlier quoted context omitted.

That's not really that ridiculous. Looking at my ChatGPT stats my biggest day of token usage was 1B tokens (seeing how far Sol Ultra could go on a difficult problem with a quantitative goal and eval harness that it could run on it's own that allowed it to keep going until it succeeded). I blew through my $100 subscription usage in that one day, but with a 80/20 token blend that's $10k in API billing. So, $70k in a we…

How much was valuable the output you got during the day? Is it at least comparable to the $10k of cost?

Definitely not. It was my first time using Sol Ultra, and I did not expect it to run for 12hr+ continuously. Previously with 5.5 I had to coax it to go for longer than a half hour, so I just started a run and forgot to check back in on it. I think I'm learning how to use it more effectively now, and I could see a scenario where that could actually be worthwhile, but it's a bit of a shot in the dark if you let it go that long uninterrupted.

Re: Discovering Cryptographic Weaknesses with Claude

#179

Post by saghm »

AvocadoPanic wrote: post #121
alwa wrote: post #82

Earlier quoted context omitted.

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."

Having domain expertise isn't specific to using AI. Not being able to tell when it's hallucinating has led to some very adverse outcomes.

I've found that one of the most useful things I can do when using LLMs is paying attention to the tool calls so that I can tell when it's giving an explanation that's obviously not based on any evidence. If it explains why a bug happens without reading the relevant files, it's obviously just a guess. If I ask about what things exist that fit certain criteria, and it doesn't search online, at best it's relying on outdated knowledge from training and at worst it's literally inventing things that don't actually exist.

In a lot of scenarios for software engineering, the cost is just wasted time without anything useful as a result, and that's already bad enough. I can't even imagine working as a lawyer and not even taking the time to validate so I don't end up reprimanded by a judge in front of my clients, but there have been so many news stories like this that obviously this is not anywhere close to a universal view...

Re: Discovering Cryptographic Weaknesses with Claude

#180

Post by uncivilized »

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.

True. People arguing over prompts is akin to people arguing over which way to pull the lever on a slot machine.
Post reply on HN