I've been repeating again and again that everywhere, but the sweet spot for beginners is to stick to the boostrapping method that will lead to the least possible modes of failure.
Because I don't want to repeat it every time, I eventually wrote everything down, so know I can just link to it:
For installing Python: "Installing and running Python: the bare minimum you can get away with"
At this point it kinda feels like spamming, but honestly, there is too much noise out there, and those points don't come across enough. Especially since most dev are either too little or too much experienced to be helpful.
We tried the alternative, and it's less productive.
At some point, there is the theory and practice.
Since LLM output are anything but an exact science from the users perspective, trials and errors are what's up.
You can state all day long how it works internally and how people should use it, but people I've not waited for you, they used it intensively, for million of hours.
I have my own sense of morality developed over years of balancing life, I don't want a robot to remind me of the average moral construct present in its training data. It's noise.
Just like I don't want a hammer to keep reminding me I could hit my fingers.
I'm pretty sure the moral stuff is there because a lot of previous chatbots were tricked to make questionable responses that led to bad press. So OpenAI put a lot of effort into making their models behave ethical.
I'm not sure why people are so annoyed by the ethical disclaimers. I don't even recall running into them, but maybe that's just because I don't ask controversial questions.
this whole subthread is an example of things most people would prefer not to see but have successfully trained themselves to ignore over the course of their lives.
excessive moralizing, being reminded that things are there for a reason etc etc
gpt is overly verbose about pointless things, i understand it's by design coz of some person's dogmatic agenda but i don't care personally.
tl;dr - ethics warnings in gpt are like coffee hot warnings on coffee cups
I've tried many system prompts so far, and I'm underwhelmed with the result. Especially, I keep insisting to just give me answers with as little context as possible. E.G, if I ask for code, just give the code.
But the gpt does what the gpt wants.
It's a minor annoyance though, 1st world problem at its best.
Streaming is expensive, but less than you think. If you run your own servers and don't use the cloud, you can serve a million user a month for a few thousand dollars.
HN makes it look casual but it has a very active and diligent moderation and a whole automated system to detect spams, self promotion, hateful comments...
The basic design is on purpose, but the backend doesn't match the front.
I have a large and very eclectic group of buddies, ranging from one extreme to the other, in term of politic, life style, believes, education, etc.
Anecdotally, this is true in my circle.
Left leaning people around me think they are more open minded, but really they just have a different set of things they accept. They have the same number of icks, just not at the same place.
The big gap is in how they behave when in contact with things they don't like.
And right leaning people have been so far more capable of cooperating with those who don't match their values.
Also, on paper, left leaning have expressed more humane values, espacially when very general or abstract. But in the day to day, when it comes to the mondain or practical, I've seen the sexist or racist guys help more my muslim or girl friends that the ones saying every body is equal.
Early on perhaps that was true, but cancel culture seems to have broad appeal across the political spectrum these days.
Although you could make an argument that it still leans left on the public side, with more of a focus on private death threats and harassment on the right. They don't approach the problem of crushing dissent with exactly the same strategy.
I know tankies and I know white nationalists, do they count? I don't approve of their political beliefs in either case but I can get along with them, as in coexist with them in a workplace or hobby space, if they behave better than they believe (most seem to, their beliefs are mostly hot air and the way they actually treat people is more egalitarian than they might care to admit themselves.)
That does seem unlikely. The extreme left is a good bit smaller than the extreme right. The vast, vast majority of Democrats that MAGA folks like to paint as communists are in fact damn near as conservative as they are on most issues. You could probably put all the actual communists in America in a single stadium, with space left over.
I don't have nazis if this is what you are refering to. Just like I don't have murderers and rapists.
But I do have communists, anarchists on one side, and royalists (people in favor or a king) and pro putin on the other. I have anti-vax and phd in physics, millionaires and state help seekers, cops and people making their own amphetamin, people going to all protests and those telling off illegal immigrants to the police.
It's like saying it's both hot and cold. You can argue I don't live in the sahara or in the north pole, but I live in France.
Because I don't want to repeat it every time, I eventually wrote everything down, so know I can just link to it:
For installing Python: "Installing and running Python: the bare minimum you can get away with"
https://www.bitecode.dev/p/installing-python-the-bare-minimu...
To manage deps: "Back to basics with pip and venv":
https://www.bitecode.dev/p/back-to-basics-with-pip-and-venv
And how I justify those very steps: "Why not tell people to "simply" use pyenv, poetry, pipx or anaconda".
https://www.bitecode.dev/p/why-not-tell-people-to-simply-use
At this point it kinda feels like spamming, but honestly, there is too much noise out there, and those points don't come across enough. Especially since most dev are either too little or too much experienced to be helpful.