Remix clone Hacker News

I don't think it will be as massive as you and a lot of people think.

The problem is reliability,you can't bulid of unstable foundations.

We would need some kind of library of "verified sentences" in LLMs, like facts verified by experts for them to be useful for a tons of stuff.

Right now if you are using LLMs for anything else that is not verifiable in a objective way (like programming, a program works or does not [let's not even talk efficency or security]) or fluff (generating fancy text for non crucial reasons) you are using a tool wrong.

▲

simonw 4 days ago | parent | next [-]

If you want to work with verified facts, feed those facts in as part of your prompt. Most good LLMs accept 100,000 tokens now, and some accept 1,000,000+.

▲

Sateeshm a day ago | parent [-]

There is still no guarantee that what comes out will be fact based.

	▲	simonw a day ago \| parent [-]
		Right, if you want guarantees of anything you don't want statistical machine learning models. In practice, I've found that the risk of LLMs hallucinating against well chosen context in low enough that I rarely worry about it.

▲

rohansood15 4 days ago | parent | prev | next [-]

That's not true. The Internet was inherently unreliable for a long time—connection drops, packet losses, hardware failures—but that didn't stop it from being a platform for incredible value.

You can build valuable, reliable systems on top of unreliable foundations. That's how humanity has progressed over the centuries.

	▲	Iulioh 4 days ago \| parent [-]
		It's still unreliable because humans are but a human lying or saying incorrect things is different from an AI confidently doing it. First of all humans or websites have reputations, with GPT you just hit refresh and you are talking to a entirely different entity and everything they said is gone. I feel like there's a difference.

▲

jajko 4 days ago | parent | prev [-]

Yeah we are seeing a massive hype wave, with tons of folks trying new ideas and startups and obviously place like HN can make you feel a massive revolution across whole mankind is happening, on at least the level of internet coming. Novelty for most folks will eventually wear off though, this ain't cute cats videos level of continuous interest for the masses, i'd say more like wikipedia, now its just the place to get some unbiased info.

When reality is you get a bit smarter assistant than ever before, still not very trustworthy but already can be saving some time if used right. Good luck hearing this ever from folks riding that hype wave.

	▲	ryandrake 3 days ago \| parent [-]
		Definitely a hype wave, and we've seen these things come and go before. Crypto, NFTs, Blockchain, Virtual Assistants, Autonomous Vehicles, Wearables, Big Data, VR/AR, 3D TV. In five years, we'll be able to add LLMs/AI to the list. I'm sure if we look, we can find a five year old HN post that starts out: "My work is already massively transformed via crypto. Pretty much everything I do starts with an interaction with a blockchain."