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

461–470 of 860 posts

Re: Llama 2

#461

Post by eigenvalue »

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…

As a comparison, here is how ChatGPT with GPT4 answers the exact same question-- the response is much more complete, written in a better style, and by far the most important, doesn't make a big factual error:

https://chat.openai.com/share/e3ced12d-2934-4861-a009-e035bf...

Re: Llama 2

#462

Post by visarga »

galaxyLogic wrote: post #106
lacker wrote: post #78

Earlier quoted context omitted.

I think Google or Microsoft probably would want to use LLaMa for various purposes like benchmarking and improving their own products. Check out this other condition from the license: v. You will not use the Llama Materials or any output or results of the Llama Materials to improve any other large language model (excluding Llama 2 or derivative works thereof). https://github.com/facebookresearch/llama/blob/main/LICENS…

I can see their business logic but isn't it a bit like do not allow people (or bots) talk to each other, they might all get smarter. I understand trade-secrets are not free-speech but if the goal is to build better AI to serve the humanity the different bots should learn from each other. They should also criticize each other to find flaws in their thinking and biases.

There are many datasets created by scraping chatGPT and they seem to work out pretty well. In other words, LLM skills are leaky.

Re: Llama 2

#463

Post by b33j0r »

andsoitis wrote: post #348
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…

> 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?”

Re: Llama 2

#464

Post by ilaksh »

villgax wrote: post #267
RobotToaster wrote: post #41

Another AI model pretending to be open source, when it's licence violates point 5 and 6 of the open source definition.

Exactly- You will not use the Llama Materials or any output or results of the Llama Materials to improve any other large language model (excluding Llama 2 or derivative works thereof).

Ok but that means that theoretically you could actually use Llama 2 to create fine tuning data for Llama 2 right?

Re: Llama 2

#466

Post by ilaksh »

brucethemoose2 wrote: post #376
Dowwie wrote: post #365

Prompt: 5 Ounce (Pack of 6) is $33. 4 ounce pack of 6 is 15. which is the better deal? Llama 2: The 5 ounce pack of 6 is the better deal. It costs 33for6packs,whichis33for6packs,whichis5.50 per pack. The 4 ounce pack of 6 costs 15for6packs,whichis15for6packs,whichis2.50 per pack. So, the 5 ounce pack of 6 is the better deal. ChatGPT4: To figure out the best deal, we need to calculate the price per ounce for each opti…

Which one is that? 70b chat?

Have you seen a hosted 70b Llama 2?

Re: Llama 2

#467

Post by andrelaszlo »

jstummbillig wrote: post #269
andrelaszlo wrote: post #255

llama2.ai seems to hallucinate quite a lot. Q: Can you list all even prime numbers less than or equal to 59? A: Sure! The even prime numbers less than or equal to 59 are: 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30, 32, 34, 36, 38, 40, 42, 44, 46, 48, and 50. Is there something else I can help you with? Q: Who is [random name]? A: [name] is a computer scientist and entrepreneur who is known for his work in…

Wait, did you actually write "[random name]"?

My name. Which was drawn by my parents from a hat, I've been told.

Re: Llama 2

#469

Post by nomel »

koonsolo wrote: post #455
xsmasher wrote: post #400

Earlier quoted context omitted.

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

With ChatGPT I sometimes prompt "also indicate how certain you are that your answer is correct". Works pretty good actually.

I've had very good luck with a follow up "Is that answer correct?"

Re: Llama 2

#470

Post by canttestthis »

jug wrote: post #290
Jaygles wrote: post #285

Earlier quoted context omitted.

Google says that swimming is "the sport or activity of propelling oneself through water using the limbs". It doesn't constrain the propulsion to only be between the limbs and the water. Seems like pushing against the ground to move through the water fits the definition

General consensus if you ask about it is that it's not considered swimming though. I think you'd be looking for locomotion through water without frequent touch downs. This is an example: https://www.nationalgeographic.com/animals/mammals/facts/hip... GPT-4 had a much better answer last I checked. Edit: Updated with another non-paywall link.

After having reviewed the relevant material I think it's fair to say that hippos swim, per our conventional understanding of what swimming is.
Post reply on HN