Telegram Group & Telegram Channel
​​gpt-3.5-turbo-instruct умеет играть в шахматы лучше большинства других топовых LLM

Нашёл интересную статью. Автор пробует запускать LLM против Stockfish (один из стандартных ботов для шахмат) на самой низкой сложности. Все модели проиграли... все, кроме gpt-3.5-turbo-instruct. Даже gpt-4o и o1-mini проиграли. Интересно как так получилось.

На ycombinator идёт бурное обсуждение.

#datascience



group-telegram.com/datastorieslanguages/321
Create:
Last Update:

​​gpt-3.5-turbo-instruct умеет играть в шахматы лучше большинства других топовых LLM

Нашёл интересную статью. Автор пробует запускать LLM против Stockfish (один из стандартных ботов для шахмат) на самой низкой сложности. Все модели проиграли... все, кроме gpt-3.5-turbo-instruct. Даже gpt-4o и o1-mini проиграли. Интересно как так получилось.

На ycombinator идёт бурное обсуждение.

#datascience

BY Data, Stories and Languages




Share with your friend now:
group-telegram.com/datastorieslanguages/321

View MORE
Open in Telegram


Telegram | DID YOU KNOW?

Date: |

"There are a lot of things that Telegram could have been doing this whole time. And they know exactly what they are and they've chosen not to do them. That's why I don't trust them," she said. 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. The Security Service of Ukraine said in a tweet that it was able to effectively target Russian convoys near Kyiv because of messages sent to an official Telegram bot account called "STOP Russian War." "There is a significant risk of insider threat or hacking of Telegram systems that could expose all of these chats to the Russian government," said Eva Galperin with the Electronic Frontier Foundation, which has called for Telegram to improve its privacy practices. Asked about its stance on disinformation, Telegram spokesperson Remi Vaughn told AFP: "As noted by our CEO, the sheer volume of information being shared on channels makes it extremely difficult to verify, so it's important that users double-check what they read."
from br


Telegram Data, Stories and Languages
FROM American