# Ask HN：你在使用生成式人工智能时，有哪些让你惊呼"天啊"的时刻？

- 来源：Hacker News 热门（buzzing.cc 中文翻译）
- 作者：andrehacker
- 发布时间：2026-06-06 07:23
- AIHOT 分数：34
- AIHOT 链接：https://aihot.virxact.com/items/cmq1kw9kg0gq5sltrj29hxfq3
- 原文链接：https://news.ycombinator.com/item?id=48406174

## AI 摘要

Hacker News 上一条“Ask HN”帖子向用户征集使用生成式人工智能（GenAI）时令人惊呼“天啊”的震撼时刻，该帖于 6 月 5 日发布，获得 105 个点赞。

## 正文

Hacker Newsnew | past | comments | ask | show | jobs | submitloginAsk HN: What was your "oh shit" moment with GenAI?737 points by andrehacker 9 days ago | hide | past | favorite | 1122 commentsMost of us were amused when DALL-E and its peers went mainstream, and we were quick to point out the obvious flaws.Then ChatGPT hit the scene and again, many of us dismissed it as a parlor trick that would never amount to much.Using LLMs for coding initially was a only small step up from basic code completion, and a welcome farewell to Stack Overflow.I am curious: what was the specific moment that you went from those quaint, dismissive observations to a slightly panicked, "Uh Oh" realization of what these models can do? jzemeocala 8 days ago | next [–] I bought an Alesis QS8.1 super cheap in perfect condition (was a top grade digital piano/synth in the 90s).and then i realized that ALL of the software (which i collected from defunct websites and archived on github) related to it was ancient and after a while of getting tired of using WINE every single time i decided i wanted a cross platform modern equivalent that did everything that several of these different programs did (plus break out some stuff that was now potentially possible with modern computer)i thought it would be extremely hard because the computer to synth communication is pretty much only via sysex commands (of which the actual wave file encoding protocol was undocumented)Claude walked me through examining the some of the original software in GHIDRA, and I had a working demo that night.....now im just playing with adding new features to it.replyjsharf 8 days ago | parent | next [–] Related story, while applying a firmware update to my Kawai CA49 piano, I bricked it due to flashing the wrong file (The process was broken, and I got desperate and tried something stupid, which bricked the piano). Claude walked me through looking for signs of life, and since OTA from the phone app wasn't working for me, it downloaded the Kawai Android APK, decompiled the Java, figured out the hardcoded key used for encrypting the firmware update. Extracted the piano firmware update, decrypted it, and then wrote a flashing script to program the piano from my laptop via bluetooth. My piano was back to working within an hour.replyidiotsecant 8 days ago | root | parent | next [–] I can't imagine where we are headed. You understand every step of what it did and can appreciate the complexity but it'll only take a few generations for this to become something like magic to the tech priests beseeching the machine spirits for blessingsreplyfasterik 7 days ago | root | parent | next [–] I think you're overestimating how much the average person knows about how technology operates today, or 30 years ago, or 1000. In some sense, we have been living with magic and tech priests since the Romans built the aqueducts. I wouldn't be surprised if widespread, cheap AI makes it easier for the average person to learn how things around them work, if they are so inclined.replylazyasciiart 7 days ago | root | parent | next [–] I meet kids today who haven’t heard of Microsoft, who regularly play GTA and hand in assignments made in Powerpoint. 20 years ago I discovered that a friend didn’t know Xbox and Word were both from Microsoft. It’s really hard to understand what is common knowledge in different parts of society.replyForHackernews 7 days ago | root | parent | next [–] Indeed. You'd be shocked how few people on Hacker News even know the difference between cross stitch and blackwork.replyoblio 7 days ago | root | parent | next [–] https://xkcd.com/2501/reply2muchcoffeeman 7 days ago | root | parent | prev | next [–] Those are just products who cares?I think the GP is alluding to understanding the fundamental way a thing works.replyBobbyTables2 7 days ago | root | parent | prev | next [–] Kids today don’t even know where the files are stored or anything about partitions, drives, directory structure or even how much disk space is available.They have some files, synced to OneDrive and do everything else fully online (Canva, etc.)Most of them have never seen a computer with a drive other than C:replyidiotsecant 7 days ago | root | parent | next [–] Kids today don't even know the most basic x86 assembly instructions! A whole class of third graders, and not one of them could tell me the difference between MOV and LEA!!!! Can you believe it?!?!replydotancohen 7 days ago | root | parent | next [–] Apt username.replyseanmcdirmid 7 days ago | root | parent | prev | next [–] My son has never seen a C: drive before. Heck, we got him a Macbook Neo a few weeks ago and I don’t think he has left more than a few coding apps since then. Thankfully he isn’t using AI yet.replylazyasciiart 5 days ago | root | parent | prev | next [–] Kids in college 20 years ago didn’t know that either. Some of them didn’t understand that they had a school email address.replyyamilg 1 day ago | root | parent | prev | next [–] To your point, we would think that just because we gained access to a vast mass of knowledge via web archives (such as Wikipedia), people would have become smarter overall, that no person with access to this would choose not to acquire the knowledge at hand. But here we are, surrounded by people who choose to stay ignorant. So, I imagine the same will happen with AI. The vast majority of people will keep using their chatbots and never in their lives will they solve their problems with these tools beyond asking general questions for troubleshooting.replythrowawaytea 7 days ago | root | parent | prev | next [–] I'm always shocked by the amount of people that have been looking and using refrigerators their whole life.... And have zero idea how it works.replydotancohen 7 days ago | root | parent | prev | next [–] > widespread, cheap AI makes it easier for the average person to learn how things around them work, if they are so inclined. It looks to me that the far more common use case will be to manipulate technology rather than understand it.The example with the synth is excellent. Today that kind of work demands somebody knowledgeable operate the AI harness. In short order, the AI may very well come up with the solution of looking online for example programs to decompile without the user even understanding what that means.replysubarctic 7 days ago | root | parent | prev | next [–] The point is, eventually not even experts will understand what it's doingreplythrowaway173738 8 days ago | root | parent | prev | next [–] If religion and human technology are any guide, there will be a lot of this but it will never be the entire sum of human activity. Some of us are just too damn curious. We go straight for the curtain. I refuse to believe that very human pattern won’t continue.replymrighele 7 days ago | root | parent | prev | next [–] "In the distant future, humans live in a computer-aided society and have forgotten the fundamentals of mathematics, including even the rudimentary skill of counting.The Terrestrial Federation is at war with Deneb, and the war is conducted by long-range weapons controlled by computers which are expensive and hard to replace. Myron Aub, a low grade Technician, discovers how to reverse-engineer the principles of pencil-and-paper arithmetic by studying the workings of ancient computers which were programmed by human beings, before bootstrapping became the norm—a development which is later dubbed "Graphitics"." [1][1] https://en.wikipedia.org/wiki/The_Feeling_of_Powerreplyaeon_ai 7 days ago | root | parent | next [–] I’m all for the sci-fi extremes that we might lose valuable skills to cognitive delegation, but the idea that we as a society will forget how to count is… extremely stupid.replyrnentjes 7 days ago | root | parent | next [–] To be fair, the average person already doesn't know how to do simple arithmetic.replyFlere-Imsaho 8 days ago | root | parent | prev | next [–] I'm not convinced that's where we are heading. LLMs are really good at explaining things ("explain to me like I'm a 5 year old").replyyen223 8 days ago | root | parent | next [–] A post that lives rent-free in my head points out that a kid who is addicted to chatgpt is going to be more literate - and therefore likely better educated - than a kid who is addicted to tiktokreplysitzkrieg 8 days ago | root | parent | next [5 more] and both saw the world through an inherited training/feed bias and censorship, hurray!replylazyasciiart 7 days ago | root | parent | next [–] Just like they always have. There’s a reason religion is mostly inherited.replyclaysmithr 7 days ago | root | parent | next [–] Everything a human knows has to be learnedreplyssl-3 7 days ago | root | parent | prev | next [–] Has there ever been a modern time when this wasn't the case?I mean: I can only go back so far, but I remember the 1980s well-enough. At that time, most of the new information that came into my brain from outside was sourced from public schools, newspapers, and the evening news on TV.None of these sources were particularly unfiltered, uncensored, or unbiased. It was always an abbreviated approximation of someone else's idea of the truth.replyseanmcdirmid 7 days ago | root | parent | next [–] Even in pre-modern times censorship was the norm. Heck, it wasn’t until the printing press was invented that the powers that be had to start doing it explicitly.replyzx8080 8 days ago | root | parent | prev | next [–] It's enough to make "explanation" a separate "educational" license to make it less broad used. Or disable it in some countries (this is happening already).replyFlere-Imsaho 7 days ago | root | parent | next [–] This is why locally running LLMs must be the future. We don't all need PHD level AIs to answer 99% of our queries, or to teach us a new thing. I'd encourage everyone to learn how to run and deploy local LLMs, even if they are not quite there yet in terms of performance.replyfivestones 7 days ago | root | parent | prev | next [–] Wait, really? Can you give specifics?replyzx8080 6 days ago | root | parent | next [–] Use VPN and try switching countries for yourself. Start from non-EU ones. You'll see.replyethbr1 8 days ago | root | parent | prev | next [–] There's a big difference between having something explained to you and developing expertise in it.I don't see an AI-as-explainer future where expertise isn't sacrificed en masse.Capitalism rarely supports a currently economically unproductive alternative for future good reasons.The recent AI tech layoffs are a warning sign that corporate leaders will happily shoot their company's (and the future's) expertise to pad next quarter's financials and trust in 90% correct, but much cheaper, AI.replyBeijinger 7 days ago | root | parent | next [–] "There's a big difference between having something explained to you and developing expertise in it."No, there isn't. You get things explained in University. Then you build on top of this knowledge.replyethbr1 5 days ago | root | parent | next [–] That's not at all how university works.You are explained things (least important part) and then you invest substantial amounts of time in practicing and exercising those new skills.Then, in your junior level jobs, the same cycle repeats.That exercise component isn't going to happen in university with AI in the loop, because AI will be able to shortcut basic practice.And it isn't going to happen in junior level work, because AI will be able to do those jobs more economically efficiently.See previous from HN fp for a more eloquent explanation: https://ergosphere.blog/posts/the-machines-are-fine/replybaq 8 days ago | root | parent | prev | next [–] Imagine someone in a position of power mandating that LLMs should not be good teachers.replyzx8080 8 days ago | root | parent | next [–] Some manager at LLM provider: "hey, we can sell 'education' ability as a separate product!".replybaq 8 days ago | root | parent | next [–] You jest, but I’m actually convinced education-tuned LLMs are (today) the only way education outcomes can actually improve in the AI era. As is, students are leveraging them for doing homework which makes homework useless, you want and economically need a model which can work as a 1:1 tutor with minimal supervision (and some hardware so lessons aren’t keyboard-driven).replyzx8080 8 days ago | root | parent | next [–] > and some hardware so lessons aren’t keyboard-driven).What's wrong with (screen-, probably) keyboard?replybaq 8 days ago | root | parent | next [–] Writing with a pen or pencil has better learning outcomes than with a keyboard for neurological reasons.https://pmc.ncbi.nlm.nih.gov/articles/PMC11943480/replyNonHyloMorph 7 days ago | root | parent | next [–] Most kids can't use a keyboard and never will. Their Apple Pencil scribbles don't seem to make them particularly smarter.Pen&pencil-> create something from (almost) nothing. Stylus input-> subpar slow interface for computation.Ipad data storage above par organisational help (no loosing lousy stuffed in bag paper).I kinda liked the AI to transpose handwritten/drawn notes into digitally orderable artifacts. Seen a couple Show HNs. Are there any advances in the field (preferably OSS or one time purchaseable as alternatively)(To add on to this: the utter physical imprecision of stylis pens is annoying. I can FEEL where a sharpt tip of a tool that is elongating my hand touches a surface and how it moves on a very fine scale/resolution. Probably not a problem for people who have not developed highly sensitive sensomotor perception because they grew up with a lot of flattness in there surrounding and not much plasticity, but: my god are these things clumsy. I always want to reach for a sharpener when i use an apple pencil lol.replyalchemism 6 days ago | root | parent | next [–] You can buy finer-tipped replacement caps for the mechanical pencil effect. Then there is the second problem: the texture of glass instead of paper.replywiether 8 days ago | root | parent | prev | next [–] I've been writing code since my teens, I've studied assembly... yet the fact that _things_ start happening when I press the power button on my computer are pure magic to me and I like it this way.I started digging a few times, but, I prefer the "magic".replyWillAdams 8 days ago | root | parent | next [–] I prefer at least a superficial understanding.Hopefully, there will never be a time when at least some folks are not reading books such as:https://www.goodreads.com/book/show/44882.Codereplyrnentjes 7 days ago | root | parent | prev | next [–] Keats blamed Newton for taken the magic out of the rainbow with a prism. Personally I think the magic only got greater.replyWJW 7 days ago | root | parent | prev | next [–] Eh. The only real things you need are:- On startup processing begins at a known address, and you put the bootloader code over there. Hardware engineers can guarantee this for you.- Every time you execute an assembly instruction, the program counter either explicitly jumps to a new location or else it just increments by 1. Hardware people can also make this happen as easily as implementing an adder.Don't get me wrong, there are LOTS of layers between the hardware and most "useful" programs any of us will ever write. But all of them are pretty understandable. They're often not very complicated, just tedious.replytonyarkles 7 days ago | root | parent | next [–] Similarly for making a basic CPU that implements the logic you’re describing. In 2006 or so I made a super simple microcontroller on an FPGA for a course project. It had a whopping 256 bytes of RAM, 1kB of ROM, and I think four 8-bit registers plus a 16-bit program counter. You could only jump +/- 256 bytes. It was largely useless but also incredibly satisfying.replyspacedcowboy 7 days ago | root | parent | prev | next [–] I'm genuinely puzzled by how you know enough about a system to even understand there is a basic assembly language, but still consider how "switching on" is 'pure magic'.Doesn't the one explain the other ? It may be turtles all the way down, but at some point there's a fundamental turtle - be it LEA or CMP ?replyidiotsecant 5 days ago | root | parent | next [–] There is an absolute gulf between knowing what assembly is and a functional computerreplyspacedcowboy 4 days ago | root | parent | next [–] Fair. I've just never come across someone who knows what assembly-language is, and who doesn't understand how a computer works. The journey of discovery is usually from the top-down, not the bottom-up.reply3dsnano 8 days ago | root | parent | prev | next [–] turtles all the way downreplypmcarlton 8 days ago | root | parent | prev | next [–] I think it will be just like Dr. Know in Spielberg's "AI" movie from 2001 — I found it amazing how the oracle, though giving mystic-sounding obfuscated answers, was actually intelligent enough to figure out (a) what the kid was asking for and (2) give the correct answer.replyjlaternman 7 days ago | root | parent | next [–] It is amazing how Dr. Know projects where AI is likely to go. And a Kubrick script, no less. Even the commercial overlap, where you pump in coins as the only way to get answers. Did it not also have ads? Truly prescient.replyLogicFailsMe 7 days ago | root | parent | prev | next [–] Honestly, don't think so. That's certainly the path one might extrapolate if the next generation grows up exactly the same way as the current generation, but that's not how it works.They will be exposed to this technology throughout childhood as their brains develop and they will develop unique ways to work with it we don't entirely understand just like GenY with cell phones and GenX with home computers. I think you deeply underestimate how adaptable we are as a species, but if you consider that we've been running the same OS and Bios as a species for the past ~40K years, perhaps you might be more optimistic?replyProcrastes 7 days ago | root | parent | next [–] As I recall, the Dr. knows were programmed to feed that information to runaway mechas who, who were, in turn, programmed to seek out the blue fairy.Probably a lesson in there somewhere.replyreactordev 7 days ago | root | parent | prev | next [–] Kids grew up on this man, they are master prompters. You’ll be asking them to fix your holoTV and your crypto phone when you’re too old to read the brainfuck.replyotabdeveloper4 8 days ago | root | parent | prev | next [–] Give it six more months and you'll have a second "oh shit" moment when you peek behind the curtain of LLMs shitting the bed.I guess tech unsavvy people who are easily amused by LLM tricks will always exist, but they'll be an increasingly smaller minority as time goes on.replyewalk153 8 days ago | root | parent | prev | next [–] This is truly remarkable. Congratulations!replyUptrenda 8 days ago | root | parent | prev | next [–] yeah thats mind blowing, nglreplyjazzyjackson 8 days ago | root | parent | prev | next [–] BallerreplyGalus 8 days ago | root | parent | prev | next [–] That's sick.replygyomu 8 days ago | parent | prev | next [–] Yes, those tools are extremely good at reverse engineering. With a bit of know how, it is now trivial to reverse engineer any protocol or crack any software, often in a matter of hours or less.A lot of people in the industry have vested interests in this not being discussed openly so you don't hear too much about it, but the implications are huge.replyj-conn 8 days ago | root | parent | next [–] What are some of the implications? Where does widely available mythos-level hacking lead? By people with a vested interest, do you mean non-cloud software vendors?replyaero142 8 days ago | root | parent | next [–] Software that had a data moat because it was hard to integrate with or migrate off of will have that moat disappear. A web site is a client now. Building data migration too for all of you competitors is easier now.replySyneRyder 8 days ago | root | parent | next [–] I've just had a SaaS that I use decide to implement a 2.4x price increase. I reacted instead by taking screenshots of every page of the SaaS, downloading their API docs, exporting what data I could, and asking Claude to build a self-hosted clone based just on those files. I had a read-only version of my entire data history completed in a single evening. Even at Opus API rates, it cost me less than half the price of a single annual seat.replygrepfru_it 8 days ago | root | parent | next [–] Heh and without api docs, just copy and paste the urls from network traffic and Claude will write a library for you.replyStanAngeloff 8 days ago | root | parent | prev | next [–] One of the many SaaS products we use at Day Job chose to gatekeep its MCP behind an enterprise plan. A brief Claude Code session later and a better, more feature-full MCP than the official was reverse-engineered from internal APIs by Opus.replyhyperman1 8 days ago | root | parent | prev | next [–] Right now, software is protected by the attacker not having enough competence. If that's over, the logical next step is using real encryption.E.g. a synth has a public key embedded. To change settings, you upload them to the vendor, who blesses them with their private key.Hacking such a synth requires either jailbreaking the synth, or the vendor losing their key . Both can be mitigated with tamper resistant hardware.We're well ahead on this path already, I assume AI will accellerate it. This is very bad news for the right to repair.replydarkwater 8 days ago | root | parent | next [–] But everything you described was basically a byproduct of incompetence somehow no? On both side. That's why the right to repair and how local HW should be treated when the online counterpart is EOLed by the manufacturer should be mandated by law. A law that stands on the side of the citizen, the end-user, obviously.replyhyperman1 8 days ago | root | parent | next [–] I would not describe it as incompetence, more as1) current encryption not available in the 1990's. These are the age of DES and weapon-grade vs commercial encryption. There was a legal cost blocking strong encryption.2) Manufacturers were not as strongly opposed to people touching the internals. After WW2, most people could fix anything, because survival depended on it. Even in the 60's radios etc. came with schematics, and building your own was normal and cost-effective. The shift happened in the '90s, with governements requiring licensing for everything, and mass manufacturing making repair less cost effective than buying a new one.Our current culture where only people blessed by the manufacturer are allowed to do anything is very recent.replyjustafewwords 8 days ago | root | parent | prev | next [–] (Reads:) "But, but...but... but everything... you described ...basically seem to be somehow a byproduct of incompetence...no"[trying-to-generate-random-making-sense-content]Let me gasps ask: The older six-fingers-"AI"-characters had learned an music-instrument by now, ander are much more capable of playing music you otherwise haddn't known or thought about..."?um What about those early shadowy boygroup, whom seem asian, no ? (-;[after-losing-entry-address-of-topic-question]But back to your trustworth-written text, Yes!regards,replyyonran 6 days ago | root | parent | prev | next [–] I think companies with valuable data to scrape (e.g. media companies) will eventually lock it behind APIs that verify Apple App Attest or Google Play Integrity. And deprecate websites which are easily scraped too. Then it will be useless to reverse engineer APIs used by apps and we will have to run the unmodified client on an unmodified OS.replyls612 7 days ago | root | parent | prev | next [–] It wouldn't surprise me if reverse engineering is put on the "highly unsafe" list in the near future in the same category as bio because of these interests. Can't have the cattle classes be able to control their own property now can we?replypixl97 7 days ago | root | parent | next [–] This is pretty much a given anyway. Making reverse engineering tools is already likely to get you sued by someone so model makers are apt to slow down the ability of their tools to reverse engineer to avoid the lawsuits themselves.replyls612 7 days ago | root | parent | next [–] Heh finally the impunity of the NSA is good for once. Good luck suing them over Ghidrareplyaizk 8 days ago | root | parent | prev | next [–] What do you mean? Everyone is talking about Mythos.replyfn-mote 8 days ago | root | parent | next [–] I think GP is talking about cracking, not pen testing.replytrumpdong 8 days ago | root | parent | next [–] Those are the same thing. They're talking about decompilation and protocol analysis.replybredren 7 days ago | root | parent | next [–] They're talking about patching Claude Code.replyElFitz 8 days ago | root | parent | prev | next [–] Some people even had some fun de-minifying JS and disassembling binaries. Successfully.replyNoMoreNicksLeft 8 days ago | parent | prev | next [–] >Claude walked me through examining the some of the original software in GHIDRA,I wanted to be able to decrypt the files on The Complete New Yorker magazine DVDs. The old software was WinXP only, and crashed by the time you turned to page 3 or 4. It walked me through using Ghidra on the relevant dll, mapped out how it was using Blowfish, what the credentials were that it was passing, and re-implemented all of that in a python script.Now all the files are in plain pdf.Right now, it's helping me write an extension to the mkv specification for embedded scripts and modify VLC to be conformant, so I can watch Black Mirror Bandersnatch. Already have a buggy implementation, about 3 days in.I've also had it add BEP 46 mutable torrent functionality to Transmission (and to some extent, to the WebTorrent library).These are all well beyond my abilities to do casually, and probably beyond my ability to do even if I spent the next 18 months doing nothing by grinding away at it.I only replied because I thought it curious that Claude apparently favors Ghidra.replymekael 8 days ago | root | parent | next [–] Interestingly enough, i’ve been sitting on a project for the last 12ish years where i just took the FMloader lib and used that from C# to turn the djvu files into pdfs. All that was needed was a decompiler and an hour of banging my head on it. I published some of the results a few years ago but need to go back and actually build out a full app.replyNoMoreNicksLeft 8 days ago | root | parent | next [–] I'm trying to not do the naive pdf creation, where each page is just the raster. Trying to keep the JBIG2 bilevel, as I get better quality at lower file size. Using jpeg2000 too, where appropriate, but the pdfs are still x2.5 the size of the original. Though, I can have it spit out decrypted djvu files that are exactly the same filesize... I just don't like that format for archival.If you want the Rolling Stone or Playboy archives decrypted, ReconSuave on github has tools to do those. I got tired of waiting for him to do The New Yorker though.replymekael 8 days ago | root | parent | next [–] Ive mainly been outputting them to high fidelity jpegs and then stuffing them into a cbz for portability. Works well went im reading on my ipad. As for the others i had them sorted out about a week or two after i decompiled the original binaries.I’ve definitely kicked myself a few times for not posting about them sooner, but the fear of pissing off CondeNast tempered my willingness to show offreplyNoMoreNicksLeft 8 days ago | root | parent | next [–] I don't think CondeNast cares.Do any of the cbz readers handle jpeg2000? It makes a big difference in filesize without any quality degradation. Like 40% smaller, maybe more in some cases. You should tinker with that if you have the time.replyfc417fc802 8 days ago | root | parent | next [–] Okular handles cbz that contain jxl with no issue. (IIUC both archive format and image format support is provided via a pluggable extension system but I don't recall the details because my setup has "just worked" for a very long time now.)Also FYI you can use mupdf to read cbz archives although I don't personally recommend it for that usecase.replypeterstjohn 8 days ago | root | parent | prev | next [–] Ooooh, you don't happen to have the code for the New Yorker decryption in a form you could send, do you? Or put up on github or even just give me the starting prompt…replypeterstjohn 7 days ago | root | parent | next [–] Okay, a couple of hours later…thanks for the hint as that's fucking dark magic ;) and I now have access to the entire New Yorker again after around 15 years :)replyNoMoreNicksLeft 7 days ago | root | parent | next [–] Since I think you'll find the one for Rolling Stone and Playboy, but not The New Yorker (I might be one of the few that has this or something like it)...https://gist.github.com/NoMoreNicksLeft/d3a4a59c7b4de0cdef1e...I'll have a more proper github repo at some point, but there are bugs I was working through. Some issues are bloated up ridiculously... a 9mb djvu file shouldn't become a 110mb pdf. Most issues will work well though. Hope it helps.replydarksim905 8 days ago | root | parent | prev | next [–] What was your setup for this and did you have any preferences set in Claude to get started with something like this?replyNoMoreNicksLeft 7 days ago | root | parent | next [–] I use Claude on the desktop, and only occasionally Claude Code. It's the one that recommended Ghidra. Walked me through the install. Taught me the basics (G to go to an address, etc). Would tell me where to go, and what to paste back to it. It eventually converged on where to find the iv and credentials and so forth (after acting confused for awhile), and then wrote the python script for me that decrypts. I'd like to think my questions (and challenges to its assertions) were intelligent enough to spur it towards the solution, but self-flattery is all that is.The dll in question was pretty obvious just from the filename alone that it was where the magic happened.If you want something similar, you might just start by asking it if it would be feasible to decompile the software in question to reverse engineer the decryption, that you'd heard Ghidra was a big deal. Keep nudging it to guide you along that sort of path.replynotagoodidea 8 days ago | parent | prev | next [–] I would be interested to learn a bit more on the how after reading also [0] and the worlk done on patching the Ableton Move firmware with the Schwung [1]. Slightly different but there is an increasing amount of work done on either old hardware and new one exploring patching, swapping or developing new firmware from scratch thanks to LLM/GenAI currently.[0] https://mforney.org/blog/2026-05-28-patching-my-guitar-amps-... [1] https://schwung.devreplytomduncalf 8 days ago | root | parent | next [–] Schwung is great. See also the recent new firmware for the Elektron Monomachine (old unsupported hardware) created using LLMsreplymattmanser 8 days ago | parent | prev | next [–] With stuff like this, do you honestly not feel that you've probably been tricked and that someone else actually did this?Don't get me wrong, I think AI can do some surprising things, but with stuff like this, often it just stole the code and the steps without attribution, it didn't figure it out.There'll probably be a blog post detailing exactly how to do this somewhere and Claude just copied the steps and code.And worse, Google search would have found it 10 years ago, but Google search today would claim there are no results?I think incredibly specific stuff like this often won't pass the 'did Claude just steal this?' test when you dig into it.replytonyarkles 7 days ago | root | parent | next [–] I appreciate where you’re coming from but no, I don’t believe so. I have had Claude do some incredible reverse engineering on very proprietary niche firmware blobs that aren’t generally available to the public. One of the really interesting reasons why I don’t believe that it’s simply regurgitation but rather iterative novel synthesis is because of the dead ends and blind alleys that led to success. It feels a lot more like “Claude has read every tutorial on Ghidra and Radare2, and has memorized the ARM architecture and datasheets for all of these microcontrollers”. Misidentifying, say, which subfamily of processors it is based on the IVT, only to course correct when I give it the VID/PID of the device booted into DFU mode.One piece of gear, Claude found a hidden and highly useful diagnostic screen. This took a few iterations too. It found the existence of it based on just running “strings” against the firmware image but needed a few rounds of me going “I tried what you suggested but this is what happened instead”. Searching Google, DuckDuckGo, and GitHub for any of the strings that were on that screen or any of the named constants associated with that screen in reverse engineered source led to exactly zero hits.More entertaining, Claude and I together also nailed down the source of a PTP synchronization bug in a piece of equipment a few months ago using the main UI .exe (written in pascal, of course), an ARM Linux image from the real-time controller in the box, and some pcaps from it interacting with other devices. The vendor released a patch a few days ago, without me having reported the bug.replyezconnect 8 days ago | root | parent | prev | next [–] It was probably done on a foreign language on an archived forum. Claude is the improvement of the internet search box.replyozim 7 days ago | root | parent | next [–] I take it….Improvement over all the assholes that tell you „just google it” after you spent two days hitting the wall.replyzellyn 8 days ago | parent | prev | next [–] I had that keyboard! I actually really like the piano-ish touch. I remember being sad though, when I realized they’d crammed all the sounds into I think 16MB (or was it 8?) and realizing how bad that was even by the late 90s! I think I still have mine in the garage somewhere… good times!replyclaytongulick 8 days ago | root | parent | next [–] I loved mine. Had it since the 90s, working perfectly.One day a few years ago my dad came by and was admiring it (it was a QS8) and asked to borrow it so he could play piano again.I, of course, said sure, but was feeling a little salty about it inside, because I wanted it to play, that's why I had it all set up.Anyway, about a year went by and I asked him about it to see if he was done with it.He said "oh that thing? I gave that away, was just taking up space"-.-replyrichardfey 8 days ago | root | parent | prev | next [–] You mean bad because they could have used a larger memory module and thus higher resolution sound samples?replyskhameneh 8 days ago | parent | prev | next [–] Hey so... mind sharing findings? I have a QS8 :)replyitomato 8 days ago | parent | prev | next [–] While not the "oh shit" moment, the wave has the same shape.I have an DigiTech GNX3000 effects pedal board - a digital modeling "workstation" that needs the aged Windows native software or Gdigi to make the most of.At best, the experience with gdigi was passable; raw access to the patches and controls, the ability to control it from the laptop, etc.In an hour or so, I had a functionally superior webmidi version up and running in Vercel using their v0 code. It kicked off a wave of subscriptions and referral chasing.I made it a template - because there are so many gnx3k users out there: https://v0.app/templates/digitech-gnx3000-sysex-tool-GC5LzXA...replydjmips 8 days ago | parent | prev | next [–] That's fantastic. Did you use a Ghidra MCP server? It's kind of magical huh?replyalright2565 8 days ago | root | parent | next [–] I've done a similar sort of thing with my camera lens' firmware updater just out of curiosity, and I didn't use any kind of MCP. It's able to write an automated script using the Ghirda API to decompile the program just fine, and then code exploration can be done by reading the code.Claude needs good variable names a lot less than humans do, so renaming/typedefing doesn't seem to be as necessary.replyshreddude 8 days ago | prev | next [–] I could go on and on, but Claude recently decompiled the firmware of my camper van, documented all the CAN interfaces, then programmed an ESP32 module to talk to the van’s integrated systems (power, HVAC, lighting, tanks). That sort of embedded systems integration is completely out of my wheelhouse.I honestly don’t understand AI naysayers. I use Claude every day both professionally as a Solution Architect and personally in a variety of projects I simply could not have ever approached alone.replywilliamdclt 8 days ago | parent | next [–] > projects I simply could not have ever approached alone.I think that's part of the divide between enthusiasts and naysayers. If you use GenAI on things that you couldn't approach alone, it's an incredible tool. If you use it on stuff that you're pretty good at, it's not a gamechanger (and if you're an expert, it's a minor boost at best). Many people's job are about doing what they're an expert at.replypmontra 8 days ago | root | parent | next [–] I'm about to complete a new non trivial functionality in a project of a costumer of mine. I spent an hour writing the spec. Then I asked Claude (Sonnet 4.6) to check if I missed something. I did, the sort of minor issues one notice after starting writing code, edge cases etc. That made me think about more issues and after a few iterations we settled down on a spec. I asked Claude to make an implementation plan and we ended up with 9 steps. It wrote the code for a step with new automatic tests and I performed some manual QA, which found further issues we didn't think about. We are at step 8 of 9 in about 12 hours of work. I would have needed a week to be there alone, with time spent researching and fixing bugs I created along the way, an inevitable part of our job but not exactly the most pleasant one.This speedup is great. It improves the overall quality of the product (as perceived by the users) because I can ask Claude to add features that my customers and I would have dismissed because they take too long to implement. We would have settled down with a more basic UX.So is it a game changer? It is in the same way those HTML / CSS framework like Bootstrap were game changers: suddenly every developer could create a decent and consistent UI in a fraction of the time with a few bells and whistles that we wouldn't have bothered coding. As a side effect a lot of web apps felt look alike mass products and web designers had to reinvent themselves, but the economics leaded inevitably in that direction. Would I spend again one of two weeks doing alone what I could write in a day or two with a LLM? Not anymore, not at this cost ($20 per month.)replyjowsie 8 days ago | root | parent | next [–] I'd love to read a full transcript of someone going through this kind of collaborative programming. I see this kind of process mentioned a lot but can't quite figure out the details in my head. If anyone has a link to a blog post or similar showing this process in depth, I'd love to give it a read :)replytkocmathla 7 days ago | root | parent | next [–] I've been using superpowers [1] for this purpose, and have really appreciated how it guides the model to use careful, methodical approaches to answering my prompts. It's great for multi-step planning, design, and implementation, but also has guidance for debugging, accepting a code review, etc.[1] https://github.com/obra/superpowersreplyburnto 7 days ago | root | parent | next [–] Yeah I feel like I’ve learned a lot from superpowers. It’s such a thoughtfully developed skillset.replysntran 7 days ago | root | parent | prev | next [–] I think it will click once you actually sit down with the AI agent, toggle Plan mode, and just tell it what you want to do in couple of sentences. It will immediately start building up the plan, presenting it to you what it thinks is the right approach , with the steps to take, with open questions that you can look at and answers. Then send them back to the AI. Repeat. That process along would give you a progress way further than you try to do it by yourself.You can tell it to start implementing step 1. And you pick it up from there. Very natural how you would approach an expert for help, but you can always audit.replypmontra 7 days ago | root | parent | next [–] I did not use plan mode but I'll give it a try.I can't provide a transcript because it's work I made for a customer and I'm bound to a clause of confidentiality.What I did is what I use to do while starting to work on a major feature: make a list of changes, new and modified functionality, think which code and db tables I will touch and how, set constraints on the edits (eg: that API must not change, that one must be retro compatible) etc. I've been a bit pedantic because this time I had to tell it to someone else. I wrote it into a md file and asked Claude to check the code and find out if my plan was consistent with the code we were starting from. It made a list of things that I needed to detail more, added some questions and we iterated on it. Basically it's what I do myself but it happened faster.replymitjam 7 days ago | root | parent | prev | next [–] This Spec Driven Development Short course on DeepLearning by Paul Everitt is a nice 2-Hour walkthrough: https://www.deeplearning.ai/courses/spec-driven-development-...replynsvd2 8 days ago | root | parent | prev | next [–] Jon Gjengset has some live streams where he does agentic coding.replyPeterStuer 7 days ago | root | parent | prev | next [–] You describe almost exactly how I work, except I always use Opus with effort locked at max. Lots of detailed multi level planning, then coding the different planned steps, which it at that point just one shots, with a plan review and adaptation after each step.5x speedup and quality.replydahart 8 days ago | root | parent | prev | next [–] > If you use it on stuff that you’re pretty good at, it’s not a gamechanger (and if you’re an expert, it’s a minor boost at best).This was probably true last year, and it’s a common talking point, but I’ve seen too many examples now of deep experts using Claude & Codex in the last year to solve very big problems, and write or rewrite large systems. The experts do complain that the LLMs can sometimes get stuck or go off the rails and they need to pay attention and actively steer. But nobody I know who’s using it is still claiming the LLMs aren’t a game changer, even quite a few people who were staunch holdouts for a long time. I was skeptical myself, for a long time, but had my oh shit moment late last year.One caveat - to get expert results, you do need to have some experience using LLMs, you need to use it to write plans and design docs, know how to use ‘skills’ and MCPs, use it to review code, and (for now) you need to understand context compaction and when/why to use sub-agents. If you’re a domain expert but an AI noob, it’s less effective than an expert who knows how to use AI and has experience.One of the biggest problem with humans is we’re wired to spot patterns and draw conclusions and then we have a really hard time seeing and accepting change and updating our mental rules. The LLMs are getting better. They have already gotten better, and they’re going to continue getting better. It’s too early to draw conclusions, and many conclusions people have already declared are out of date and no longer true.replybawolff 8 days ago | root | parent | prev | next [–] I think part of it is we often notice bad AI usage. The llm generated "art" by someone with bad taste, or the patches to open source projects by people who cant program at all and are teerrible.If the use is half decent people just dont notice it.replytstrimple 8 days ago | root | parent | next [–] Anti-AI zealots (from a practical usability position. Not necessarily the moral ones) are like the people who looked at The Daily WTF and decided no humans are capable of programming. They had plenty of examples to point at, but refuse to look at decent to great programmers. The stories of "The AI deleted my database!" are prevalent and boosted by these folks because it confirms their biases. It literally doesn't matter if the LLM wrote strong warnings about the action about to be taken. They don't see that aspect of it. Just the fact that someone claims "The AI deleted my database!" is enough for them.Despite all the liars telling me gaming is easier on Linux than Windows, most new games have some sort of issues launching with default settings. CC is able to dive into both the exact error logs and the recent community feedback on what tweaks / configurations are needed to make it work. I rarely have to go beyond two prompts before a game is playable. CC and Proton are enabling the Linux gaming experience far more than Linus ever has or ever was interested in.replyFlere-Imsaho 8 days ago | root | parent | next [–] > Despite all the liars telling me gaming is easier on Linux than Windows, most new games have some sort of issues launching with default settings. CC is able to dive into both the exact error logs and the recent community feedback on what tweaks / configurations are needed to make it work. I rarely have to go beyond two prompts before a game is playable. CC and Proton are enabling the Linux gaming experience far more than Linus ever has or ever was interested in.Heh - I've just gone through a similar journey transitioning from Windows to Bazzite to play Steam games on Linux. I wouldn't have bothered pre-LLMs because my day job is Linux/Software and the thought of trying to fix issues here just to play games put me off.replyOJFord 7 days ago | root | parent | prev | next [–] Imo it's still great for areas you have expertise in, because it's a tool for automating the boring, repetitive, or time-consuming bits that you can then expert-verify.I'd rather review & tweak generated test cases than write a load of boilerplate, test setup, etc. myself.replyLouisSayers 8 days ago | root | parent | prev | next [–] I find it's a huge boost for my day-to-day work.If you work on architecture and Claude docs, then you can essentially just have it fill in the gaps. Work then mostly becomes a matter of defining what the next piece of functionality is (which you can also use Claude to help with).The stuff that used to take days now takes hours. It's not perfect, but if you get your codebase into a good shape then the payoff is huge.replymattmanser 8 days ago | root | parent | next [–] I re-read something I did 6 months ago doing this.It's so obviously AI and had much less value than I thought now I look at it with fresh eyes.Worse it doesn't read like I wrote it, I don't recognize myself in the doc.replyjorl17 8 days ago | root | parent | prev | next [–] While I think this is true> If you use GenAI on things that you couldn't approach alone, it's an incredible tool.I think this isn't true in all cases> If you use it on stuff that you're pretty good at, it's not a gamechanger (and if you're an expert, it's a minor boost at best).I think even then there's a divide.I mostly work greenfield projects (and love it!). For these, AI has been a literal game changer. Our projects are built faster, with one or two orders of magnitude more automated tests, and all quality metrics are up.Meanwhile, nearly all of my friends complain that AI doesn't help them. But they mostly work in very large existing codebases.Still, even in large projects I think AI (the expensive variant) has been a complete gamechanger for me. Sure, I spend a lot on tokens, but I just feel happier and enjoy what I do more. The singalong people say about "thinking at a higher abstraction level" is what I feel. I really am thinking about architecture and larger patterns, instead of the boring nitty-gritty (which wasn't boring at all when I was a kid learning to code!...)I think a key factor in all of this, to me, has been dictation. Most of the time, I don't write -- I use voice-to-text. I don't even read what comes out of it -- the LLMs get it (it is mostly unintelligible to anyone else) .This means when I'm planning a big feature, I give a gigantic brain dump to the LLM in perfect stream of consciousness way, going through ideas, pros and cons, edge cases, what exists, what doesn't exist, where I'm sure of something, where I'm not sure and want the LLM to browse the state-of-the-art. Sometimes I spend 20 minutes just talking to the microphone before I send the first prompt. When I pair that with Opus, I find that I am able to build much faster and to go through alternative designs much more frequently as well.I keep trying to tell all my friends: use voice to text and braindump to the computer. But they refuse... I couldn't imagine having to type everything nowadays. Even though I'm a fast typer, it's still much slower than the speed of my thought, which, granted, is still faster than the speed of my voice.In effect, I filter much less, but I've come to think that's positive for the good LLMs: I throw all the edge cases and what ifs I'm thinking about -- all those years of experience dealing with similar systems.If I wanted to go back to work in-office, that would be my major problem: I need to be able to talk with my computer all the time, loudly, and pacing through my room.replybthallplz 8 days ago | root | parent | next [–] Yay for dictation! It's so nice to just think aloud and then have an easily editable record of your thoughts, even when you aren't feeding the outputs to LLMs.reply400thecat 8 days ago | root | parent | prev | next [–] How do you use voice-to-text? You mean, in the browser? I am only familiar with Claude Code, which I have installed on remote server, and there obviously, voice-to-text does not work. I have to type, which is tiring.replybigfudge 8 days ago | root | parent | next [–] I’ve installed Hex on os x. You just hold down a

> 正文较长，站内仅导出已展示部分；完整内容请阅读原文。