Should have set the effort level to “high”

I’d like to think I taught my child to lie better

The elephant’s name? Luigi.

They also believe a rock can think like a human so…

This is SpaceX so I assume they meant cybertruck

So you’re saying it was Space Jesus?

Antisocial people develop an antisocial AGI promising it won’t be antisocial towards a select group. Surprised Pikachu when the AGI concludes they are not in the in group

“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.

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

Considering it was under Mao that Xi’s family was exiled it is a rather salient comparison.

Edit: and we can know how much power Mao had by how big of a power vacuum he left. The fact of the matter is it is a single party republic, and that’s why Mao was replaced with someone more sensible. If there was a sizable power vacuum things would not have turned out this way.

I mean at least 1/3 of Americans say it’s why we have the 2nd amendment. And 2/3 of the Supreme Court would likely agree, just they wouldn’t admit we are at that point where it is necessary. It’s ingrained in our culture down to the American revolution. But yeah, whenever leftist groups arm themselves they get wiped out, see the Black Panthers as an example.

Xi has no more absolute power over the government than Mao had (who was forced to step aside). And saying it is in no way democratic is patently false considering all their politicians need to be elected in at the local level. Lastly, Xi’s family was exiled from Beijing and they survived only to have Xi become the leader.

Psychedelics doesn’t magically make a bad person into a good person, just look at Joe Rogan. Though I am all for putting the entire admin deep into a k-hole that they will never escape from

Yeah, it’s only our fault if they die a peaceful death instead of going to trial

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 😅

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

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

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

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

I’m sure they will find away. I heard they are going to use robots to make the food, imagine the markups!