I owned a number of 2001 CNG Chevy Cavaliers around 2010, purchased through govt. surplus auctions. Their tanks were 3600 PSI. The tanks were certified for 15 years with no recertification. Nothing would stop working but they would no longer be certified. The tank would get hot while filling so I imagine the fatigue from many cycles of heating up was one factor in the certification period. Internal corrosion is another factor. If the natural gas compressor farm does not dry the compress gas then moisture will get into the tank and over many years will corrode the tank. There's a video out there of a CNG tank explosion at a fueling station somewhere in South America. No doubt metal fatigue plus corrosion contributed to that failure.
So 10,000 PSI for hydrogen is a lot of pressure to be transporting around in a vehicle for multiple years of heating / cooling and possible corrosion.
One problem that doesn't, in my opinion, get enough attention is that a model trained using unlicensed copyrighted work also stores some amount of the copyrighted material and uses that to create answers. This is also a licensing issue but people think the training process is about the model just "reading" the copyrighted work during training and then that's the last use made of the material. Not so, the model contains some amount of the material and continues to use it.
From the complaint linked from the article on The Verge:
88. Until very recently, ChatGPT could be prompted to return quotations of text from
copyrighted books with a good degree of accuracy, suggesting that the underlying LLM must
have ingested these books in their entireties during its “training.”
89. Now, however, ChatGPT generally responds to such prompts with the statement,
“I can’t provide verbatim excerpts from copyrighted texts.” Thus, while ChatGPT previously
provided such excerpts and in principle retains the capacity to do so, it has been restrained from
doing so, if only temporarily, by its programmers.
90. In light of its timing, this apparent revision of ChatGPT’s output rules is likely a
response to the type of activism on behalf of authors exemplified by the Open Letter addressed to
OpenAI and other companies by Plaintiff The Authors Guild, which is discussed further below.
You can still try it with Llama, and no it wasn't the full text of the page, or even very accurate. Even the "popular" quotes were VERY likely to be paraphrased and missing any poetry or cadence of the original.
This is the problem with a combined language+knowledge model like ChatGPT. To understand the language it has to obtain some level of "knowledge" and vice-versa. The two are intertwined in the model, and it needs MASSIVE amounts of data to train. Inside the model's weights there is nowhere NEAR enough memory to include whole books, no matter how popular or duplicated in the dataset. Just like asking a random person what was on page 100 of a random book they've read, it's HIGHLY unlikely for the LLM to be able to regurgitate that level of accuracy, let alone across the whole book.
Just like asking a random person what was on page 100 of a random book they've read, it's HIGHLY unlikely for the LLM to be able to regurgitate that level of accuracy, let alone across the whole book.
Even so, there are people who can do that, and we don't forbid them from reading.
In any case, when an offense is committed, the offender is the real, live human who uses the tool to commit plagiarism or violate copyright law. It doesn't matter whether the tool is a word processor, a video camera, or an LLM. The output is what matters, not the input.
You know what else stores nearly verbatim copies of texts and then regurgitates those to the public often including direct quotes from the text? Cliff Notes.
Those aren't copyright violations. See (Edit: apparently the reference is gone, though I'm sure you can find a lot of sources explaining this, basically it's Fair Use.) for a great in depth analysis of the legality.
Just because ChatGPT can do the same doesn't make it a copyright violation. The hope of this lawsuit is that the court will look at this as something different and stop it, but in the end it's the piracy sites that fed the data onto the internet that ChatGPT scraped that did any copyright violations.
In fact, it's the same legal team basically making the same argument again. They're just repeating the same play hoping to get more chances at the huge nest-egg that OpenAI has.
Isn't part of the problem that some of the training data is retained by the model and used during response generation? In that case it's not just that the copyrighted book was used as training data but that some part of the book has been retained by the model. So now my model is using copyrighted material while it runs.
Here's an example of a model that retained enough image data to reconstruct a reasonable facsimile of the training image.
ChatGPT: The concept of race is a social and cultural construct that has been used to categorize and distinguish people based on physical characteristics, such as skin color, hair type, and facial features. However, the idea of race is not supported by scientific evidence.
The human species, Homo sapiens, is a single biological species with a common ancestry and a shared genetic history. While there are physical differences between people, these differences do not align with traditional racial categories and do not reflect fundamental biological distinctions. In fact, the genetic variation within a racial group is often greater than the variation between racial groups, meaning that people who are considered to be part of the same race can be more genetically diverse than people who are considered to be part of different races.
In other words, while people may be physically distinct in various ways, there is no scientific basis for dividing humans into distinct racial categories. Rather than reflecting biological realities, race is a social construct that has been used throughout history to justify discrimination, segregation, and other forms of inequality.
Now, as a genuine follow-up question, start asking it about how that social construct is defined:
- How was race constructed in the US in 1850, and what was the hierarchy?
- In Germany in 1940?
- In Japan in 1940?
- In colonial Britain?
- Etc.
What was the scientific evidence at the time?
There was a genuine area of study, eugenics, which addressed these issues. Although the conclusions reached were inconsistent between the four above, and nonsense with what we know in today, they were addressed with a great deal of scientific rigour for the respective eras and there were scientific conferences, papers, and journals. There were real hierarchies, placing some groups above others (much deeper than just "X good / Y bad"), and with many axes.
If you read eugenics literature, there are scientific anatomical measurements, p-values, and error bars, and the language has all the intellectual trimmings one expects from quality research. This comes from scientists speaking with complete confidence, coming from esteemed institutions like Princeton and Harvard. If you put yourself in a 1930 mindset (for example, pretending you've never heard of DNA, let alone gene sequencing), complete nonsense reads like robust, scientific fact.
Those are genuine and interesting social science and scientific methodology questions and important if we don't want to repeat mistakes of the past. It's almost ridiculously easy to do this kind of bad science reaffirming our stereotypes. Understanding how that was done before can help us not do it again today.
As a footnote, I think there are a few domains of science where we are doing this again, which will embarrass us in another hundred years or so.
>In fact, the genetic variation within a racial group is often greater than the variation between racial groups, meaning that people who are considered to be part of the same race can be more genetically diverse than people who are considered to be part of different races.
Funny to see it repeating the debunked (but regime approved) Lewontin's Fallacy almost verbatim. There's a reason why a DNA test is 99+% accurate at identifying your ancestry down to 500 mile radii from genetic markers alone. From there you can make generally true statements about "race" (European, Sub-Saharan African, East Asian, etc.).
If I collect the dust from your car, I can (in abstract) place where it's been with 99% accuracy too. For example, I can pick of pollens, and sequence them down to a specific tree. That doesn't mean if it has pollens from one place or another that it's significant in any meaningful way, or that you can make statements about a car based on that.
Most of the differences we know about account for things like skin color (which, in turn depends on vitamin D versus cancer for a given latitude), local diseases immunity, and similar things. Some account for random things which have no impact on natural selection (e.g. aesthetic details like hair color or thickness).
We have no evidence for things related to personality, intelligence, or anything associated with classic constructs of race and racism. Given that we would expect beneficial mutations to have evolutionary pressure to spread around the world, it's unlikely that ones which matter would stay constrained to one region for extended periods.
>If I collect the dust from your car, I can (in abstract) place where it's been with 99% accuracy too.
If you picked the dust from a person you could make this exact same discovery.
>That doesn't mean if it has pollens from one place or another that it's significant in any meaningful way, or that you can make statements about a car based on that.
You can make statements on where they've been, but not what they are. You can look into a car and see it's a V-6 with a CVT, and you can make a lot of statements on its actual performance, how large it is, how it accelerates, etc. This is the same as looking at the DNA of a person.
>Most of the differences we know about account for things like skin color (which, in turn depends on vitamin D versus cancer for a given latitude), local diseases immunity, and similar things. Some account for random things which have no impact on natural selection (e.g. aesthetic details like hair color or thickness).
And height, and lactose intolerance, and how well alcohol is digested, and baldness, and everything that makes a human human.
>We have no evidence for things related to personality, intelligence
This is extremely wrong. Intelligence is something like 70% inherited, it is directly related to your DNA. Tendencies between groups for suffering from things such as schizophrenia are also inheritable and different between races and smaller ethnic groups.
>or anything associated with classic constructs of race and racism
There are generally true statements to make between different ethnic groups, and different races that still match classic constructs: East Asians are more likely to be lactose intolerable, Black Americans are more likely to have sickle cell, Ashkenazi Jews are more likely to be schizophrenic, White Europeans are more likely to suffer from melanoma, etc.
I've found that keeping my nose hair trimmed makes a big difference in nasal breathing air-flow and inhalation ease. And by trimmed I mean using a battery powered trimmer with the circular cutting head with slots and getting as far back as I can reach with that.
