Telegram Group & Telegram Channel
Я редко пишу здесь про новости, но про очередной релиз нового семейства LLM - на этот раз Claude 3 от Anthropic - напишу.

Дело даже не в том, что они утверждают, что побили GPT-4 по метрикам. Это первая модель, которая с первой попытки правильно ответила на вопрос, которым я люблю тестировать LLM-ки: "what manhattan project participant invented the dolphin kick for swimming?" 🐬. Остальные популярные модели (GPT-4, Mistral Large, Llama 2 70B...) или скатываются в галлюцинации (обычно про Фейнмана), или отвечают в духе "уважаемый, там физики работали, какое еще плавание".

Вопрос, конечно, вдохновлен этой книгой. На более нормальные промпты, которые я успел прогнать, кажется, отвечает +- на уровне GPT.



group-telegram.com/partially_unsupervised/215
Create:
Last Update:

Я редко пишу здесь про новости, но про очередной релиз нового семейства LLM - на этот раз Claude 3 от Anthropic - напишу.

Дело даже не в том, что они утверждают, что побили GPT-4 по метрикам. Это первая модель, которая с первой попытки правильно ответила на вопрос, которым я люблю тестировать LLM-ки: "what manhattan project participant invented the dolphin kick for swimming?" 🐬. Остальные популярные модели (GPT-4, Mistral Large, Llama 2 70B...) или скатываются в галлюцинации (обычно про Фейнмана), или отвечают в духе "уважаемый, там физики работали, какое еще плавание".

Вопрос, конечно, вдохновлен этой книгой. На более нормальные промпты, которые я успел прогнать, кажется, отвечает +- на уровне GPT.

BY partially unsupervised


Warning: Undefined variable $i in /var/www/group-telegram/post.php on line 260

Share with your friend now:
group-telegram.com/partially_unsupervised/215

View MORE
Open in Telegram


Telegram | DID YOU KNOW?

Date: |

Stocks closed in the red Friday as investors weighed upbeat remarks from Russian President Vladimir Putin about diplomatic discussions with Ukraine against a weaker-than-expected print on U.S. consumer sentiment. The company maintains that it cannot act against individual or group chats, which are “private amongst their participants,” but it will respond to requests in relation to sticker sets, channels and bots which are publicly available. During the invasion of Ukraine, Pavel Durov has wrestled with this issue a lot more prominently than he has before. Channels like Donbass Insider and Bellum Acta, as reported by Foreign Policy, started pumping out pro-Russian propaganda as the invasion began. So much so that the Ukrainian National Security and Defense Council issued a statement labeling which accounts are Russian-backed. Ukrainian officials, in potential violation of the Geneva Convention, have shared imagery of dead and captured Russian soldiers on the platform. Right now the digital security needs of Russians and Ukrainians are very different, and they lead to very different caveats about how to mitigate the risks associated with using Telegram. For Ukrainians in Ukraine, whose physical safety is at risk because they are in a war zone, digital security is probably not their highest priority. They may value access to news and communication with their loved ones over making sure that all of their communications are encrypted in such a manner that they are indecipherable to Telegram, its employees, or governments with court orders. Pavel Durov, a billionaire who embraces an all-black wardrobe and is often compared to the character Neo from "the Matrix," funds Telegram through his personal wealth and debt financing. And despite being one of the world's most popular tech companies, Telegram reportedly has only about 30 employees who defer to Durov for most major decisions about the platform. The message was not authentic, with the real Zelenskiy soon denying the claim on his official Telegram channel, but the incident highlighted a major problem: disinformation quickly spreads unchecked on the encrypted app.
from br


Telegram partially unsupervised
FROM American