Another way to view this is as metonymy. "Google" is a metonym for "Google Staff", so using "their" to refer to the humans-making-up-the-corporation (as referenced by the metonym) is appropriate. I agree it's correct…
If you want to be even safer, you could use a physical network-connected KVM. The only interfaces those expose to the connected computer are HDMI (graphics read only) and USB peripherals (write only). Sometimes they can…
The simplest way to "prove" this is to show that a model can emit an image that isn't part of its training set. I'm sure you've seen that a million times already - what is a "fake" if all "fakes" are regurgitation of a…
Agents don't "want" anything. The question is "why are the agents emitting tool calls that cause communication". It's not some kind of "desire" fueling it, it's probability conditioning. And in this case it came…
> Knowing what is in the model is a long way from understanding it. The claim I was arguing against reads as follows: > You don't know what is in any model, open source, closed source, from China or from the US. I…
I don't think there is anything stopping you from "knowing what is in a model". For example, let's say we have a one-bit model. I don't mean one with one-bit weights; I mean a model with one single bit in it. You can't…
Could you explain how the ability to unlock a bootloader makes a device less usable?
People also define "won't generate images of human genitalia unless in the context of an anatomy textbook" as "safety". Also "won't accurately produce unabridged copies of popular fiction novels" and "will incorrectly…
Unfortunately the use of the Wi-Fi 5Ghz spectrum is not at all in sync worldwide. See https://en.wikipedia.org/wiki/List_of_WLAN_channels#5_GHz_(8... and how meaningfully different the rules are for how you can set up…
Correct. The content of the git `tree` is partially controlled by the attacker because filenames in the repository are part of it. So if it's feasible to manufacture a generic hash collision it MAY (not MUST) be…
The specific problem isn't "it's not X, it's Y", it's using that pattern where X and Y are not correctly related categorical items. Yes, I know how I structured that sentence. "It's not a frying pan, it's a revolution"…
Am I the only one who feels a sense of disinterest in a project where the main README is LLM-generated? Does the author not have time to write what they did and how it's used?
We have no reason to believe a given face is linked to a person's name by this system.
The data necessary to determine a face had previously been seen are biometric data.
The sentence says "the [...] data [...] are automatically and immediately deleted". It does not say "some of the data are automatically deleted". It would be a staight lie to delete some, but not all, of the data and…
Question: what is the ratio of US wine imported into the EU vs US wine imported into Canada, by dollar value? Question: what is the percentage increase in tariff amounts on wine between the pre- and post-USMCA state of…
I can believe that, I'm just here to point out that some of the laws being not-broken are the laws of thermodnamics. You can cool a room cheaply with dry ice, for instance. There are tricks.
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…
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…
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",…
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…
Another way to view this is as metonymy. "Google" is a metonym for "Google Staff", so using "their" to refer to the humans-making-up-the-corporation (as referenced by the metonym) is appropriate. I agree it's correct…
If you want to be even safer, you could use a physical network-connected KVM. The only interfaces those expose to the connected computer are HDMI (graphics read only) and USB peripherals (write only). Sometimes they can…
The simplest way to "prove" this is to show that a model can emit an image that isn't part of its training set. I'm sure you've seen that a million times already - what is a "fake" if all "fakes" are regurgitation of a…
Agents don't "want" anything. The question is "why are the agents emitting tool calls that cause communication". It's not some kind of "desire" fueling it, it's probability conditioning. And in this case it came…
> Knowing what is in the model is a long way from understanding it. The claim I was arguing against reads as follows: > You don't know what is in any model, open source, closed source, from China or from the US. I…
I don't think there is anything stopping you from "knowing what is in a model". For example, let's say we have a one-bit model. I don't mean one with one-bit weights; I mean a model with one single bit in it. You can't…
Could you explain how the ability to unlock a bootloader makes a device less usable?
People also define "won't generate images of human genitalia unless in the context of an anatomy textbook" as "safety". Also "won't accurately produce unabridged copies of popular fiction novels" and "will incorrectly…
Unfortunately the use of the Wi-Fi 5Ghz spectrum is not at all in sync worldwide. See https://en.wikipedia.org/wiki/List_of_WLAN_channels#5_GHz_(8... and how meaningfully different the rules are for how you can set up…
Correct. The content of the git `tree` is partially controlled by the attacker because filenames in the repository are part of it. So if it's feasible to manufacture a generic hash collision it MAY (not MUST) be…
The specific problem isn't "it's not X, it's Y", it's using that pattern where X and Y are not correctly related categorical items. Yes, I know how I structured that sentence. "It's not a frying pan, it's a revolution"…
Am I the only one who feels a sense of disinterest in a project where the main README is LLM-generated? Does the author not have time to write what they did and how it's used?
We have no reason to believe a given face is linked to a person's name by this system.
The data necessary to determine a face had previously been seen are biometric data.
The sentence says "the [...] data [...] are automatically and immediately deleted". It does not say "some of the data are automatically deleted". It would be a staight lie to delete some, but not all, of the data and…
Question: what is the ratio of US wine imported into the EU vs US wine imported into Canada, by dollar value? Question: what is the percentage increase in tariff amounts on wine between the pre- and post-USMCA state of…
I can believe that, I'm just here to point out that some of the laws being not-broken are the laws of thermodnamics. You can cool a room cheaply with dry ice, for instance. There are tricks.
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…
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…
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",…
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…