Comments URL: https://news.ycombinator.com/item?id=44044350

Points: 1

# Comments: 0

If they abstract all this away into one interface I won't know which model I'm getting. I prefer reliability.

For example the rhyming example brings to mind a feature where you give the model starting input and ending input and ask it to fill in.

Can not only imagine it being useful in that sense, but for ways at retroactively arriving at some answer, or solution or something. Like the causal chain that leads to a specific answer.

Another idea is to show all possible word variations, and then the middle is rewritten based on the chosen word.

It's not like "Oh their quality of life is exactly the same as in the US it's just cheaper! So it's totally fine for us to pay them peanuts! Right? Peanuts buy you a house there... I mean the house has no plumbing but it's a house!" No, their quality of life is absolute crap compared to first world countries (as someone from a third world country). And paying them like shit will only prolong their suffering.

The least the company could do is pay them fairly which means they can travel or live a better quality life.

GPT-4o will never offhand, unprompted and 'unprimed', suggest a rare but relevant book like Shinichi Nakazawa's "A Holistic Lemma of Science" but a base model Mixtral 8x22B or Llama 405B will. (That's how I found it).

It seems most of the RLHF'd models seem biased towards popularity over relevance when it comes to recall. They know about rare people like Tyler Volk... but they will never suggest them unless you prime them really heavily for them.

Your point on recommendations from humans I couldn't agree more with. Humans are the OG and undefeated recommendation system in my opinion.

I know Worldcat has something like this when you search for a book, but the API, I assume is only for library institutions and I'm not a library nor an institution.

All I want to do is talk to my computer, like:

"Sort these files" or whatever. Straight away. No noise.

And it should have a history of what was done already, so it knows what I'm talking about.

If people are concerned about safety, it could just be a 'mode' or an app that isn't a terminal but looks like a terminal.

The brain does saturate eventually and gets bored. Then the crisis of meaning. Then something meaningful emerges.

We’re all gonna die. Let’s just enjoy life to the fullest.

One idea I had is everyone is paid a thriving wage, and in exchange, if they in the future develop their passion into something that can make a profit, they pay back 20% of their profits they make up to some capped amount.

This allows for extreme generality. It truly frees people to pursue whatever they fancy every day until they catch lightning in a bottle.

There would be 0 obligation as to what to do, and when to pay back the money. But of course would have to be only open to honest people, so that neither side is exploiting the other.

Both sides need a sense of gratitude, and wanting to give back. A philanthropic 'flair' "If it doesn't work out, it's okay", and a gratitude and wanting to give back someday on the side of the receiver, as they continue working on probably the most resilient thing they could ever work on (the safest investment), their lifelong passion.