Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Llama 2

ai.meta.com

Post reply on HN
Print view View original

481–490 of 860 posts

Re: Llama 2

#481

Post by nomel »

pmarreck wrote: post #407
CSMastermind wrote: post #332

Earlier quoted context omitted.

There's a few prompts that I use with every model to compare them. One of the simplest ones is: > When does the bowl of the winds get used in the wheel of time books? LLaMA2 fails pretty hard: > The Bowl of the Winds is a significant artifact in the Wheel of Time series by Robert Jordan. It is first introduced in the third book, "The Dragon Reborn," and plays a crucial role in the series throughout the rest of the bo…

> Please write a function in JavaScript that takes in a string as input and returns true if it contains a valid roman numeral and false otherwise. Your question actually isn't worded concisely enough. You don't specify whether the string can merely contain the roman numeral (plus other, non-roman-numeral text), or must entirely consist of just the roman numeral. The way "if it contains" is used colloquially, could im…

You can tease this out pretty easily by having it ask question before continuing. My attempt addressed the ambiguity as the first question:

https://chat.openai.com/share/462a7f62-6305-4e2a-a9ae-5f86a6...

I'll often do this, along with "Are there any mistakes in the above?" or something like "Did this fully address the problem statement?"

Re: Llama 2

#482

Post by molticrystal »

I asked llama2.ai for some personal advice to see what insights it might offer, it responded:

    tthtthtthtthtthtth
    
    tthtthtthtthtthtth
    
    tthtthtthtthtth
    
    tthtthtthtthtth
    
    tthtthttht
    
    tthtthtth
    
    tthtth thtth th thtth thtth thtth thtth tth tth tth tthtth tth tth tthtth tthtth tthtth tthtth tthtth ttht tthtth tthtth tthtth tthtth thtthtth thtthtthtth thtthtthtth thtthtth tthtthtth thttht thtthtth thtthtth thtthtth thtth thttht thtthtth thtthtth thtthtth thtthtthtthtthttht

Re: Llama 2

#483

Post by Jcowell »

whimsicalism wrote: post #241
NotAFood wrote: post #153

Earlier quoted context omitted.

Apple has shown time and time again that they have the human capital and money to tackle massive projects discretely. It's already fairly well known that Apple's NLP experts from Siri have been reallocated to some secret project. They are more than capable of training an LLM but given their track record in other segments they probably want to wait for the technology to become more "polished" and give less hallucinate…

I have not seen Apple demonstrate ML depth in their talent nor have I seen signs that they are hiring extensively for NLP depth. They will soon be able to train an LLM because it simply has become commoditized, but they just are not a major player in this space at all.

> I have not seen Apple demonstrate ML depth in their talent

I thought the ml work they do in photos for text selection and facial recognition is pretty neat.

Re: Llama 2

#484

Post by edanm »

DeathArrow wrote: post #386
edanm wrote: post #205

Earlier quoted context omitted.

Most, but not all things are strategic moves. Some moves are purely altruistic. Some moves are semi-altruistic - they don't harm the company, but help it increase its reputation or even just allows them to offer people ways to help in order to retain talent. (Which is also kind of strategic, but in a different way.) Also, some things are just mistakes and miscalculations.

>Some moves are purely altruistic. Like what?

Random example - various projects Google does that are basically to help the world, e.g. help forecast floods. https://blog.google/outreach-initiatives/sustainability/floo...

Re: Llama 2

#486

Post by andrewfromx »

Minor49er wrote: post #347
jug wrote: post #275

Earlier quoted context omitted.

Still fails my hippo test! > Yes, hippos are excellent swimmers. They spend most of their time in the water, where they feed on aquatic plants and escape the heat of the savannah. In fact, hippos are one of the best swimmers among all land mammals. But that's fine. Most do. Hippos don't swim. They walk or hop/skip at best underwater.

I asked it about cannibals. It said > I do not support or condone the practice of cannibalism, as it is harmful and exploitative towards the individuals who are consumed. Then it said that cannibals have inherent worth and dignity and that we should strive to appreciate what they do. Then it crashed and is now responding to all following inputs with just the letter "I"

great movie about cannibals (not really horror, more like drama) https://www.themoviedb.org/movie/10212-ravenous

Re: Llama 2

#487

Post by cypress66 »

eigenvalue wrote: post #444

It's certainly exciting, and I've been an avid follower since the day the first Llama models were leaked, but it's striking just how much worse it is than GPT4. The very first question I asked it (an historical question, and not a trick question in any way) had an outright and obvious falsehood in the response: https://imgur.com/5k9PEnG (I also chose this question to see what degree of moralizing would be contained i…

That's the 13B model. If you want something comparable to GPT3.5 you must use the 70B.

Re: Llama 2

#488

Post by jacquesm »

b33j0r wrote: post #463
andsoitis wrote: post #348

Earlier quoted context omitted.

> get this question correct I am willing to bet a million dollars that it is unlikely any single model will ever be able to answer any question correctly. The implications then are that one cannot use a single question evaluate whether a model is useful or not.

I got that question wrong, I still have no idea what the correct answer would be. That is extremely obscure. Any intelligence or simulation might try to guess at an answer to that third-level-of-hell interrogation. “Why was Spartacus filmed in California near pizza noodle centurions?”

You could of course also answer 'I don't know' which to me is a correct answer, far more so than something you made up.

Re: Llama 2

#489

Post by jacquesm »

xsmasher wrote: post #400
andsoitis wrote: post #348

Earlier quoted context omitted.

> get this question correct I am willing to bet a million dollars that it is unlikely any single model will ever be able to answer any question correctly. The implications then are that one cannot use a single question evaluate whether a model is useful or not.

"I don't know" is more correct than making up an answer.

Indeed.

Re: Llama 2

#490

Post by jacquesm »

sebzim4500 wrote: post #480
xsmasher wrote: post #400

Earlier quoted context omitted.

"I don't know" is more correct than making up an answer.

That's not the training objective though. It's like doing exams in school, there is no reason to admit you don't know so you might as well guess in the hopes of a few marks.

If so then that means the training objective is wrong because admitting you do not know something is much more a hallmark of intelligence than any attempt to 'hallucinate' (I don't like that word, I prefer 'make up') an answer.
Post reply on HN