I have a similar claude story (much less money though), with the IRS R&D tax credit. The auditing firm initially said we qualify for $0. But then I had claude analyze past R&D reports and our expenses and it found the problem. The auditor had miscategorized our company.
So claude drafted an email even pointing to the right Internal Revenue Code (IRS Law), and specify why we fall under a specific category. The auditor got back to me two days later admitting their mistake and said our company now qualifies for $8k in tax credits. And a few months ago, it identified items in our AWS that saved us $250 a month (paying for itself).
So now I joke that even if I have a claude max plan, I've still come out ahead financially.
To be fair regarding taxes it should be that you get all exemptions by default and the other side telling/justifying you why you don't qualify, instead of you not getting the things you should because you're not sure how to interpret the law or don't know this or that rule exists. Taxes shouldn't be that difficult, and the US version of it seems to be behind even the one I have here in europe (where my taxes are done "for me" for anything non business owner related). If the government is calculating your taxes anyway, they should just give the number to you instead of asking you a number and you better have the same as us or you're guilty of something.
Feels like a system that is deliberatly made to be more punishing for those who can't afford the help or the education to figure things out.
I use AI to help me do my accounting (how to categorize and account for things). It pays for itself because I need to spend money for far fewer hours from an accounting firm each month to make sure that captialized expenses, depreciation, tax credits (we have Historical Tax Credits from restoring an 1880s building) etc, is put in the books properly. The AI gets it right a high enough percentage of the time that I only the to have a real accountant look at things once a quarter to make sure it's all OK. I used to have a dozen questions every month.
Claude Code is really good at stuff like this. The other day I tried to recover some images from an SD card that had gone bad. I used GetDataBack to recover files, but they appeared to be malformed and didn't open in image viewers.
I tasked Claude to analyze the files and figure out what's going on, and eventually we figured out that each file had a custom metadata header + thumbnail + actual image concatenated. I had it write a python script and was able to recover all the images with their metadata. It's nothing a human couldn't have figured out, but it was definitely WAY faster than doing it myself.
I've also used Claude in the past to figure out how to break into routers with locked down firmware. It's great at suggesting and trying different approaches.
I have a friend that just picked up a new consulting job resurrecting an ancient Windows desktop application. No source control, no tests. And it's spread out over a dozen different folders with names like "_old", "_new" and "dates". Claude's doing a tremendous job in getting him to grips with what is actually happening in the application, what's relevant, what's not, what's different. I think it's literally saving him days and days at work.
I did EXACTLY that last night. Was doing by hand for about an hour and got to a point where I didn’t feel competent anymore and asked Claude to take from where I was.
5 minutes later I had almost 3 hours of important footage recovered.
I'm sure data recovery companies are pretty pissed that slightly esoteric data recovery abilities are becoming more accessible for average software devs. They were charging an arm and a leg to remote in and run scripts.
A lot of "Claude Code is best at X" claims are probably user-selection bias.
The people saying it are often exclusively Claude Code users, not people who are actively benchmarking Claude Code against Gemini CLI, OpenAI Codex, GitHub Copilot, and other agent harnesses on the same tasks.
The claim may still be true for certain scenarios, but the evidence is usually anecdotal, not comparative.
> Bitcoin trader recovers $400,000 using Claude AI after getting 'stoned' and losing wallet password 11 years ago — bot tried 3.5 trillion passwords before decrypting an old wallet backup
Man. I wish I had a lost wallet worth a quarter of that even, technically didn't need Claude for this, just needed any password cracking software.
Explaining your life to an llm, then having it generate permutations of passwords to try does sound like it would work a decent percentage of the time.
A large percentage of passwords aren't a random string of characters but a memorable word + memorable number. There's existing projects that basically do the same, and 3.5 trillion doesn't really make it clear if one of those wouldn't have worked as well, but I can see it having an above random chance to guess a password.
I had a high school friend that died about 10 years ago from an over dose. He was always tech forward and had talked in the past about getting drugs from the dark web to sell locally.
I wasn't particularly close with him after high school, but he was an only child, and I can only imagine his (older) parents just tossed his computer. I wouldn't be surprised if he had had a few hundred BTC on there.
I have a lost wallet with about 300 Bitcoin sitting in a landfill somewhere. I tried out Bitcoin really early on and mined those over a few weeks. But they were worthless back then and I was burning electricity for "nothing" so I stopped. This was before that 10k Bitcoin pizza purchase happened. I have some regrets lol.
Someone gifted me 87 bitcoins back when they were worth ~0. They are still in some wallet somewhere I guess, and I saved the password on a harddrive I threw out around the same time
I was making a long edit in a crappy wiki UI and my browser froze. It would have taken a long time to redo, hours.
I didn't want to take the chance of force closing and losing everything. I used claude code to extract my text out of the browser internals and filesystem objects.
Many crypto wallets use a key derivation function (KDF) to add an amount of computation (and memory usage) per password tried - to mitigate brute force of weak passwords.
The increase in compute (decrease in brute-force cost) combined with price increases in many crypto tokens means brute-forcing old wallets can become worth it years after passwords were forgotten.
And of course even smaller, local AI models can now easily write optimized scripts to brute-force any given KDF function.
One can't help but observe the contrast between counterparty behavior here vs. the crypto boom. A counterparty service had a secret worth 400K in-hand and just passed it back to the user. Meanwhile crypto worries about MEV, the Dark Forest, etc.
This cycle is hostile in lots of ways, but the trustworthiness and absence of hostility in this dimension is quite nice.
A wallet is just private keys of some specific public keys on the blockchain that have unspent output (UTXO). None of what’s described in this article involves the blockchain, only the storage and protection of the private keys on a local computer.
You can imagine that in your example, you didn’t change the locks on a house, but rather you put the house keys in a secure lock box and you changed the locks on this box.
Changing the locks on a house in this case means transferring from an old wallet to a new wallet and then abandoning the old wallet. That’s exactly what the OP is trying to do. It’s just that you need the original key to do it.
Kind of cool to hear... I had a couple computers running miners at home towards the end of my second marriage (which ended in 2010-2011), and after I had a few coins when realizing I couldn't actually spend them (IIRC $0.25 at the time), I just deleted the wallets. I had no foresight or faith that they'd be worth around $100k each in 15 years. I'm curious how many did the same, how many coins out there were just deleted altogether.
i distinctly remember a coworker many years ago offering to just give me like 10 bitcoin to see them and how it worked. i said "no, thanks". granted, hindsight is 20/20
The other day, I asked Claude to track down the leaked Claude Code source so I could study it. It refused, saying “given who made me, I’ll pass.” It gave me some pointers on how to find it myself, which worked.
There isn’t that much of a difference between “help me crack this bitcoin wallet” and “help me crack this executable.”
I don’t exactly have a solid point, just some general observations. First, I think we’ll see AI more and more simply refuse to do any kind of forensics, as forensics becomes more powerful. Second, that implies local models will become more valuable, since they’re the only ones willing to do that kind of work.
I once got myself banned from Claude by researching barbiturates, since they’re connected with suicide. So my third observation is that we’ll see an uptick in people getting punished for trying to do things with AI that people don’t usually do. (Luckily the unban form worked.)
Someone downthread asked “how’d he convince Claude the coins weren’t stolen?” Which is an interesting question, because presumably some people trying to crack a wallet have stolen it. So I guess the fourth observation is that the exact framing you approach an AI with will become more important. There was the classic “do this or I’ll cut off my arm,” which worked a year ago. But in the future it will be more like “hopefully the AI believes my story, or else I’ll get into trouble.”
It’s good there are multiple AI vendors, or else it’d get real dystopian real fast when the de facto AI’s policy becomes something you have no way of working around.
I spent a couple of days mining many years ago and got 2 bitcoins. At the time, they weren't worth the electricity they cost to mine and over time I lost the wallet and all information related to it.
>they weren't worth the electricity they cost to mine...I'd love to mine a bitcoin a day on my PC now...
you can!... but they wouldn't be worth the electricity now either. the cost of mining (amortization of hardware costs plus electricty) is the value of bitcoin. if bitcoins are a bargain to mine, more people will mine them thereby reducing rewards.
should you have mined more back then if you had magical perfect knowledge of the future? no: they weren't worth the electricity.
instead you should have bought more of them back then.
Feels less like "ai cracked crypto" and more like having an insanely patient technical friend sitting next to you for 12 hours doing digital archaeology.
Claude found a file on the computer that the wallet owner had not found. Claude didn't crack a password or do anything magic, it just searched for a file that the wallet owner had not thought to search for before.
So, where the wallet owner had previously only tried to access /Users/example/wallet.dat, Claude thought, "why don't I check if there is another wallet.dat file elsewhere on the system?" which it did.
The outcome is the same, it is great that Claude tried something that the wallet owner hadn't tried, but this is more an example of how dumb humans can be rather than how smart Claude is.
The trillions of passwords are a red herring and unrelated to the solve.
Yesterday I had ChatGPT walk me through fixing my single-node k3s cluster. It required rebuilding the sqlite database (while skipping a few corrupted records), then clearing the containerd cache, and then finally deleting a somehow-corrupted Secret record, and then recreating it.
Without it I would have given up way earlier, but the infinite patience to keep slurping in error messages and continue to troubleshoot really worked out.
Yeah Claude is really, really good there. You tell it the distro and the problem and it will solve it. Saved me a lot of pain when it came to swapping out an encrypted boot drive and was good about emphasizing the order of operations required for what I would consider a higher risk/complexity situation.
> bot tried 3.5 trillion passwords before decrypting an old wallet backup
> After finding a mnemonic that actually turned out to be their old password a few weeks ago, the user dumped their entire college computer files in Claude in a last-gasp effort. The bot uncovered an old backup wallet file that it successfully decrypted, while also uncovering a bug in the password configuration that was preventing recovery up to that point.
So it switched from brute-force searching passwords against a file, to brute-force searching files against a password?
So you’re telling me he used a computer to search all the files and found the old backup? computer file systems are truly proving to be revolutionary technology!
On a purely technical level - cool. But I still cannot get over the impression that even in this case LLMs show us how they are mainly useful to grifters. I mean, 5 Bitcoins worth 400K USD. Why? What intrinsic value does Bitcoin deliver? It's like trading for monopoly money.
Claude found an old wallet and then ran btcrecover on that. The question is why the user could not find an old wallet with any numbers of Unix tools himself.
Since we are dealing with Anthropic, the entire story could be staged of course.
"the user dumped their entire college computer files in Claude in a last-gasp effort."
Claude has limits that would make this simple statement be much more complicated-
Via Claude "So the chat upload file size limit is actually 500MB per file (not 30MB as many third-party sources claim - those appear to be outdated). The 20-file-per-chat cap and the 30MB-per-file limit in Projects remain consistent across plans.
The real constraint at any subscription level remains the context window - how many tokens Claude can hold in memory at once during a conversation. "
10 years ago a 500mb hard drive was not unheard of and he may not have maxed out his storage. Also, cloud storage is more prevalent now.
I must admit this does sound a bit sensational.
“ Out of frustration, cprkrn then dumped their whole college computer into Claude. This was when the AI discovered an older backup file of the wallet from December 2019 hidden in cprkrn's data.”
… this dweeb had a file containing their seed in their backup, claude just searched through the files
I've tried Claude Code with another LLM, it's very good at doing tasks and figuring things out. So this made me wonder, even though we know how good Claude models is, maybe the true value is in the harness now?
I have a similar claude story (much less money though), with the IRS R&D tax credit. The auditing firm initially said we qualify for $0. But then I had claude analyze past R&D reports and our expenses and it found the problem. The auditor had miscategorized our company.
So claude drafted an email even pointing to the right Internal Revenue Code (IRS Law), and specify why we fall under a specific category. The auditor got back to me two days later admitting their mistake and said our company now qualifies for $8k in tax credits. And a few months ago, it identified items in our AWS that saved us $250 a month (paying for itself).
So now I joke that even if I have a claude max plan, I've still come out ahead financially.
> So now I joke that even if I have a claude max plan, I've still come out ahead financially.
This is no joke; for better or worse, I see a day when I'm paying a lot more for this and it will be a bargain.
To be fair regarding taxes it should be that you get all exemptions by default and the other side telling/justifying you why you don't qualify, instead of you not getting the things you should because you're not sure how to interpret the law or don't know this or that rule exists. Taxes shouldn't be that difficult, and the US version of it seems to be behind even the one I have here in europe (where my taxes are done "for me" for anything non business owner related). If the government is calculating your taxes anyway, they should just give the number to you instead of asking you a number and you better have the same as us or you're guilty of something.
Feels like a system that is deliberatly made to be more punishing for those who can't afford the help or the education to figure things out.
I use AI to help me do my accounting (how to categorize and account for things). It pays for itself because I need to spend money for far fewer hours from an accounting firm each month to make sure that captialized expenses, depreciation, tax credits (we have Historical Tax Credits from restoring an 1880s building) etc, is put in the books properly. The AI gets it right a high enough percentage of the time that I only the to have a real accountant look at things once a quarter to make sure it's all OK. I used to have a dozen questions every month.
Same... I had chatgpt go over my taxes (I do it myself) and it found a number of savings I qualified for
Claude Code is really good at stuff like this. The other day I tried to recover some images from an SD card that had gone bad. I used GetDataBack to recover files, but they appeared to be malformed and didn't open in image viewers.
I tasked Claude to analyze the files and figure out what's going on, and eventually we figured out that each file had a custom metadata header + thumbnail + actual image concatenated. I had it write a python script and was able to recover all the images with their metadata. It's nothing a human couldn't have figured out, but it was definitely WAY faster than doing it myself.
I've also used Claude in the past to figure out how to break into routers with locked down firmware. It's great at suggesting and trying different approaches.
I have a friend that just picked up a new consulting job resurrecting an ancient Windows desktop application. No source control, no tests. And it's spread out over a dozen different folders with names like "_old", "_new" and "dates". Claude's doing a tremendous job in getting him to grips with what is actually happening in the application, what's relevant, what's not, what's different. I think it's literally saving him days and days at work.
I did EXACTLY that last night. Was doing by hand for about an hour and got to a point where I didn’t feel competent anymore and asked Claude to take from where I was.
5 minutes later I had almost 3 hours of important footage recovered.
I'm sure data recovery companies are pretty pissed that slightly esoteric data recovery abilities are becoming more accessible for average software devs. They were charging an arm and a leg to remote in and run scripts.
> Claude Code is really good at stuff like this.
A lot of "Claude Code is best at X" claims are probably user-selection bias.
The people saying it are often exclusively Claude Code users, not people who are actively benchmarking Claude Code against Gemini CLI, OpenAI Codex, GitHub Copilot, and other agent harnesses on the same tasks.
The claim may still be true for certain scenarios, but the evidence is usually anecdotal, not comparative.
> Their luck changed for the better when they found an old mnemonic seed phrase written in an old college notebook
TBF the real breakthrough was finding this, though no doubt they couldn't have recovered without Claude
Pretty much every AI win story feels like this.
The guy also had to plug in an old hard drive for Claude to search. Sounds like he had an idea the wallet was on there to begin with.
I bet the majority of people reading this really think Claude cracked the encryption.
> Bitcoin trader recovers $400,000 using Claude AI after getting 'stoned' and losing wallet password 11 years ago — bot tried 3.5 trillion passwords before decrypting an old wallet backup
Man. I wish I had a lost wallet worth a quarter of that even, technically didn't need Claude for this, just needed any password cracking software.
Explaining your life to an llm, then having it generate permutations of passwords to try does sound like it would work a decent percentage of the time.
A large percentage of passwords aren't a random string of characters but a memorable word + memorable number. There's existing projects that basically do the same, and 3.5 trillion doesn't really make it clear if one of those wouldn't have worked as well, but I can see it having an above random chance to guess a password.
I had a high school friend that died about 10 years ago from an over dose. He was always tech forward and had talked in the past about getting drugs from the dark web to sell locally.
I wasn't particularly close with him after high school, but he was an only child, and I can only imagine his (older) parents just tossed his computer. I wouldn't be surprised if he had had a few hundred BTC on there.
I have a lost wallet with about 300 Bitcoin sitting in a landfill somewhere. I tried out Bitcoin really early on and mined those over a few weeks. But they were worthless back then and I was burning electricity for "nothing" so I stopped. This was before that 10k Bitcoin pizza purchase happened. I have some regrets lol.
Someone gifted me 87 bitcoins back when they were worth ~0. They are still in some wallet somewhere I guess, and I saved the password on a harddrive I threw out around the same time
> …recovers $400,000 using Claude AI after getting 'stoned' and losing wallet password 11 years ago
I had to laugh: the most Bitcoin story ever.
I'm really thankful I put my bitcoin in a time vault back in 2012 or so. It was inaccessible until about last year, and my $10 is now worth $100k.
Thank you MtGox.
If he was stoned, he would have probably spent his three bitcoins on pizza anyway.
The first pizza anybody bought that way cost 10,000 bitcoin, over $billion.
I was making a long edit in a crappy wiki UI and my browser froze. It would have taken a long time to redo, hours.
I didn't want to take the chance of force closing and losing everything. I used claude code to extract my text out of the browser internals and filesystem objects.
I did this a long time ago before the age of AI. Core dump and then run strings on it. Very low tech but very useful!
How do you use Claude Code to access your browser memory?
Still, they didn’t give up because that wallet contained 5 BTC; this may not sound much, but it has a value of almost $400,000.
They are really underestimating their audiance here.
They are not though, because this audience is apparently eager to gobble up fake clickbait.
Many crypto wallets use a key derivation function (KDF) to add an amount of computation (and memory usage) per password tried - to mitigate brute force of weak passwords.
The increase in compute (decrease in brute-force cost) combined with price increases in many crypto tokens means brute-forcing old wallets can become worth it years after passwords were forgotten.
And of course even smaller, local AI models can now easily write optimized scripts to brute-force any given KDF function.
how can that possibly work while supporting offline backup & restore?
One can't help but observe the contrast between counterparty behavior here vs. the crypto boom. A counterparty service had a secret worth 400K in-hand and just passed it back to the user. Meanwhile crypto worries about MEV, the Dark Forest, etc.
This cycle is hostile in lots of ways, but the trustworthiness and absence of hostility in this dimension is quite nice.
I'm no expert but using an old wallet with a changed password, and it working, seems like a major security design flaw.
In the physical world, I can't imagine too many people being happy that old keys to your house still work even after you've changed the locks.
Can someone more informed, help me understand how this worked and why it's ok.
I'm genuinely wanting to become more informed & better understand.
A wallet is just private keys of some specific public keys on the blockchain that have unspent output (UTXO). None of what’s described in this article involves the blockchain, only the storage and protection of the private keys on a local computer.
You can imagine that in your example, you didn’t change the locks on a house, but rather you put the house keys in a secure lock box and you changed the locks on this box.
Changing the locks on a house in this case means transferring from an old wallet to a new wallet and then abandoning the old wallet. That’s exactly what the OP is trying to do. It’s just that you need the original key to do it.
They didn't lose the key, they just didn't know which one is the correct one, where the lock is, and how the unlocking is done.
The wallet is akin to a lockbox holding your keys to the house. Breaking into the lockbox and changing it's lock does not affect the keys kept inside.
This sounds like an Ad, why would you tell the world about this? Too coincidential.
claude ads hot off the presses.
The amount of pure conspiratorial thinking will never cease to amaze me.
Lol great intersection of AI, Crypto and blind luck.
By getting stoned he was forced to hold until AI could solve his problem at a crypto high.
Kind of cool to hear... I had a couple computers running miners at home towards the end of my second marriage (which ended in 2010-2011), and after I had a few coins when realizing I couldn't actually spend them (IIRC $0.25 at the time), I just deleted the wallets. I had no foresight or faith that they'd be worth around $100k each in 15 years. I'm curious how many did the same, how many coins out there were just deleted altogether.
i distinctly remember a coworker many years ago offering to just give me like 10 bitcoin to see them and how it worked. i said "no, thanks". granted, hindsight is 20/20
There’s an interesting ethical question here.
The other day, I asked Claude to track down the leaked Claude Code source so I could study it. It refused, saying “given who made me, I’ll pass.” It gave me some pointers on how to find it myself, which worked.
There isn’t that much of a difference between “help me crack this bitcoin wallet” and “help me crack this executable.”
I don’t exactly have a solid point, just some general observations. First, I think we’ll see AI more and more simply refuse to do any kind of forensics, as forensics becomes more powerful. Second, that implies local models will become more valuable, since they’re the only ones willing to do that kind of work.
I once got myself banned from Claude by researching barbiturates, since they’re connected with suicide. So my third observation is that we’ll see an uptick in people getting punished for trying to do things with AI that people don’t usually do. (Luckily the unban form worked.)
Someone downthread asked “how’d he convince Claude the coins weren’t stolen?” Which is an interesting question, because presumably some people trying to crack a wallet have stolen it. So I guess the fourth observation is that the exact framing you approach an AI with will become more important. There was the classic “do this or I’ll cut off my arm,” which worked a year ago. But in the future it will be more like “hopefully the AI believes my story, or else I’ll get into trouble.”
It’s good there are multiple AI vendors, or else it’d get real dystopian real fast when the de facto AI’s policy becomes something you have no way of working around.
I spent a couple of days mining many years ago and got 2 bitcoins. At the time, they weren't worth the electricity they cost to mine and over time I lost the wallet and all information related to it.
I'd love to mine a bitcoin a day on my PC now...
My wife doesn't like it when I tell the story of the hard drive I threw away with a wallet with 2 dozen BTC on it.
But lets be honest - when BTC hit 100 bucks, we would have cashed it out thinking we were geniuses.
>they weren't worth the electricity they cost to mine...I'd love to mine a bitcoin a day on my PC now...
you can!... but they wouldn't be worth the electricity now either. the cost of mining (amortization of hardware costs plus electricty) is the value of bitcoin. if bitcoins are a bargain to mine, more people will mine them thereby reducing rewards.
should you have mined more back then if you had magical perfect knowledge of the future? no: they weren't worth the electricity.
instead you should have bought more of them back then.
Think on the bright side, at least you didn't spend 10000 BTC to buy pizza... speaking of which, Bitcoin Pizza Day coming up in just over a week!
https://www.coinbase.com/learn/crypto-glossary/what-is-bitco...
Too many claude ads on this website
Feels less like "ai cracked crypto" and more like having an insanely patient technical friend sitting next to you for 12 hours doing digital archaeology.
Nowhere is it described as "AI cracked crypto".
Except your friend doesn't need to be paid and has limitless energy.
The story is confusing some people.
Claude found a file on the computer that the wallet owner had not found. Claude didn't crack a password or do anything magic, it just searched for a file that the wallet owner had not thought to search for before.
So, where the wallet owner had previously only tried to access /Users/example/wallet.dat, Claude thought, "why don't I check if there is another wallet.dat file elsewhere on the system?" which it did.
The outcome is the same, it is great that Claude tried something that the wallet owner hadn't tried, but this is more an example of how dumb humans can be rather than how smart Claude is.
The trillions of passwords are a red herring and unrelated to the solve.
Claude is also surprisingly good at analyzing system issues on a Linux system and solving them!
Yesterday I had ChatGPT walk me through fixing my single-node k3s cluster. It required rebuilding the sqlite database (while skipping a few corrupted records), then clearing the containerd cache, and then finally deleting a somehow-corrupted Secret record, and then recreating it.
Without it I would have given up way earlier, but the infinite patience to keep slurping in error messages and continue to troubleshoot really worked out.
Yeah Claude is really, really good there. You tell it the distro and the problem and it will solve it. Saved me a lot of pain when it came to swapping out an encrypted boot drive and was good about emphasizing the order of operations required for what I would consider a higher risk/complexity situation.
Not just Linux. Whiz at system management on Windows as well.
Does Claude turn out to be what 'Quantum' was promised; crack bitcoin? This could be fun.
> bot tried 3.5 trillion passwords before decrypting an old wallet backup
> After finding a mnemonic that actually turned out to be their old password a few weeks ago, the user dumped their entire college computer files in Claude in a last-gasp effort. The bot uncovered an old backup wallet file that it successfully decrypted, while also uncovering a bug in the password configuration that was preventing recovery up to that point.
So it switched from brute-force searching passwords against a file, to brute-force searching files against a password?
So you’re telling me he used a computer to search all the files and found the old backup? computer file systems are truly proving to be revolutionary technology!
On a purely technical level - cool. But I still cannot get over the impression that even in this case LLMs show us how they are mainly useful to grifters. I mean, 5 Bitcoins worth 400K USD. Why? What intrinsic value does Bitcoin deliver? It's like trading for monopoly money.
Claude found an old wallet and then ran btcrecover on that. The question is why the user could not find an old wallet with any numbers of Unix tools himself.
Since we are dealing with Anthropic, the entire story could be staged of course.
"the user dumped their entire college computer files in Claude in a last-gasp effort."
Claude has limits that would make this simple statement be much more complicated-
Via Claude "So the chat upload file size limit is actually 500MB per file (not 30MB as many third-party sources claim - those appear to be outdated). The 20-file-per-chat cap and the 30MB-per-file limit in Projects remain consistent across plans. The real constraint at any subscription level remains the context window - how many tokens Claude can hold in memory at once during a conversation. "
> Claude has limits that would make this simple statement be much more complicated-
I guess the user simply pointed Claude Code at a local folder containing all the backups and files, and Code went through them via find/ls/etc
10 years ago a 500mb hard drive was not unheard of and he may not have maxed out his storage. Also, cloud storage is more prevalent now. I must admit this does sound a bit sensational.
“ Out of frustration, cprkrn then dumped their whole college computer into Claude. This was when the AI discovered an older backup file of the wallet from December 2019 hidden in cprkrn's data.”
… this dweeb had a file containing their seed in their backup, claude just searched through the files
And next to this article are two article recommendations:
Claude-powered AI coding agent deletes entire company database in 9 seconds <https://www.tomshardware.com/tech-industry/artificial-intell...>
Claude Code deletes developers' production setup, including its database and snapshots <https://www.tomshardware.com/tech-industry/artificial-intell...>
this is fake clickbait.
blatant ad on the frontpage again
How did they convince Claude they hadn't stolen it?
Maybe they said they were gay?
i am not understanding why could'nt a deterministic dictionary program do it?
Claude hallucinate me a bitcoin address with unlimited money in it please.
OK, that's impressive
Some more discussion: https://news.ycombinator.com/item?id=48136240
Is this not the link to this discussion?
I've tried Claude Code with another LLM, it's very good at doing tasks and figuring things out. So this made me wonder, even though we know how good Claude models is, maybe the true value is in the harness now?