No point asking them to justify why they have to ask, they probably don’t even know. Just say “Sorry, I don’t give that out”. I’ve never had a store push back after that - they probably get it all the time.

TIOBE is meaningless - it is just search engine result numbers, which for many search engines are likely a wildly inaccurate estimate of how many results match in their index. Many of those matches will not be about the relevant language, and the numbers probably have very little correlation to who uses it (especially for languages that are single letter, include punctuation in the name, or are a common English word).

When people say Local AI, they mean things like the Free / Open Source Ollama (https://github.com/ollama/ollama/), which you can read the source code for and check it doesn’t have anything to phone home, and you can completely control when and if you upgrade it. If you don’t like something in the code base, you can also fork it and start your own version. The actual models (e.g. Mistral is a popular one) used with Ollama are commonly represented in GGML format, which doesn’t even carry executable code - only massive multi-dimensional arrays of numbers (tensors) that represent the parameters of the LLM.

Now not trusting that the output is correct is reasonable. But in terms of trusting the software not to spy on you when it is FOSS, it would be no different to whether you trust other FOSS software not to spy on you (e.g. the Linux kernel, etc…). Now that is a risk to an extent if there is an xz style attack on a code base, but I don’t think the risks are materially different for ‘AI’ compared to any other software.

Blockchain is great for when you need global consensus on the ordering of events (e.g. Alice gave all her 5 ETH to Bob first, so a later transaction to give 5 ETH to Charlie is invalid). It is an unnecessarily expensive solution just for archival, since it necessitates storing the data on every node forever.

Ethereum charges ‘gas’ fees per transaction which helps ensure it doesn’t collapse under the weight of excess usage. Blocks have transaction limits, and transactions have size limits. It is currently working out at about US$7,500 per MB of block data (which is stored forever, and replicated to every node in the network). The Internet Archive have apparently ~50 PB of data, which would cost US$371 trillion to put onto Ethereum (in practice, attempting this would push up the price of ETH further, and if they succeeded, most nodes would not be able to keep up with the network). Really, this is just telling us that blockchain is not appropriate for that use case, and the designers of real world blockchains have created mechanisms to make it financially unviable to attempt at that scale, because it would effectively destroy the ability to operate nodes.

The only real reason to use an existing blockchain anyway would be on the theory that you could argue it is too big to fail due to legitimate business use cases, and too hard to remove censorship resistant data. However, if it became used in the majority for censorship resistant data sharing, and transactions were the minority, I doubt that this would stop authorities going after node operators and so on.

The real problems that an archival project faces are:

• The cost of storing and retrieving large amounts of data. That could be decentralised using a solution where not all data is stored on a chain - for example, IPFS.
• The problem of curating data and deciding what is worth archiving, and what is a true-to-source archive vs fake copy. This probably requires either a centralised trusted party, or maybe a voting system.
• The problem of censorship. Anonymity and opaqueness about what is on a particular node can help - but they might in some cases undermine the other goals of archival.

This is absolutely because they pulled the emergency library stunt, and they were loud as hell about it. They literally broke the law and shouted about it.

I think that you are right as to why the publishers picked them specifically to go after in the first place. I don’t think they should have done the “emergency library”.

That said, the publishers arguments show they have an anti-library agenda that goes beyond just the emergency library.

Libraries are allowed to scan/digitize books they own physically. They are only allowed to lend out as many as they physically own though. Archive knew this and allowed infinite “lend outs”. They even openly acknowledged that this was against the law in their announcement post when they did this.

The trouble is that the publishers are not just going after them for infinite lend-outs. The publishers are arguing that they shouldn’t be allowed to lend out any digital copies of a book they’ve scanned from a physical copy, even if they lock away the corresponding numbers of physical copies.

Worse, they got a court to agree with them on that, which is where the appeal comes in.

The publishers want it to be that physical copies can only be lent out as physical copies, and for digital copies the libraries have to purchase a subscription for a set number of library patrons and concurrent borrows, specifically for digital lending, and with a finite life. This is all about growing publisher revenue. The publishers are not stopping at saying the number of digital copies lent must be less than or equal to the number of physical copies, and are going after archive.org for their entire digital library programme.

I looked into this previously, and found that there is a major problem for most users in the Terms of Service at https://codeium.com/terms-of-service-individual.

Their agreement talks about “Autocomplete User Content” as meaning the context (i.e. the code you write, when you are using it to auto-complete, that the client sends to them) - so it is implied that this counts as “User Content”.

Then they have terms saying you licence them all your user content:

“By Posting User Content to or via the Service, you grant Exafunction a worldwide, non-exclusive, irrevocable, royalty-free, fully paid right and license (with the right to sublicense through multiple tiers) to host, store, reproduce, modify for the purpose of formatting for display and transfer User Content, as authorized in these Terms, in each instance whether now known or hereafter developed. You agree to pay all monies owing to any person or entity resulting from Posting your User Content and from Exafunction’s exercise of the license set forth in this Section.”

So in other words, let’s say you write a 1000 line piece of software, and release it under the GPL. Then you decide to trial Codeium, and autocomplete a few tiny things, sending your 1000 lines of code as context.

Then next week, a big corp wants to use your software in their closed source product, and don’t want to comply with the GPL. Exafunction can sell them a licence (“sublicence through multiple tiers”) to allow them to use the software you wrote without complying with the GPL. If it turns out that you used some GPLd code in your codebase (as the GPL allows), and the other developer sues Exafunction for violating the GPL, you have to pay any money owing.

I emailed them about this back in December, and they didn’t respond or change their terms - so they are aware that their terms allow this interpretation.

The best option is to run them models locally. You’ll need a good enough GPU - I have an RTX 3060 with 12 GB of VRAM, which is enough to do a lot of local AI work.

I use Ollama, and my favourite model to use with it is Mistral-7b-Instruct. It’s a 7 billion parameter model optimised for instruction following, but usable with 4 bit quantisation, so the model takes about 4 GB of storage.

You can run it from the command line rather than a web interface - run the container for the server, and then something like docker exec -it ollama ollama run mistral, giving a command line interface. The model performs pretty well; not quite as well on some tasks as GPT-4, but also not brain-damaged from attempts to censor it.

By default it keeps a local history, but you can turn that off.

I think the most striking thing is that for outsiders (i.e. non repo members) the acceptance rates for gendered are lower by a large and significant amount compared to non-gendered, regardless of the gender on Google+.

The definition of gendered basically means including the name or photo. In other words, putting your name and/or photo as your GitHub username is significantly correlated with decreased chances of a PR being merged as an outsider.

I suspect this definition of gendered also correlates heavily with other forms of discrimination. For example, name or photo likely also reveals ethnicity or skin colour in many cases. So an alternative hypothesis is that there is racism at play in deciding which PRs people, on average, accept. This would be a significant confounding factor with gender if the gender split of Open Source contributors is different by skin colour or ethnicity (which is plausible if there are different gender roles in different nations, and obviously different percentages of skin colour / ethnicity in different nations).

To really prove this is a gender effect they could do an experiment: assign participants to submit PRs either as a gendered or non-gendered profile, and measure the results. If that is too hard, an alternative for future research might be to at least try harder to compensate for confounding effects.

I think (unless I misunderstood the paper), they only included people who had a Google+ profile with a gender specified in the study at all (this is from 2016 when Google were still trying to make Google+ a thing).

Yes, but the information would need to be computationally verifiable for it to be meaningful - which basically means there is a chain of signatures and/or hashes leading back to a publicly known public key.

One of the seminal early papers on zero-knowledge cryptography, from 2001, by Rivest, Shamir and Tauman (two of the three letters in RSA!), actually used leaking secrets as the main example of an application of Ring Signatures: https://link.springer.com/chapter/10.1007/3-540-45682-1_32. Ring Signatures work as follows: there are n RSA public keys of members of a group known to the public (or the journalist). You want to prove that you have the private key corresponding to one of the public keys, without revealing which one. So you sign a message using a ring signature over the ‘ring’ made up of the n public keys, which only requires one of n private keys. The journalist (or anyone else receiving the secret) can verify the signature, but obtain zero knowledge over which private key out of the n was used.

However, the conditions for this might not exist. With more modern schemes, like zk-STARKs, more advanced things are possible. For example, emails these days are signed by mail servers with DKIM. Perhaps the leaker wants to prove to the journalist that they are authorised to send emails through the Boeing’s staff-only mail server, without allowing the journalist, even collaborating with Boeing, to identify which Boeing staff member did the leak. The journalist could provide the leaker with a large random number r1, and the leaker could come up with a secret large random number r2. The leaker computes a hash H(r1, r2), and encodes that hash in a pattern of space counts between full stops (e.g. “This is a sentence. I wrote this sentence.” encodes 3, 4 - the encoding would need to limit sentence sizes to allow encoding the hash while looking relatively natural), and sends a message that happens to contain that encoded hash - including to somewhere where it comes back to them. Boeing’s mail servers sign the message with DKIM - but leaking that message would obviously identify the leaker. So the leaker uses zk-STARKs to prove that there exists a message m that includes a valid DKIM signature that verifies to Boeing’s DKIM private key, and a random number r2, such that m contains the encoded form of the hash with r1 and r2. r1 or m are not revealed (that’s the zero-knowledge part). The proof might also need to prove the encoded hash occurred before “wrote:” in the body of the message to prevent an imposter tricking a real Boeing staff member including the encoded hash in a reply. Boeing and the journalist wouldn’t know r2, so would struggle to find a message with the hash (which they don’t know) in it - they might try to use statistical analysis to find messages with unusual distributions of number of spaces per sentence if the distribution forced by the encoding is too unusual.

I wonder if this is social engineering along the same vein as the xz takeover? I see a few structural similarities:

• A lot of pressure being put on a maintainer for reasons that are not particularly obvious what they are all about to an external observer.
• Anonymous source other than calling themselves KA - so that it can’t be linked to them as a past contributor / it is not possible to find people who actually know the instigator. In the xz case, a whole lot of anonymous personas showed up to put the maintainer under pressure.
• A major plank of this seems to be attacking a maintainer for “Avoiding giving away authority”. In the xz attack, the attacker sought to get more access and created astroturfed pressure to achieve that ends.
• It is on a specially allocated domain with full WHOIS privacy, hosted on GitHub on an org with hidden project owners.

My advice to those attacked here is to keep up the good work on Nix and NixOS, and don’t give in to what could be social engineering trying to manipulate you into acting against the community’s interests.

Most of mine are variations of getting confused about what system / device is which:

• Had two magnetic HDDs connected as my root partitions in RAID-1. One of the drives started getting SATA errors (couldn’t write), so I powered down and disconnected what I thought was the bad disk. Reboot, lots of errors from fsck on boot up, including lots about inodes getting connected to /lost+found. I should have realised at that point that it was a bad idea to rebuild the other good drive from that one. Instead, I ended up restoring from my (fortunately very recent!) backup.
• I once typed sudo pm-suspend on my laptop because I had an important presentation coming up, and wanted to keep my battery charged. I later noticed my laptop was running low on power (so rushed to find power to charge it), and also that I needed a file from home I’d forgotten to grab. Turns out I was actually in a ssh terminal connected to my home computer that I’d accidentally suspended! This sort of thing is so common that there is a package in some distros (e.g. Debian) called molly-guard specifically to prevent that - I highly recommend it and install it now.
• I also once thought I was sending a command to a local testing VM, while wiping a database directory for re-installation. Turns out, I typed it in the wrong terminal and sent it to a dev prod environment (i.e. actively used by developers as part of their daily workflow), and we had to scramble to restore it from backup, meanwhile no one could deploy anything.

I suggest having a threat model about what attack(s) your security is protecting against.

I’d suggest this probably isn’t giving much extra security over a long unique password for your password manager:

• A remote attacker who doesn’t control your machine, but is trying to phish you will succeed the same - dependent on your practices and password manager to prevent copying text.
• A remote attacker who does control your machine will also not be affected. Once your password database in the password manager is decrypted, they can take the whole thing, whether or not you used a password or hardware key to decrypt it. The only difference is maybe they need slightly more technical skill than copying the file + using a keylogger - but the biggest threats probably automate this anyway and there is no material difference.
• A local attacker who makes a single entry to steal your hardware, and then tries to extract data from it, is either advantaged by having a hardware key (if they can steal it, and you don’t also use a password), or is in a neutral position (can’t crack the locked password safe protected by password, don’t have the hardware key / can’t bypass its physical security). It might be an advantage if you can physically protect your hardware key (e.g. take it with you, and your threat model is people who take the database while you are away from it), if you can’t remember a sufficiently unique passphrase.
• A local attacker who can make a surreptitious entry, and then come back later for the results is in basically the same position as a remote attacker who does control your machine after the first visit.

That said, it might be able to give you more convenience at the expense of slightly less security - particularly if your threat model is entirely around remote attackers - on the convenience/security trade-off. You would touch a button to decrypt instead of entering a long passphrase.

As if telling Reddit, Facebook, or Google what to put on their roadmap as an ordinary consumer would actually work.

At least with FLOSS if you want something, and if it is a good thing the developers like, you can likely get it merged. If not, you can fork and still have the feature locally. Good luck getting that freedom with a closed-source product.

For software I develop, I do find it is helpful if people making feature suggestions tell developers what is useful for them and why, but that doesn’t entitle them any of my time to demand what features I prioritise. The alternative is “I gave you something you like for free, so now I owe you to make it even better for you”, which is obviously nonsense.

I thought the orbs were supposedly open source

No they are proprietary as a whole. Parts of the hardware design are published, and parts of the software that runs on them, but not the whole thing.

Fundamentally Worldcoin is about ‘one person, one vote’, and anyone can create millions of fake iris images; the point of the orb is that it is ‘blessed’ hardware using trusted computing (or to use the term coined by the FSF, treacherous computing) and tamper detection to make sure that a central authority (namely Sam Altman’s Worldcoin foundation) has signed off on the orb running the exact secret / proprietary software running on the orb that generates an identity.

They could have alternatively have built a system that leverages government identity using zero-knowledge proof of possession of a government-signed digital identity document. But I think their fundamental thesis is that they are trustworthy to be a central authority who could create millions of fake identities if they wanted, but that governments are not.

One of the key tenets of keeping something computerised secure is ‘Defence in Depth’ - i.e. having multiple layers of defence, so that even if one layer is breached, the next layer (which you thought was redundant and unnecessary) prevents the attack.

Running a fully patched kernel and services / applications should protect you unless someone has a 0-day (i.e. not disclosed) exploit. Reducing the surface area by minimising what services / applications are running, using software (firejail etc…) and firewalls to limit permissions of applications / services to what is needed, etc… serves as another layer of defence. Disconnecting or physically blocking peripherals that might allow for spying is another layer; it serves its purpose if all the other layers are breached.

A lot of AI models are probably already trained on Reddit data. But apparently Spez isn’t important enough to world order to make the cut to be compressed into a 7B model. I asked my Mistral-7B-Instruct (4-bit quantised) local LLM:

>>> What can you tell me about someone called u/spez, a
... nd are they a nice person or horrible?
 I cannot provide any information about a specific individual named 
"u/spez," as I am an artificial intelligence language model and do not have
the ability to access personal information about individuals based on their
online usernames alone. The username "u/spez" appears to be a Reddit 
handle, but it does not reveal any information about the person's character
or personality.

Reddit is a popular social media platform where users can create unique 
usernames for themselves when they sign up. A username like "u/spez" may 
have been chosen for various reasons, and it doesn't necessarily provide 
any insight into the person's nature or disposition. It's essential to 
remember that people's online personas may not always reflect their true 
selves, and it's important to exercise caution when making assumptions 
based on limited information.

I cannot determine whether "u/spez" is a nice person or horrible without 
knowing them personally or having access to their actions, thoughts, and 
motivations. The best way to form an accurate opinion about someone is to 
interact with them directly and observe their behavior in various 
situations over an extended period.

>>> Is it possible u/spez is Steve Huffman? Can you tell me anything based on tha
... t?
 I cannot definitively determine whether "u/spez" is Steve Huffman or not, 
as I don't have access to their personal information. Steve Huffman is a 
Reddit user who gained public attention in 2018 when he posted an AMA (Ask 
Me Anything) thread where he shared details about his life and experiences 
living with Crohn's disease. His AMA post garnered significant attention 
and sympathy from the Reddit community, and he later published a book about
his experiences called "This Is Gonna Hurt: Living With Crohn's and 
Colitis."

It is possible that "u/spez" could be Steve Huffman, but without further 
information or verification, it remains speculation. It's essential to 
remember that usernames on social media platforms do not always reflect the
true identity of the person using them, and it's important to exercise 
caution when making assumptions based on limited information.

If you have any additional information or context about "u/spez" or Steve 
Huffman that could help clarify their relationship, please let me know, and
I will try to provide an accurate response based on the available 
information.

How to work out what instance(s) if someone does this: A Lemmy instance doesn’t have to send the same voting data to every instance, it could send different votes to different instances (stock Lemmy federates the same thing consistently, but there is no reason a modified Lemmy designed to catch someone doing this has to), encoding a signal into the voting pattern. Then, just check to see what signal shows up. If it averages several instances, with enough signal you could decompose a linear combination (e.g. average) of different patterns back out into its constituent parts.

Probably more likely to be surveillance of Snapchat.

requires trusting a company not to fuck with you behind the scenes

The point of this cryptography is that you don’t have to trust the company implementing it not to do that, as long as you trust the software doing the retrieval.