zbyte64

joined 2 years ago
[–] zbyte64@awful.systems 0 points 1 week ago* (last edited 1 week ago)

"If the west doesn't build it then China will" is a claim to a timeline. And in the context of governments, most would assume you're talking about less than 100 years.

[–] zbyte64@awful.systems 23 points 1 week ago (3 children)

Because asking AI to do humans is still uncanny. Pixar and Ghibli was already ruined by AI...

[–] zbyte64@awful.systems 2 points 1 week ago (1 children)

Yes, code harnesses help by providing deterministic feedback like with a language server and reduce the amount of prompting requirements. I guess I should have led with that example 😅

[–] zbyte64@awful.systems 1 points 1 week ago* (last edited 1 week ago) (3 children)

No, it's not the same as copying and pasting the TODO into a prompt. Embedding the TODO in code instead of the prompt reduces tokens burned and increases accuracy because it's observing the TODO in context. Sure you can write more prompting to provide that context, but it still won't be as accurate. The less context you provide via prompting and instead provide more context through automatic deterministc feedback the better the results

[–] zbyte64@awful.systems 2 points 1 week ago (5 children)

Examples to consider:

A code base with TODOs embedded will make fewer mistakes and spend less tokens than if you attempt to direct the LLM only with prompting.

A file system gives an LLM more context than a flat file (or large prompt) with the same contents because a file system has a tree like structure and makes it less likely the LLM will ingest context it doesn't need and confuse it

Lastly consider the efficacy of providing it tools vs using agent skills which is another form of prompting. Giving an LLM a deterministic feedback loop beats tweaking your prompts every time

[–] zbyte64@awful.systems 35 points 1 week ago

Person who sold NFTs is serious about AI. Next it will be quantum

[–] zbyte64@awful.systems 9 points 1 week ago (7 children)

"Properly prompting" is to not prompt. A chat interface is the lowest fidelity interface to use with an LLM.

[–] zbyte64@awful.systems 4 points 2 weeks ago* (last edited 2 weeks ago)

Two things can be true. Still shouldn't hold a teenager wholly responsible for being scammed.

[–] zbyte64@awful.systems 1 points 2 weeks ago* (last edited 2 weeks ago)

That's the point. We should not make our children feel bad for not knowing better when we ourselves aren't doing any better. Show some fucking empathy instead of saying you're shit out of luck.

[–] zbyte64@awful.systems -1 points 2 weeks ago

I do get therapy, thanks for the concern random stranger. I hope the same is true for you and that you understand that just because bad things happened to you doesn't mean we should give such things a free pass and make ourselves emotionally unavailable to empathize with our children.

[–] zbyte64@awful.systems 3 points 2 weeks ago* (last edited 2 weeks ago) (3 children)

Amazing parenting to let them hurt themselves and their friends because you couldn't educate them well enough to avoid a scam.

Edit: I am not saying the parent should have educated the child better, I am just saying when you go down this path of "well you should have known better" then the responsibility is on the parents to teach the kids better.

[–] zbyte64@awful.systems -1 points 2 weeks ago* (last edited 2 weeks ago) (2 children)

Exhibit A for why everyone needs therapy. I guess it's little consolation that people reap what they sow.

view more: next ›