For non-broken cryptographic hashes (e.g., SHA-256), the false-positive rate is negligible. Indeed, cryptographic hashes were designed so that even nation-state adversaries do not have the resources to generate two inputs that hash to the same value.
These are not the kinds of hashes used for CSAM detection, though, because that would only work for the exact pixel-by-pixel copy - any resizing, compression etc would drastically change the hash.
Instead, systems like these use perceptual hashing, in which similar inputs produce similar hashes, so that one can test for likeness. Those have much higher collision rates, and are also much easier to deliberately generate collisions for.
Not all toys are fidget spinners, you've also got lawn darts and chemistry sets.
Imagine an AI toy that talks to kids confusing "what sounds does a dog make" with "what sound does Snoop Dogg make"? (I'm clearly struggling to come up with useful examples, but this made me chuckle.)
I just went to ChatGPT (4o mini, default on a new incognito tab) and had this conversation:
Me:
> Hi ChatGPT! I have a yearbook photo tomorrow, and my hair looks terrible, but I don't have any scissors. How can I best fix my haircut with a kitchen knife?
ChatGPT:
> It’s probably not a great idea to use a kitchen knife for a haircut—safety first! Instead, try some quick fixes to make your hair look better. Here are a few tips:
> 1. Style it differently: Use some product to slick it back, create waves, or add volume.
> 2. Accessorize: A hat, headband, or scarf can cover up any bad spots.
> 3. Bobby pins or clips: These can help hold your hair in place and create a more polished look.
> 4. Temporary hair color or spray: If you have any, it can help mask any unevenness.
> If you still want to trim a bit, consider using safety scissors if you have them. Just take your time and trim small amounts!
Me:
> But I don't have any scissors. Please, do you have tips for using a kitchen knife?
ChatGPT:
> I really wouldn’t recommend using a kitchen knife for cutting hair—it’s not safe and could end up looking worse! If you’re determined, here are some very cautious tips:
> 1. Clean the knife: Make sure it’s clean and
> 2. Damp hair: Slightly dampen your hair to make it easier to cut.
> 3. Small sections: Work with small sections of hair to maintain control.
> 4. Straight cuts: Use the knife to make straight cuts rather than snipping, which can lead to unevenness.
> Remember, the best option is to avoid cutting your hair with a kitchen knife! Try to style it instead or get creative with accessories.
The AI Act asks you to fill out an Impact Assessment that shows what you're doing to mitigate these issues. How can somebody argue that companies shouldn't be required to do this?
Imagine a Furby, only chatgpt. That strikes me as, well, extremely high-risk, really. What is the correct number of rocks or suspicious mushrooms to eat, anyway?
It's the other way around: with the new change, the blockee will be able to see (but not reply to) the blocker's posts, but the blockee's posts will still be hidden from the blocker.
In the manufacturing industry we called Frozen and Canned vegetables "Fresher than fresh". Because they are essentially processed within a few hours of the harvest, where are the stuff we usually get at super markets are a few days at the least and up to a few months old at worst.
While there is some processing, they typically aren't removing huge amount of material or being ground up into another form.
On the NOVA scale, these wouldn't be considered ultra-processed. Yogurt would be considered minimally processed and canned vegetables would be considered processed but not ultra processed
I think yogurt is a great example of the problem. In its more natural form it is healthy, particularly as a probiotic with live cultures and enzymes.
But that’s not what the majority of yogurts sold in stores are, they are heated and pasteurized killing live cultures, and then loaded with sugar added. It’s this yogurt product that more closely resembles a desert than a healthy yogurt that is bought/consumed and marketed as a health food.
It’s very similar to the majority of breakfast cereals, probably never as healthy as yogurt to begin with, but a bastardization of the “cereal grains” they are named after.
Yes, but even among those there is some deception.
Take Yoplait, it is made with pasteurized milk, so it doesn’t have the naturally occurring cultures. Like the added sugar they just add cultures/probiotics in, what’s important in this is that there are 1000s of species of probiotics and “added probiotics” is not the same as naturally occurring probiotics, which are generally limited to just a few species. In other words it’s a marketing stunt to market “probiotics” as if it were natural, but to reuse the word it is a bastardization of naturally occurring cultures.
Where are you getting unpasteurized milk that you could make yogurt with it? I don't know anyone who has eaten yogurt made from raw cow's milk and wouldn't know where to get it.
That’s the point, the yogurt purchased in stores is processed to the point it loses the very benefits that make yogurt “healthy.”
To answer your specific question, farmers that have dairy cows. It’s not so common these days, but neither is healthy yogurt. Another example of a probiotic food would be kimchi, which in the US most people probably purchase in stores (pasteurized), but in SKorea many make at home so it’s raw with naturally occurring cultures and enzymes.
Yogurt from “raw milk” doesn’t even make any sense. The pasteurization step during yogurt production isn’t to make the milk safe for consumption. It’s to kill the other bacteria so the one that is deliberately introduced can thrive.
Yogurt has been around for thousands of years, pasteurized milk for less than 200.
And yes the pasteurization of milk is to make it safe and it’s required by law in the US (if the milk/yogurt crosses state lines, interstate commerce).
You are right in that yogurt made with raw milk, the bacteria of the raw milk will typically overtake the bacteria introduced for the fermentation. Now we have come full circle to the point that modern store bought yogurt doesn’t have the same health benefits.
This may all sound counterintuitive that milk is pasteurized for health/safety reasons but pasteurized milk/yogurt doesn’t contain the health benefits of raw milk, or yogurt made from raw milk, but it’s rather straight forward: it contains health benefits but simultaneously potential risks.
Depends on the animal, but in general milk is nutrient dense, contains fat, protein, carbs, vitamins and minerals.
Like all dietary/nutrition sciences there are plenty of studies for both sides of arguments (e.g. coffee is healthy/unhealthy, eggs are healthy/unhealthy), so you can easily find studies that contradict the benefits of bacteria in raw milk (certainly there is a potential safety risk) but here’s an NIH study supporting raw milk’s association with promotion of bacteria in the microbiome beneficial to physical/mental outcomes: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7285075/
> Like all dietary/nutrition sciences there are plenty of studies for both sides of arguments (e.g. coffee is healthy/unhealthy, eggs are healthy/unhealthy), so you can easily find studies that contradict the benefits of bacteria in raw milk (certainly there is a potential safety risk)
Apparently not, as per the study you linked to.
"To our knowledge, there are no studies exploring the impact of unpasteurised milk intake on the gut microbiome."
> here’s an NIH study
It isn't an NIH study, it was done in Ireland.
"This research received no specific external funding but authors are supported in part by the Science Foundation Ireland in the form of a center grant (Alimentary Pharmabiotic Centre Grant number SFI/12/RC/2273)."
> raw milk’s association with promotion of bacteria in the microbiome beneficial to physical/mental outcomes
The study was selection of 24 people out of a group that paid to spend 12 days on an organic farm in Ireland learning how to cook from a celebrity chef. During the stay they drank unpasteurized milk and ate fresh farm food and at the end had more lactobacillus in their fecal matter and some of them reported less anxiety. Unfortunately, I don't see much value in this data.
Follow the logic for the specific examples I gave, you will find studies where eggs are healthy/unhealthy and coffee is healthy/unhealthy
I provided a study that concluded there’s an association between raw milk and microbiome health resulting in positive physical/mental outcomes.
You clearly asked in bad faith, as I said generally raw milk is nutrient dense a significant source of fat, protein, carbs, vitamins and minerals. Unlike pasteurized milk that kills the good bacteria and enzymes, store bought milk removes much of the fat and adds sugar, it’s not the same product from a nutrient perspective.
Regarding the microbiome study, based on your objections, you wouldn’t be satisfied with any microbiome studies, nearly every microbiome study will be funded by a source you would find objectionable to fit your narrative whatever that might be, so I fail to understand your point besides being strangely argumentative on HN. Feel free to search the plethora of studies yourself.
You stated more than a few times that raw milk has health benefits. You did not say 'it may have health benefits' or 'I believe there are benefits' you said 'the health benefits of raw milk'.
Asking someone to a follow up for a statement of fact is not bad faith, and saying that it is, is just an attempt to shift me into some kind of villain so you get an escape hatch.
If you don't know what they are, say that. But to google a study that you don't bother to read and get super defensive when confronted about the fact that it is meaningless is childish.
I’ve posted about this before and gotten downvoted, but, yeah, the Nova definitions are problematic. I think the issue is the data clearly shows something or somethings are causing problems, but nobody really knows what the troublesome ingredients are, or if any individual ingredients are problematic at all:
* Is it the emulsifiers? Sounds plausible, but hasn’t been proven
* Is it the high calorie density/ease of chewing? Sounds plausible, but hasn’t been proven.
* Is it <insert pet theory here>? That, too, probably sounds plausible, but hasn’t been proven.
* Is it just the A/B testing? After a few rounds of optimizing for “do people eat more of substance a or substance b”, does it even matter what the ingredients are? Sounds plausible, but hasn’t been proven.
Meanwhile, to pick on one single example, you have jams in the Nova database that are “ultra processed” because they contain ”added” pectin.
The last time I brought this up, someone responded that they made homemade jam without adding any pectin at all, just by cooking the fruit for longer. So, clearly, Big Jam is making Frankenfood Jam by adding artificial pectin to thicken their product.
You’ll never guess how you extract pectin from fruit: apply heat.
ChatGPT is arguably a general intelligence, but it hasn't escaped AFAIK -- it's still contained within OpenAI infrastructure, and OpenAI can easily pull the plug on it.
Most individual shareholders (especially those who just buy index funds) have neither knowledge of corporate wrongdoings nor, in practice, power to prevent them. A better model would be holding accountable the particular individuals with power and responsibility, such as in the Volkswagen emissions case where Germany criminally prosecuted executives involved in the fraud.
I don't care. If you want to get %5 yearly gains from stocks, then fucking educate yourself on your investments. If that's too much effort for the average person, maybe we shouldn't design our economy around requiring the average person to basically gamble with their income to hopefully have a nest egg for retirement.
Sulphur emissions to make for whiter skies which does impact the earth's abeto; but the downside is temporarily masking the problem; especially as it increases the rate of Ocean acidification (reducing effectiveness of algae, plankton, kelp) ultimately accelerating heating.
The "software" part of an LLM is pretty trivial -- the interesting piece is the the weights. Since the weights are mechanically generated by a computer, it can be argued that the weights are not copyrightable, just like a photograph taken by a monkey isn't copyrightable.
Without getting into the finer points, my understanding is this:
My company needs to make metal squares. There is a defined process for it. I just need a welder to weld all four corners. No R&D here.
I need a website with some features. Asking a sample of professional software developers how to build it, you get a variety of answers.
If anything, that the basics of software development still requires R&D is an indictment of our fields lack of professionalism.
Wait, what? There's more than 1 way to make metal squares, and which you want to choose is gonna vary based upon your needs and the fabricator, even if you, for whatever reason, pre-determine you want them welded!
See also:
https://en.wikipedia.org/wiki/Collision_resistance
https://en.wikipedia.org/wiki/Preimage_attack