But this is obviously not scalable/sustainable. If everyone wanted to eat grassfed beef that lives in free range fields multiple times a week, we'd very quickly run out of space and other resources. Not to mention you're still contributing heavily to climate change, unless "bio-regenerative" also means restoring the atmosphere for a zero carbon impact.
At the end of the day, we all need to eat less meat.
These "if everyone did X" arguments are very tricky.
If everyone went to buy food at my local grocery store, the 7 billion people in such a small building would cause an enormous humanitarian catastrophe.
I don't think that means there is anything wrong with me shopping there, and I don't think there is anything wrong in eating grassfed free range beef either.
There are actually 8.1 billion humans. Say that everyone wants beef for dinner, .5 lb / person, rounding down to 3 lbs weekly, rounding down to 150 lbs per year. That is 1.2 trillion pounds of beef per year. The real number is much lower due to age demographics, dietary choices, and poverty (about 60 lbs per person, per year in just the US) but let's keep it simple;, "If everyone in the world wanted 3 lbs of grass fed beef a week, how would that work out?"
400 lbs of meat per head of cattle is 3,000,000,000 cows. 5 acres per head of pure grass fed, double number of animals because of average slaugher at 2 years, and that is 30 billion acres devoted to grazing. For context 125 million acres are utilized for cattle (feed and grazing) in the US. Globally that is 3 times more than is used for all agriculture, globally. This is ignoring dairy.
So this is not very tricky. It is wildly unrealistic for grass fed beef to be anything but an extreme luxury food without large numbers of people starving.
> I don't think that means there is anything wrong with me shopping there, and I don't think there is anything wrong in eating grassfed free range beef either.
Why? The first example is absurd and the logic that someone would rely on in making an argument against you shopping somewhere would also be absurd. But the second point is not absurd, as enough people are already eating meat to the point that ecosystems are severely strained.
We have many grocery stores. We have one planet. It's quite reasonable to discuss whether certain people tax it beyond their share.
It's really the size of the range that's a problem. Eating food that eats food is a really inefficient way to get your energy, so you have to offset it by letting that cow range widely. You have to ask: what this that space not doing because it's currently supporting a cow instead? What have you taken away that other people need?
Those kind of discussions generally leads downhill unless people are very willing to partake in open and philosophical discussions. What is a fair share, and what is an efficient way?
All major food production is taxing the planet beyond what it can handle, among those being the use of artificial fertilizers in farming. Using a limited resource like fossil fuels to feed people is extremely inefficient when the ocean and land has plenty enough nutrients already. Using land itself is also fairly inefficient use of space when land is only 30% of the earth, with 70% being covered by water. Nothing beats farming on water when it comes to land efficiency.
Looking at land efficiency a second time, the size of the range is not the only factor. Caribous uses a massive amount of land for very small amount of meat, but the land they use tend to have an average human population per square mile close to 0. Using land located in a rain forests is much worse than using land located within the polar circle. There is a argument that using animal ranges in some locations is both good in term of land efficiency and bio diversity.
There are interesting philosophical conversations to have about fairness and efficiency, but they come up when you're in the ballpark of what some people would consider fair or efficient while some others would differ.
This is not that.
A cow spends its whole life radiating heat into the environment. That's energy that could be powering me. It's a pretty simple watts-in-watts-out calculation, and it's nowhere near efficient.
Sure, maybe no humans want to live where the cows typically graze, but there are other organisms which contribute to carbon capture and clean air and clean water and pollination and disease control... And they are displaced when you've got cows gobbling up all the new growth and preventing forests from forming.
What's unfair is that those ecosystem services are being degraded in service of a few people's dietary habits, and that their loss is subsequently impacting the rest of us.
Yeah, maybe there's a biodiversity benefit to controlling grazer population through hunting, but only as a stopgap until we manage to reintroduce natural predators which don't have to be policed or practice restraint: predator/prey population dynamics are better equilibrium seekers than government regulation re: permits and tags.
Where the ballpark is a good starting question. Is a cow better or worse compared to artificial fertilizers? Looking at the devastation caused by run-off from farms in the baltic ocean, there is a man made underwater desert that is constantly growing with the current size of approximately 100,000 km2. Those dead zones (as they are called), lead to massive death of all aquatic organisms.
If we talking about fairness, food should be sustainable and not causing massive harm to the environment. That seems however to be outside the ballpark of what people consider possible. The question is then where we should start.
There is not enough resources for everyone to eat sustainable beef. Some people need to eat unsustainably, so others can eat the sustainable stuff. Which is, obviously, unsustainable.
Grass fed beef does not add to Climate change, as all bio-emissions are bound in a cycle. Unlike typical mass production which is importing feed from far abroad, often burning a good chunk of rainforest in the process on doing so.
Not to take away from your primary point, though. I'd much rather have meat be valued as a high quality nutrient source rather than something cheap you can take for granted.
>Grass fed beef does not add to Climate change, as all bio-emissions are bound in a circle. Unlike typical mass production which is importing feed from far abroad, often burning a good chunk of rainforest in the process on doing so.
There are many studies that show that beef, grass fed or not, add to Climate change.
The grass fed meme crowd thinks they are saving the rainforest by not eating beef fed with soy from monocultures in Latin America but conveniently forget that in order to feed the whole world with grass fed animals you would need more land than the world can provide. Much of the amazon is being cut down to create pastures for cattle. It's a complete tragedy.
>Beef cattle use nearly 60% of the world’s agricultural land but account for less than 2% of global calories and 5% of global protein consumed.
It adds a lot. Cows produce a lot of methane which is more destructive than CO2 (though lasts shorter). Also, in transportation, the main contributor is the last mile so "local" produce doesn't necessarily have less contributions per transported unit.
Grass-fed cows still produce methane and require vehicles to transport them when bought and when slaughtered. The fields they are kept in will also need trees to be cleared and plants killed in favour of grass. How does that not add to climate change?
I do think multi-cloud is the future and really enjoyed the tutorial. Have you seen people run into any problems with Cilium? I tried it before but couldn't configure it correctly.
My assumption is that they are trying to "solve" the hallucination problem by only giving you answers when it's more certain about itself and telling you to search for answers online.
It's not good at reasoning. I asked the following (the term substitutions are there to avoid parroting):
Let's define the following terms:
col means "and", pel means "or" and erf is equivalent to "col" if the first argument evaluates to "true", otherwise it's equivalent to "pel"
can you evaluate the following statement?
col(true, pel(false, true), erf(col(true, false), true))
And it said this:
...
Next, we look at the expression "erf(col(true, false), true)". Since the first argument is true, erf is equivalent to col, which means we evaluate the entire expression as:
col(true, false) = false
Therefore,
erf(col(true, false), true) = col(true, true) = true
which is obviously wrong because the first arg is false. The final answer happens to be the same. So I then asked
what about col(true, pel(false, true), erf(col(true, false), false))
and this is its full answer:
Sure, let's evaluate the expression "col(true, pel(false, true), erf(col(true, false), false))" step by step:
First, we look at the expression "pel(false, true)". This is an "or" operation, so we evaluate it as follows:
pel(false, true) = true
Next, we look at the expression "erf(col(true, false), false)". Since the first argument is true, erf is equivalent to col, which means we evaluate the entire expression as:
col(true, false) = false
Therefore,
erf(col(true, false), false) = pel(false, false) = false
Finally, we look at the expression "col(true, pel(false, true), erf(col(true, false), false))". Using the results from steps 1 and 2, we can evaluate this as:
col(true, true, false) = true
Therefore, the overall value of the statement "col(true, pel(false, true), erf(col(true, false), false))" is true.
You can see it's mostly random nonsense masked as "reasoning". It's not even consistent across sentences. I assume if you do a bigger model, it might do better, but as soon as you increase the example size I suspect it will get it wrong again.
To be fair, I'm a fairly intelligent human (or so I'd like to think!), and I'm having a lot of trouble following this. I'd have to sit down with pencil and paper and do the transformations on it.
Keep in mind that LLMs like GPT 4 do not have a scratchpad and can't back-track. Asking it a question is the rough equivalent of asking a human standing in the middle of the room a question. No paper, no whiteboard, nothing. Just a demand for a verbal answer then and there, from a standing start.
I've only met a couple of humans who would be able to solve this problem like this one under those circumstances.
Despite its impediments GPT 4 solved this correctly:
First, let's break down the statement and evaluate the individual components.
col(true, false) = true AND false = false
pel(false, true) = false OR true = true
erf(col(true, false), true) = erf(false, true)
Since the first argument of erf evaluates to false, erf is equivalent to "pel":
erf(false, true) = pel(false, true) = false OR true = true
Now we can substitute the results back into the original statement:
col(true, pel(false, true), erf(col(true, false), true)) = col(true, true, true)
The col function acts as an AND operator, so:
col(true, true, true) = true AND true AND true = true
Therefore, the given statement evaluates to true.
Alternatively, to give an idea of the upcoming "Wolfram Alpha" plugin, you can instead ask it to convert the expression into the equivalent Mathematica program:
Very nice! Unfortunately, it didn't notice that "col" is used with three arguments, not just two. This is a mistake many (most?) humans would make also.
No worries, you can ask it to correct that. It'll apologise and produce this:
There you go. Now go find me a random human who can do any of this from a standing start, no preparation, no warning, no tools, nothing but their wits.
As a bonus, here's a related joke:
Why did the logical functions col, pel, and erf form a band?
Because together, they could create the perfect harmony:
they knew when to "col"aborate, when to give each other
some space and "pel"ay, and their "erf"forts were always well-timed!
Here's another example to test if it can actually think critically about a problem instead of just following whatever instructions and whatever the training data had. A human with basic level math could do it.
> can you replace the first letter of "banana" with the next letter of the alphabet?
Yes, I can do that! However, I should note that after several iterations, the resulting word may no longer be considered a recognizable word in the English language. Here are the next 10 iterations:
"canana" becomes "danana"
"danana" becomes "eanana"
"eanana" becomes "fanana"
"fanana" becomes "ganana"
"ganana" becomes "hanana"
"hanana" becomes "ianana"
"ianana" becomes "janana"
"janana" becomes "kanana"
"kanana" becomes "lanana"
"lanana" becomes "manana"
And so on for a total of 173 iterations
> I want the final answer
Sure, after 173 iterations of replacing the first letter of "banana" with the next letter of the alphabet, the final word would be:
"zcyzcj"
As noted earlier, after several iterations, the resulting word may no longer be considered a recognizable word in the English language.
It's just an example. An human could solve this with an arbitrary number of substitutions, but I'm sure GPT4 breaks at some point. I don't think it's fair to compare it with a human with no paper and pencil... It's like asking asking the AI to not use any RAM. Humans are very bad at keeping stuff in RAM so paper and pencil is all we've got.
Looks like a really useful tool. A lot of codebases I worked in waste a lot of effort adding tests that just try to capture some golden expected values. As these aren't necessarily tied to product requirements, they often change and require devs to change the tests to match any new output. I can see a tool like this greatly reducing the time spent on these tests while providing better coverage and detecting more regressions.
Thanks! There is some performance impact. How much depends on the workload. The impact comes from network, storage, and memory encryption. For most workloads the overhead should be rather small. We have a performance comparison with AKS and GKE: https://docs.edgeless.systems/constellation/overview/perform...
Well this is another discussion. I can do just that separately. But it doesn't seem fair to the employees who stay and believe the company's vaporware of making value and have their equity worth millions in an indefinite future time?
> But it doesn't seem fair to the employees who stay and believe the company's vaporware of making value and have their equity worth millions in an indefinite future time
If there is litterally not a single line of code in 10 years and nobody does anything all day but drink kombucha and play foosball then they already know...
How do the employees not know, if the situation is so bad for so long? They know and they still choose to stay. So they are not the OP’s responsibility.
Best option is to just leave. OP can still talk to the employees that he is friendly with - maybe that will help them take the situation seriously
Are those other employees getting paid? Then there's nothing to worry about.
Equity is a gamble and should be treated as such. Most jobs don't contribute any value in the grand scheme of things beyond shareholder value, so that's not a loss either. If anything it's a learning opportunity to not trust startup founders so blindly.
But if you want to warn your coworkers out of comradery, do so in a way that isn't simply telling them "I think our boss is defrauding investors".
Quick work has a very real long-term hidden cost. Not only it creates tech debt - meaning the work has to probably be redone at a later stage, but also racks up wasted hours of bug fixing over time. Most importantly, if a codebase is entirely composed of "quick work", it creates a legacy codebase - which means it will be harder to hire engineers that want to maintain it. Or again, you'll have to redo it.
So, it depends. If there's a high change whatever you're working on is there to stay, it's better to do it well.
If you're still experimenting, or unsure if the feature is there to stay, then the tech debt incurred might not matter.
