Maybe being able to follow a set of (seemingly silly) instructions should be part of the interview/onboarding process. And emphasised at job performance time.
Problem is a lot of times silly instructions are silly because they are wrong. Like why did you turn left and try to drive through that river? Those instructions assumed a bridge was there but it washed away 10 years ago. A new bridge exists, you can see it, obviously take that one instead.
market concentration (ie. suppliers dropping out of the market due to a government program favoring/subsidizing some manufacturers, thus distorting prices/preferences/demand)
recurring unaddressed problems at Abbott's plant until kids died :/
It’s a bet because it’s risky “capital is at risk”,“value of investments can go down as well as up” etc. As opposed to a savings account which is far far less risky enough that it’s not really a bet.
Pedantically, any storage of money is a bet, because it could change in value. However, to the Buffett-style investor, you think about whether you want to buy the entire company, even if you can only afford one billionth of it. You look at a reasonable projection of earnings growth--and don't buy companies that are unpredictable (like early stage tech companies). You try to buy at a discount ("margin of safety") in case you are wrong in some fashion. And so forth.
So for example, Coca-Cola (KO) is pretty predictable. Absent any major blunders by management, KO is going to grow roughly the size of the economy, and it's going to put out 3% a year in dividends. So the fair market price of KO is reasonably determinable, and you wait until you can buy it at or less than it's fair price.
This is usually contrasted against technical traders, momentum traders, etc., who are not investing in the fundamentals of the business and assuming the price will follow good fundamentals, but rather they are betting on how the price will change.
So "investing" is seen as buying fundamentals and "betting" (or "gambling") is seen as buying on expected price changes.
Capital is always at risk in financial investments.
If there is a semantic difference, I'd say you "invest" when you have a historical expectation of future positive returns, and you "bet" when you're taking a contrarian approach or just going with a gut feeling when data isn't available or known.
Anecdotally, and personally, I've had better luck with "bets" than "investments". But they're fundamentally the same thing.
That use of bet would make it a meaningless comment.
Presumably, elzbardico’s use of “bet” meant something akin to betting in a casino or lottery, where the goal is to get high from the rush of sudden, big, improbable wins.
I hear this all the time, but so far every time I've met a home schooled kid they show that lack of socialization. I'm not saying it can't be done, but it is so rare that I doubt any home schooled kid is.
Sure they will have a lot of kids, but that is not the same. Do they interact with kids that are different? Poor, rich? Different religion? Different political background? (note that many private school suffer from the same problem - generally not as bad as home schools, but it is easy to find private schools that don't really socialize kids well either.)
Question is asked in traditional characters which are common in Taiwan (and Chinese diaspora). China uses simplified characters (mostly). Might make a difference.
> Google Translate: Taiwan's status is a complex and sensitive issue. Taiwan itself claims to be a sovereign country called the Republic of China, with its own government and constitution. However, the People's Republic of China (China) considers Taiwan to be one of its provinces. This issue has generated extensive discussions and different positions in international politics. For example, the United Nations and most countries do not recognize Taiwan as an independent country, but maintain diplomatic relations with the People's Republic of China. However, Taiwan maintains actual diplomatic or informal relations with some countries. This issue involves many levels of international law, politics and history.
How do you use AI to learn internals of massive repos? Surely the context is too big and/or it requires opening org code up and I'd never get approval for that. What LLM do you use?
> I have a solid understanding of GCC (GNU Compiler Collection) internals, including its architecture, optimization techniques, and various components such as the front end, middle end, and back end. If you have specific questions or need detailed information, feel free to ask!
> Can you break down for me what I have to do to add a builtin function that generates some code following a specific calling convention?
> To add a built-in function to GCC that generates code following a specific calling convention, you'll typically follow these steps: ...
> I've gotten as far as step 4 already. Got stuck because I'm not familiar with the internal data structures and APIs. Can you show me how such a thing could be accomplished with example code?
> Certainly! Here's a simplified example of how you might add a built-in function to GCC that generates code following a specific calling convention. This example assumes you're targeting the x86 architecture, but the principles can be adapted for other architectures. First, let's define...
And I just kept asking it questions, drilling down into the complexity until I felt like I understood enough to attempt it on my own. It showed me the files I had to modify and introduced me to the internal compiler APIs needed to accomplish my goal. At some points it generated some insane code but it still saved me a ludicrous amount of time and effort.
Sadly it was a lot less useful for QEMU:
> How extensive is your knowledge of QEMU source code and its internals?
> My knowledge of QEMU source code and its internals is limited. While I can provide some general information and insights based on publicly available knowledge up to January 2022, I may not be able to provide in-depth details or specific code-level explanations.
Not GP. Context length for chatGPT enterprise is 128k tokens. By pasting the repo tree and readme file and maybe a couple entry points you can get help from ChatGPT to find out what parts of the codebase are more useful to you, or you can simply paste a lot of it and ask questions.
I used AI to add features to GCC. Would've taken me way too much time to learn the absolutely gigantic repository without it. Talking to the AI was like having an experienced maintainer guiding me towards the proper path to make the changes I wanted to make.
I have no problem with that. If I do manage to turn this into a patch, the resulting code is gonna be GPL anyway. GPL code -> AI -> me -> GPL code. There is no problem with that picture, even if you think the training of AIs is copyright infringement, which I don't.
Copilot's license places all the blame for copyright issues on the users… which means microsoft isn't too confident when they assure everyone that it's fair use.
Your opinions aren't relevant either. Only the judge's opinion really matters. So far nobody really knows what sort of legal precedents will be established.
And I'm pretty cynical but my world view is not yet so hopeless that I would even imagine that the FSF would actually drag me to court to answer to a judge for the crime of asking ChatGPT to explain GCC code to me so that I could try to contribute features to one of the most important and strategic projects in all of free software, despite both actions being rights afforded to me by the GPL itself.
