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

201–210 of 217 posts

Re: Claude Code can debug low-level cryptography

#201

Post by hitarpetar »

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.

except it's not a colleague, it's not capable of ideation, it's taking your words and generating new ones based on them. which can maybe be useful sometimes but, yeah, not really the same as bouncing ideas off a colleague

Re: Claude Code can debug low-level cryptography

#202

Post by bontaq »

rtpg wrote: post #61
simonw wrote: post #11

Using coding agents to track down the root cause of bugs like this works really well: > Three out of three one-shot debugging hits with no help is extremely impressive. Importantly, there is no need to trust the LLM or review its output when its job is just saving me an hour or two by telling me where the bug is, for me to reason about it and fix it. The approach described here could also be a good way for LLM-skepti…

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…

I would say a lot of people are only posting their positive experiences. Stating negative things about AI is mildly career-dangerous at the moment where as the opposite looks good. I found the results from using it on a complicated code base are similar to yours, but it is very good at slapping things on until it works.

If you're not watching it like a hawk it will solve a problem in a way that is inconsistent and, importantly, not integrated into the system. Which makes sense, it's been trained to generate code, and it will.

Re: Claude Code can debug low-level cryptography

#203

Post by dcow »

kryogen1c wrote: post #169
Wowfunhappy wrote: post #107

Earlier quoted context omitted.

I agree, and I can actively feel myself slipping (and perhaps more critically, not learning new skills I would otherwise have been forced to learn). It's a big problem, but somewhat orthogonal to "what is the quickest way to solve the task currently in front of me."

> but somewhat orthogonal to "what is the quickest way to solve the task currently in front of me." That depends on if you ignore the future. You are never just solving the problem in front of you; you should always act in a way that propagates positivity forward in time.

Some jobs require investment in the future. Some do not. That’s just reality. Not white how I feel about it personally, but I think there is a fair amount of the developer trade that is operational.

Re: Claude Code can debug low-level cryptography

#204

Post by hitarpetar »

XenophileJKO wrote: post #99
imiric wrote: post #88

Earlier quoted context omitted.

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…

I mean I "understand" your point. However, this isn't any different than being a technical lead in a system of any significant complexity.. you will constantly be reviewing work that you are not always an expert on, it is a very similar practice. I'm constantly reviewing things that I am not a domain expert on. I have to identify what is risky, what I don't know, etc. Throwing to the AI first is no different than thr…

> Throwing to the AI first is no different than throwing to someone else first

except in all the ways that it is obviously different

Re: Claude Code can debug low-level cryptography

#205

Post by hitarpetar »

simonw wrote: post #41
pton_xd wrote: post #33

> Full disclosure: Anthropic gave me a few months of Claude Max for free. They reached out one day and told me they were giving it away to some open source maintainers. Related, lately I've been getting tons of Anthropic Instagram ads; they must be near a quarter of all the sponsored content I see for the last month or so. Various people vibe coding random apps and whatnot using different incarnations of Claude. Or j…

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…

> since even for that much money it cuts off at a certain point to avoid over-use

if anything this just confirms that the unit economics are still bad

Re: Claude Code can debug low-level cryptography

#206

Post by advael »

dns_snek wrote: post #147
advael wrote: post #122

Earlier quoted context omitted.

With all due respect, "wow this is cool, I wonder what it'll turn into" is basically the mandatory baseline stance to take. I'm lucky that's where I'm still basically at, because anyone in a technical position who shows even mild reticence beyond that is likely to be unable to hold a job in the face of their bosses' frothing enthusiastic optimism about these technologies

Is it that bad out there? Yeah, I don't think I could last in a job that tries to force these tools into my workflow.

You can get pretty far by mostly just claiming to use it "when it makes sense" but you do meet people who are very pushy about it. Hoping that calms down as knowledge of the downsides becomes more widespread

Re: Claude Code can debug low-level cryptography

#207

Post by monocasa »

AbstractH24 wrote: post #188
ThrowawayR2 wrote: post #187

Earlier quoted context omitted.

Moving up abstraction layers really only succeeds with a solid working knowledge of the lower layers. Otherwise, you're just flying blind, operating on faith. A common source of bugs is precisely a result of developers failing to understand the limits of the abstractions they are using.

So we can all only succeed if we know how CPUs handle individual instructions?

There's generally a pretty quick falloff of how much help knowledge of each layer under you generally provides as you go deeper.

That being said, if you're writing in C, having a pretty good idea of how a cpu generally executes instructions is pretty key to success I'd say.

Re: Claude Code can debug low-level cryptography

#208

Post by dateSISC »

simonw wrote: post #11

Using coding agents to track down the root cause of bugs like this works really well: > Three out of three one-shot debugging hits with no help is extremely impressive. Importantly, there is no need to trust the LLM or review its output when its job is just saving me an hour or two by telling me where the bug is, for me to reason about it and fix it. The approach described here could also be a good way for LLM-skepti…

whose

Re: Claude Code can debug low-level cryptography

#209

Post by heavyset_go »

embedding-shape wrote: post #183
heavyset_go wrote: post #140

Earlier quoted context omitted.

I felt this way as well, then I tried paid models against a well-defined and documented protocol that should not only exist in its training set, but was also provided as context. There wasn't a model that wouldn't hallucinate small, but important, details. Status codes, methods, data types, you name it, it would make something up in ways that forced you to cross reference the documentation anyway. Even worse, the mod…

> the fact that I'm being confidently lied to by a damn computer on a regular basis Many of us who grew up being young and naive on the internet in the 90s/early 00s, kind of learnt not to trust what strangers tell us on the internet. I'm pretty my first "Press ALT+F4 to enter noclip" from a multiplayer lobby set me up to be able to deal with LLMs effectively, because it's the same as if someone on HN writes about so…

This is more like being trolled by your microwave by having it replace your meals with scuba gear randomly.

Re: Claude Code can debug low-level cryptography

#210

Post by Razengan »

simonw wrote: post #191
Razengan wrote: post #186

Earlier quoted context omitted.

I used the Claude website and Mac desktop app for a relatively standard iOS SwiftUI project. I used Claude Code with VS Code for some Godot stuff, and even there it sometimes gave outdated and outright made-up APIs (functions that seemed like they should exist but did not etc.)

Unfortunately LLMs mostly suck at Swift and SwiftUI from what I've heard - they still change pretty often and as a result there aren't enough fresh examples in the training data. As primarily a Python/JavaScript programmer I don't have that problem!

They're terrible at anything new, including knowing about THEMSELVES and their latest versions.

This is me asking ChatGPT 5 about ChatGPT 5: https://i.imgur.com/aT8C3qs.png

Asking about Nintendo Switch 2: https://i.imgur.com/OqmB9jG.png

This could be solved and LLMs could be a lot more useful if they could be a wrapper around live web search: Just search for this shit, scrap the top few results, and summarize the info to me.

But that's a stillborn dream, crippled because Google won't let 3rd-party AIs use their search willy nilly and websites don't want to be scrapped :(

Don't get me wrong: I see the potential in AIs/LLMs and I think they could be amazing for everything, but like every awesome thing, they're hampered by corporate (and government) idiocy.

Post reply on HN