It's a bias even if the true population distribution isn't linear. For example, if you have a training corpus where 50% of the text follows "black bobblehead" with "arrested" and 20% of the text follows "white…
No, a "bias" is a statistical term meaning a probability distribution that has an expected value differing from the population's expected value. A human's discriminatory bias against an ethnicity is just one type of…
The reason nuclear reactors are dangerous is because if you turn off the power cooling them down, they react (and radiate) more. If you turn off the power cooling a data center, the servers within rapidly stop doing any…
My comment is literally explaining the result of the paper, in which it is shown that LLMs can and do develop biases based on text appearing in their training data set even where such text is not in any training example…
I think you're missing the point of TFA. The LLMs take in text which conditions their output. That means even nonsense text - such as a "tribal affiliation" to a tribe that may not have ever existed - ALSO condition the…
That's not how training works. Training tries to produce something that scores highly in training evaluations. With one data point, the evaluation is solely how closely the model output resembles the single input text.…
KYC stands for Know Your Customer, the regulations that require institutions moving money between two parties to positively identify each of those two parties. I think the intellectual position "it should be illegal for…
I don't think this is what the GP meant, but he's accidentally correct in that there is indeed no good reason for a password to reach the server. The client could do a challenge-response PAKE with the server, proving…
> and by the same token I don't think you intended this, but the word choice here gave me a chortle.
I think the most useful word in both cases is "extrapolating". An LLM extrapolates from its context window to the immediate next token. This word applies whether you view what's happening as "reasoning", "prediction",…
I do not feel you addressed my point at all. I want to install an app now, and protect against its developer doing a rugpull on my local files later. I do not want to need to review each new app version in advance as I…
Let's say I want to secure my system against an app developer deciding to delete my data stored in their app. To do that, I wish to store a copy of all the files the app has written to my filesystem, and put that copy…
Actually, MicroG by default doesn't download or run droidguard binaries at all. You're missing my point here, which is that failing to describe a particular threat scenario leads to meaningless words spoken about…
Whether Claude is or is not available via AWS Bedrock is entirely decided by Anthropic, not by you and not by Amazon. And you can't buy the data sets (the REAL power...) from any AI company.
I think the three valid criticisms you listed are valid, but there are other quite a few other IMO-valid criticisms of AI. Here are a few as I see them: - AI centralizes power in the hands of capital, rendering those…
They're both security, just security "against" different things. Graphene frequently fails to clearly describe the threat model when calling something "more secure". For example, let's say hypothetically I want to be…
If all rights were inalienable, an employment contract would not mean I need to pay my employee, because I would have an inalienable right to keep my own property (cash). Also nobody would offer the contract in the…
I, personally, don't feel that "making money by doing business in a particular market" should be a right it is illegal to waive. If it were inalienable, things like regional distribution agreements would be void, since…
There's no way to prove the second partition is real encrypted data instead of random garbage. It gets wear-leveled but that would also be the case if the true partition had been resized before. It doesn't matter if the…
Media converters are effectively a switch, but less flexible. I would buy a switch with an sfp+ port instead and use it with an appropriate sfp module.
I don't understand how wear leveling makes deniability impossible. You just have to overwrite sectors in the false partition at the same rate as ones in the true partition. Since both the true and false partitions are…
This is a nonsensical goal. If I drag a browser window to the right, making it cover the right-hand half of my monitor, it serves no useful purpose for "centered" content to migrate to the left edge of the window (the…
No, I think you misunderstood me. We engineer the model-training algorithm and then we USE the model. The model is a mess of random gobbledegook that happens to be the best optimizer for the training algorithm's reward…
Imagine for a moment that batteries with decent shelf lives are free. You build a power plant on a geothermal vent in Iceland. The electricity it produces is plentiful and cheap. You run it full tilt charging batteries.…
I think you've entirely missed what I'm trying to say. If your objective is to expend as little energy as possible, it would be irrational to expand into space - that's a waste of effort. If your objective is to…
It's a bias even if the true population distribution isn't linear. For example, if you have a training corpus where 50% of the text follows "black bobblehead" with "arrested" and 20% of the text follows "white…
No, a "bias" is a statistical term meaning a probability distribution that has an expected value differing from the population's expected value. A human's discriminatory bias against an ethnicity is just one type of…
The reason nuclear reactors are dangerous is because if you turn off the power cooling them down, they react (and radiate) more. If you turn off the power cooling a data center, the servers within rapidly stop doing any…
My comment is literally explaining the result of the paper, in which it is shown that LLMs can and do develop biases based on text appearing in their training data set even where such text is not in any training example…
I think you're missing the point of TFA. The LLMs take in text which conditions their output. That means even nonsense text - such as a "tribal affiliation" to a tribe that may not have ever existed - ALSO condition the…
That's not how training works. Training tries to produce something that scores highly in training evaluations. With one data point, the evaluation is solely how closely the model output resembles the single input text.…
KYC stands for Know Your Customer, the regulations that require institutions moving money between two parties to positively identify each of those two parties. I think the intellectual position "it should be illegal for…
I don't think this is what the GP meant, but he's accidentally correct in that there is indeed no good reason for a password to reach the server. The client could do a challenge-response PAKE with the server, proving…
> and by the same token I don't think you intended this, but the word choice here gave me a chortle.
I think the most useful word in both cases is "extrapolating". An LLM extrapolates from its context window to the immediate next token. This word applies whether you view what's happening as "reasoning", "prediction",…
I do not feel you addressed my point at all. I want to install an app now, and protect against its developer doing a rugpull on my local files later. I do not want to need to review each new app version in advance as I…
Let's say I want to secure my system against an app developer deciding to delete my data stored in their app. To do that, I wish to store a copy of all the files the app has written to my filesystem, and put that copy…
Actually, MicroG by default doesn't download or run droidguard binaries at all. You're missing my point here, which is that failing to describe a particular threat scenario leads to meaningless words spoken about…
Whether Claude is or is not available via AWS Bedrock is entirely decided by Anthropic, not by you and not by Amazon. And you can't buy the data sets (the REAL power...) from any AI company.
I think the three valid criticisms you listed are valid, but there are other quite a few other IMO-valid criticisms of AI. Here are a few as I see them: - AI centralizes power in the hands of capital, rendering those…
They're both security, just security "against" different things. Graphene frequently fails to clearly describe the threat model when calling something "more secure". For example, let's say hypothetically I want to be…
If all rights were inalienable, an employment contract would not mean I need to pay my employee, because I would have an inalienable right to keep my own property (cash). Also nobody would offer the contract in the…
I, personally, don't feel that "making money by doing business in a particular market" should be a right it is illegal to waive. If it were inalienable, things like regional distribution agreements would be void, since…
There's no way to prove the second partition is real encrypted data instead of random garbage. It gets wear-leveled but that would also be the case if the true partition had been resized before. It doesn't matter if the…
Media converters are effectively a switch, but less flexible. I would buy a switch with an sfp+ port instead and use it with an appropriate sfp module.
I don't understand how wear leveling makes deniability impossible. You just have to overwrite sectors in the false partition at the same rate as ones in the true partition. Since both the true and false partitions are…
This is a nonsensical goal. If I drag a browser window to the right, making it cover the right-hand half of my monitor, it serves no useful purpose for "centered" content to migrate to the left edge of the window (the…
No, I think you misunderstood me. We engineer the model-training algorithm and then we USE the model. The model is a mess of random gobbledegook that happens to be the best optimizer for the training algorithm's reward…
Imagine for a moment that batteries with decent shelf lives are free. You build a power plant on a geothermal vent in Iceland. The electricity it produces is plentiful and cheap. You run it full tilt charging batteries.…
I think you've entirely missed what I'm trying to say. If your objective is to expend as little energy as possible, it would be irrational to expand into space - that's a waste of effort. If your objective is to…