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

Claude 3 model family

anthropic.com

Post reply on HN
Print view View original

571–580 of 723 posts

Re: Claude 3 model family

#571

Post by barfingclouds »

xetplan wrote: post #528
geysersam wrote: post #236

Earlier quoted context omitted.

The guard rails on the models make the llm-market a complete train wreck. Wish we could just collectively grow up and accept that if a computer says something bad that doesn't have any negative real world impact - unless we let it - just like literally any other tool.

I don't disagree but on the other hand, I never run into problems with the language model being censored because I am not asking it to write bad words just so I can post online that it can't write bad words. Both sides in this to me need to get a life.

Yeah I spent a lot of time with Claude 2 and if I hadn’t heard online that it’s “censored,” I wouldn’t have even known. It’s given me lots of useful answers in close to natural human language.

Re: Claude 3 model family

#572

Post by barfingclouds »

rthnbgrredf wrote: post #350

Could anyone recommend an open-source tool capable of simultaneously sending the same prompt to various language models like GPT-4, Gemini, and Claude, and displaying their responses side by side for comparison? I tried chathub in the past, but they decided to not release any more source as of now.

Poe. Poe has Claude 3 right now as well as Gemini pro (not ultra), gpt 4 and 3.5, mistral large, llama, others

Re: Claude 3 model family

#573

Post by chpatrick »

Jensson wrote: post #566
chpatrick wrote: post #560

Earlier quoted context omitted.

The original argument by vineyardmike was "LLMs are a next character predictor, therefore they are not intelligent". I'm saying that as a human you can restrict yourself to a being a next character predictor, yet you can still communicate intelligently. What part do you disagree with?

> I'm saying that as a human you can restrict yourself to a being a next character predictor A smart entity being able to emulate a dumber entity doesn't support in any way that the dumber entity is also smart.

Sure, but the original argument was that next-character-prediction implies lack of intelligence, which is clearly not true when a human is doing it.

That doesn't mean LLMs are intelligent, just that you can't claim they're unintelligent just because they generate one character at a time.

Re: Claude 3 model family

#574

Post by famouswaffles »

Jensson wrote: post #566
chpatrick wrote: post #560

Earlier quoted context omitted.

The original argument by vineyardmike was "LLMs are a next character predictor, therefore they are not intelligent". I'm saying that as a human you can restrict yourself to a being a next character predictor, yet you can still communicate intelligently. What part do you disagree with?

> I'm saying that as a human you can restrict yourself to a being a next character predictor A smart entity being able to emulate a dumber entity doesn't support in any way that the dumber entity is also smart.

You're not emulating anything. If you're communicating with someone, you go piece by piece. Even thoughts are piece by piece.

Re: Claude 3 model family

#575

Post by chpatrick »

evantbyrne wrote: post #564
chpatrick wrote: post #560

Earlier quoted context omitted.

The original argument by vineyardmike was "LLMs are a next character predictor, therefore they are not intelligent". I'm saying that as a human you can restrict yourself to a being a next character predictor, yet you can still communicate intelligently. What part do you disagree with?

I'm not sure what point you think you are making by arguing with the worst possible interpretations of our comments. Clearly intelligence refers to more than just being able to put unicode to paper in this context. The subject matter of this thread was a LLM's inability to perform basic tasks involving analytical reasoning.

No, that's shifting the goalposts. The original claim was that LLMs cannot possibly be intelligent due to some detail of how they output the result ("smarter autocorrect").

Re: Claude 3 model family

#576

Post by Jensson »

famouswaffles wrote: post #574
Jensson wrote: post #566

Earlier quoted context omitted.

> I'm saying that as a human you can restrict yourself to a being a next character predictor A smart entity being able to emulate a dumber entity doesn't support in any way that the dumber entity is also smart.

You're not emulating anything. If you're communicating with someone, you go piece by piece. Even thoughts are piece by piece.

Yeah, I am writing word by word, but I am not predicting the next word I thought about what I wanted to respond and am now generating the text to communicate that response, I didn't think by trying to predict what I myself would write to this question.

Re: Claude 3 model family

#577

Post by wesleyyue »

wesleyyue wrote: post #255
trenchgun wrote: post #242

Earlier quoted context omitted.

How do I change GPT4 to Claude 3 in double.bot?

It's default to claude 3 right now so I could get it out quick, but working on a toggle for the front-end now to switch between the two.

for future readers, the setting is now shipped in >v0.49. The default is now back to GPT-4 as it has lower latency but you can manually change it to Claude 3 in settings if you wish to try out Anthropic's new model.

Re: Claude 3 model family

#578

Post by ricardobeat »

not2b wrote: post #538
sigmoid10 wrote: post #505

Earlier quoted context omitted.

Did you use GPT3.5 for chat? I just tried it on vanilla ChatGPT using GPT4 with no extra stuff and it immediately gets the correct answer: "Sally has 3 brothers, and each of them has 2 sisters. The description implies that Sally's brothers are her only siblings. Therefore, the two sisters each brother has must be Sally and one other sister. This means Sally has just one sister."

But the second sentence is incorrect here! Sally has three siblings, one is her sister, so her brothers are not her only siblings. So ChatGPT correctly gets that Sally has one sister, but makes a mistake on the way.

You meant four siblings? (3 brothers + 1 sister)

Re: Claude 3 model family

#579

Post by chpatrick »

Jensson wrote: post #576
famouswaffles wrote: post #574

Earlier quoted context omitted.

You're not emulating anything. If you're communicating with someone, you go piece by piece. Even thoughts are piece by piece.

Yeah, I am writing word by word, but I am not predicting the next word I thought about what I wanted to respond and am now generating the text to communicate that response, I didn't think by trying to predict what I myself would write to this question.

Your brain is undergoing some process and outputting the next word which has some reasonable statistical distribution. You're not consciously thinking about "hmm what word do I put so it's not just random gibberish" but as a whole you're doing the same thing.

From my point of view as someone reading the comment I can't tell if it's written by an LLM or not, so I can't use that to conclude if you're intelligent or not.

Post reply on HN