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

Claude Code can debug low-level cryptography

words.filippo.io

Post reply on HN
Print view View original

81–90 of 217 posts

Re: Claude Code can debug low-level cryptography

#81

Post by chatmasta »

danielbln wrote: post #78
chatmasta wrote: post #72

Earlier quoted context omitted.

What makes it better than VSCode Co-pilot with Claude 4.5? I barely program these days since I switched to PM but I recently started using that and it seems pretty effective… why should I use a fork instead?

Claude Code is not a VSCode fork, it's a terminal CLI. It's a rather different interaction paradigm compared to your classical IDE (that said, you can absolutely run Claude Code inside a terminal inside VSCode).

Ah, I think I’m getting it confused with Cursor. So Claude Code is a terminal CLI for orchestrating a coding agent via prompts? That’s different than the initial releases of VSC copilot, but now VSC has “agent” mode that sounds a lot like this. It basically reduces the IDE to a diff viewer.

Re: Claude Code can debug low-level cryptography

#82

Post by undeveloper »

chatmasta wrote: post #72
simonw wrote: post #41

Earlier quoted context omitted.

I think it might be that they've hit product-market fit. Developers find Claude Code extremely useful (once they figure out how to use it). Many developers subscribe to their $200/month plan. Assuming that's profitable (and I expect it is, since even for that much money it cuts off at a certain point to avoid over-use) Anthropic would be wise to spend a lot of money on marketing to try and grow their paying subscribe…

What makes it better than VSCode Co-pilot with Claude 4.5? I barely program these days since I switched to PM but I recently started using that and it seems pretty effective… why should I use a fork instead?

I find copilot simply worse at "understanding" codebases than claude code

Re: Claude Code can debug low-level cryptography

#83

Post by ori_b »

Wowfunhappy wrote: post #80
rtpg wrote: post #61

Earlier quoted context omitted.

I understand the pitch here ("it finds bugs! it's basically all upside because worst case there's no output anyways"), but I'm finding some of these agents to be ... uhhh... kind of agressive at trying to find the solution and end up missing the forest for the trees. And there's some "oh you should fix this" stuff which, while sometimes isn't _wrong_, is completely besides the point. The end result being these robots…

Sometimes you hit a wall where something is simply outside of the LLM's ability to handle, and it's best to give up and do it yourself. Knowing when to give up may be the hardest part of coding with LLMs. Notably, these walls are never where I expect them to be—despite my best efforts, I can't find any sort of pattern. LLMs can find really tricky bugs and get completely stuck on relatively simple ones.

Doing it yourself is how you build and maintain the muscles to do it yourself. If you only do it yourself when the LLM fails, how will you maintain those muscles?

Re: Claude Code can debug low-level cryptography

#84

Post by ericphanson »

ay wrote: post #25
lordnacho wrote: post #14

I'm not surprised it worked. Before I used Claude, I would be surprised. I think it works because Claude takes some standard coding issues and systematizes them. The list is long, but Claude doesn't run out of patience like a human being does. Or at least it has some credulity left after trying a few initial failed hypotheses. This being a cryptography problem helps a little bit, in that there are very specific keywo…

> Claude doesn't run out of patience like a human being does. It very much does! I had a debugging session with Claude Code today, and it was about to give up with the message along the lines of “I am sorry I was not able to help you find the problem”. It took some gentle cheering (pretty easy, just saying “you are doing an excellent job, don’t give up!”) and encouragement, and a couple of suggestions from me on how…

Claude told me it stopped debugging since it would run out of tokens in its context window. I asked how many tokens it had left and it said actually it had plenty so could continue. Then again it stopped, and without me asking about tokens, wrote

Context Usage • Used: 112K/200K tokens (56%) • Remaining: 88K tokens • Sufficient for continued debugging, but fresh session recommended for clarity

lol. I said ok use a subagent for clarity.

Re: Claude Code can debug low-level cryptography

#85

Post by reachableceo »

cmrdporcupine wrote: post #7
qsort wrote: post #2

This resonates with me a lot: > As ever, I wish we had better tooling for using LLMs which didn’t look like chat or autocomplete I think part of the reason why I was initially more skeptical than I ought to have been is because chat is such a garbage modality. LLMs started to "click" for me with Claude Code/Codex. A "continuously running" mode that would ping me would be interesting to try.

I absolutely agree with this sentiment as well and keep coming back to it. What I want is more of an actual copilot which works in a more paired way and forces me to interact with each of its changes and also involves me more directly in them, and teaches me about what it's doing along the way, and asks for more input. A more socratic method, and more augmentic than "agentic". Hell, if anybody has investment money an…

Have you tried to ask the agents to work with you in the way you want?

I’ve found that using some high level direction / language and sharing my wants / preferences for workflow and interaction works very well.

I don’t think that you can find an off the shelf system todo what you want. I think you have to customize it to your own needs as you go.

Kind of like how you customize emacs as it’s running to your desires.

I’ve often wondered if you could put a mini LLM into emacs or vscode and have it implement customizations :)

Re: Claude Code can debug low-level cryptography

#86

Post by SamInTheShell »

nl wrote: post #69
SamInTheShell wrote: post #15

Earlier quoted context omitted.

> Gemini and it's tooling is absolute shit. Which model were you using? In my experience Gemini 2.5 Pro is just as good as Claude Sonnet 4 and 4.5. It's literally what I use as a fallback to wrap something up if I hit the 5 hour limit on Claude and want to just push past some incomplete work. I'm just going to throw this out there. I get good results from a truly trash model like gpt-oss-20b (quantized at 4bits). The…

I think you must be using it quite differently to me. I can one-shot new webapps in Claude and Codex and can't in Gemini Pro.

The type of stuff I tend to do is much more complex than a simple website. I really can't rely on AI as heavily for stuff that I really enjoy tinkering with. There's just not enough data for them to train on to truly solve distributed system problems.

Re: Claude Code can debug low-level cryptography

#87

Post by majormajor »

bongodongobob wrote: post #77
majormajor wrote: post #60

Earlier quoted context omitted.

They're quite good at algorithm bugs, a lot less good at concurrency bugs, IME. Which is very valuable still, just that's where I've seen the limits so far. Their also better at making tests for algorithmic things than for concurrency situations, but can get pretty close. Just usually don't have great out-of-the-box ideas for "how to ensure these two different things run in the desired order." Everything that I disli…

Well if you know it's wrong, tell it, and why. I don't get the expectation for one shotting everything 100% of the time. It's no different than bouncing ideas off a colleague.

I don't care about one-shotting; the stuff it's bad for debugging at is the stuff where even when you tell it "that's not it" it just makes up another plausible-but-wrong idea.

For code modifications in a large codebase the problem with multi-shot is that it doesn't take too many iterations before I've spent more time on it. At least for tasks where I'm trying to be lazy or save time.

Re: Claude Code can debug low-level cryptography

#88

Post by imiric »

fn-mote wrote: post #64
XenophileJKO wrote: post #53

Earlier quoted context omitted.

I guess there are several unsaid assumptions here. The article is by a domain expert working on their domain. Throw work you understand at it, see what it does. Do it before you even work on it. I kind of assumed based on the audience that most people here would be domain experts. As for the building intuition, perhaps I am over-estimating what most people are capable of. Working with and building systems using LLMs…

> I kind of assumed based on the audience that most people here would be domain experts. No take on the rest of your comment, but it’s the nature of software engineering that we work on a breadth of problems. Nobody can be a domain expert in everything. For example: I use a configurable editor every day, but I’m not a domain expert in the configuration. An LLM wasted an hour of my day pointing me in “almost the right…

Exactly.

A typical programmer works within unfamiliar domains all the time. It's not just about being familiar with the programming language or tooling. Every project potentially has new challenges you haven't faced before, new APIs to evaluate and design, new tradeoffs to consider, etc.

The less familiar you are with the domain or API, the less instincts and influence you have to steer the LLM in the right direction, and the more inclined you are to trust the tool over yourself. So when the tool is wrong, as it often still is, you can spend a lot of time fighting with it to produce the correct output.

The example in the article is actually the best case scenario for these tools. It's essentially pattern matching using high quality code, from someone who's deeply familiar with the domain and the code they've written. The experience of someone unfamiliar trying to implement the same algorithm from scratch by relying on LLMs would be vastly different.

Re: Claude Code can debug low-level cryptography

#89

Post by sega_sai »

SamInTheShell wrote: post #71
sega_sai wrote: post #50

Earlier quoted context omitted.

I get that even with the 2.5 pro

That's weird. I can prompt 2.5 Pro and Claude Sonnet 4.5 about the same for most typescript problems and they end up doing about the same. I get different results with Terraform though, I think Gemini 2.5 Pro does better on some Google Cloud stuff, but only on the specifics. Is just strange to me that my experience seems to be a polar opposite of yours.

I don't know. The last problem I tried was a complex one -- migration of some scientific code from CPU to GPU. Gemini was useless there, but Claude proposed realistic solutions and was able to explore and test those.

Re: Claude Code can debug low-level cryptography

#90

Post by nicklaf »

bongodongobob wrote: post #77
majormajor wrote: post #60

Earlier quoted context omitted.

They're quite good at algorithm bugs, a lot less good at concurrency bugs, IME. Which is very valuable still, just that's where I've seen the limits so far. Their also better at making tests for algorithmic things than for concurrency situations, but can get pretty close. Just usually don't have great out-of-the-box ideas for "how to ensure these two different things run in the desired order." Everything that I disli…

Well if you know it's wrong, tell it, and why. I don't get the expectation for one shotting everything 100% of the time. It's no different than bouncing ideas off a colleague.

It's painfully apparent when you've reached the limitations of an LLM to solve a problem it's ill-suited for (like a concurrency bug), because it will just keep spitting out non-sense, eventually going in circles or going totally off the rails.
Post reply on HN