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

131–140 of 723 posts

Re: Claude 3 model family

#131

Post by hobofan »

Alifatisk wrote: post #19

I hate that they require a phone number but this might be the only way to prevent abuse so I'll have to bite the bullet. > We’ve made meaningful progress in this area: Opus, Sonnet, and Haiku are significantly less likely to refuse to answer prompts that border on the system’s guardrails than previous generations of models. Finally someone who takes this into account, Gemini and chatGPT is such an obstacle sometimes…

I think you interpreted that wrong.

Less refusals than "previous generations of models" presumably means that is has less refusals than _their_ previous generations of models (= Claude 2), which was notorious for being the worst in class when it came to refusals. I wouldn't be surprised if it's still less permissive than GPT-4.

Re: Claude 3 model family

#132

Post by msp26 »

vermorel wrote: post #28

Does any of those LLM-as-a-service companies provide a mechanism to "save" a given input? Paying only for the state storage and the extra input when continuing the completion from the snapshot? Indeed, at 1M token and $15/M tokens, we are talking of $10+ API calls (per call) when maxing out the LLM capacity. I see plenty of use cases for such a big context, but re-paying, at every API call, to re-submit the exact sam…

> I see plenty of use cases for such a big context, but re-paying, at every API call, to re-submit the exact same knowledge base seems very inefficient.

If you don't care about latency or can wait to set up a batch of inputs in one go there's an alternative method. I call it batch prompting and pretty much everything we do at work with gpt-4 uses this now. If people are interested I'll do a proper writeup on how to implement it but the general idea is very straightforward and works reliably. I also think this is a much better evaluation of context than needle in a haystack.

Example for classifying game genres from descriptions.

Default:

[Prompt][Functions][Examples][game description]

- >

{"genre": [genre], "sub-genre": [sub-genre]}

Batch Prompting:

[Prompt][Functions][Examples][description][description][description]...

- >

{"game1": {...}, "game2": {...}, "game3": {...}, ...}

Re: Claude 3 model family

#133

Post by 2c2c2c »

kylebenzle wrote: post #105
jimbokun wrote: post #93

If you showed someone this article 10 years ago, they would say it indicates Artificial General Intelligence has arrived.

1. It's an advertisement/press release, not so much an "article". 2. This would NOT be called even "AI" but "machine learning" 10 years ago. We started using AI as a marketing term for ML about a year ago.

I can recall AI being used to describe anything involving neural nets by laymen since google deepmind. approaching 10 years

Re: Claude 3 model family

#135

Post by jasondclinton »

virgildotcodes wrote: post #68

Just signed up for Claude Pro to try out the Opus model. Decided to throw a complex query at it, combining an image with an involved question about SDXL fine tuning and asking it to do some math comparing the cost of using an RTX 6000 Ada vs an H100. It made a lot of mistakes. I provided it with a screenshot of Runpod's pricing for their GPUs, and it misread the pricing on an RTX 6000 ADA as $0.114 instead of $1.14.…

Hi, CISO of Anthropic here. Thank you for the feedback! If you can share any details about the image, please share in a private message.

No LLM has had an emergent calculator yet.

Re: Claude 3 model family

#136

Post by uoaei »

Workaccount2 wrote: post #125
anonymouse008 wrote: post #87

Earlier quoted context omitted.

I'm convinced GPT is running separate helper functions on input and output tokens to fix the 'tokenization' issues. As in, find items of math, send it to this hand made parser and function, then insert result into output tokens. There's no other way to fix the token issue. For reference, Let's build the GPT Tokenizer https://www.youtube.com/watch?v=zduSFxRajkE

I'd almost say anyone not doing that is being foolish. The goal of the service is to answer complex queries correctly, not to have a pure LLM that can do it all. I think some engineers feel that if they are leaning on an old school classically programed tool to assist the LLM, it's somehow cheating or impure.

Of course. But we must acknowledge that many have blinders on, assuming that scale is all you need to beat statistical errors.

Re: Claude 3 model family

#137

Post by trenchgun »

wesleyyue wrote: post #62

Just added Claude 3 to Chat at https://double.bot if anyone wants to try it for coding. Free for now and will push Claude 3 for autocomplete later this afternoon. From my early tests this seems like the first API alternative to GPT4. Huge!

Very nice!

Re: Claude 3 model family

#138

Post by brookst »

behnamoh wrote: post #119
jimbokun wrote: post #93

If you showed someone this article 10 years ago, they would say it indicates Artificial General Intelligence has arrived.

That's the good thing about intelligence: We have no fucking clue how to define it, so the goalpost just keeps moving.

Intelligence is tough but tractable. Consciousness / sentience, on the other hand, is a mess to define.

Re: Claude 3 model family

#139

Post by egeozcan »

addandsubtract wrote: post #94
egeozcan wrote: post #47

Earlier quoted context omitted.

AFAIK there's no strict EU ban but no EU country is listed here: https://www.anthropic.com/claude-ai-locations Perhaps you meant Europe the continent or using a VPN? edit: They seem to have updated that list after I posted my comment, the outdated list I based my comment on: https://web.archive.org/web/20240225034138/https://www.anthr... edit2: I was confused. There is another list for API regions, which has all EU c…

They updated the list of supported countries here: https://www.anthropic.com/supported-countries I was just able to sign up, while not being able to a few weeks ago.

Oh well, it seems to have updated after my comment. Now it seems they support the whole EU and many more additional countries.

But it still errors out when trying to sign up from Germany:

https://i.imgur.com/rX0XA8d.jpeg

https://i.imgur.com/Xlyqm8D.jpeg

Re: Claude 3 model family

#140

Post by KoolKat23 »

behnamoh wrote: post #116
virgildotcodes wrote: post #68

Just signed up for Claude Pro to try out the Opus model. Decided to throw a complex query at it, combining an image with an involved question about SDXL fine tuning and asking it to do some math comparing the cost of using an RTX 6000 Ada vs an H100. It made a lot of mistakes. I provided it with a screenshot of Runpod's pricing for their GPUs, and it misread the pricing on an RTX 6000 ADA as $0.114 instead of $1.14.…

When OpenAI showed that GPT-4 with vision was smarter than GPT-4 without vision, what did they mean really? Does vision capability increase intelligence even in tasks that don't involve vision (no image input)?

Yes. They increase the total parameters used in the model and adjust the existing parameters.
Post reply on HN