🍓 o1 ака Strawberry уже тут. Все подробности

Модель разрывает своего предшественника gpt-4o на "reasoning-heavy tasks".

Доступна всем пользователям подписки Plus. Если у вас еще не добавлена, попробуйте эту ссылку и кнопку "Try it in ChatGPT Plus"

– Документация
– Блог-пост
– System Card PDF

🍓 Советы по промтингу новой модели:

Keep prompts simple and direct: The models excel at understanding and responding to brief, clear instructions without the need for extensive guidance.

Avoid chain-of-thought prompts: Since these models perform reasoning internally, prompting them to "think step by step" or "explain your reasoning" is unnecessary.

Use delimiters for clarity: Use delimiters like triple quotation marks, XML tags, or section titles to clearly indicate distinct parts of the input, helping the model interpret different sections appropriately.

Limit additional context in retrieval-augmented generation (RAG): When providing additional context or documents, include only the most relevant information to prevent the model from overcomplicating its response.

💰 Цены на API

o1-preview – $15.00 / 1M input tokens $60.00 / & 1M output tokens
o1-mini – $3.00 / 1M input tokens & $12.00 / 1M output tokens

While reasoning tokens are not visible via the API, they still occupy space in the model's context window and are billed as output tokens.

🚫 Лимиты

o1-preview – 30 сообщений/ неделя
o1-mini – 50 сообщений/ неделя
Модели через API – 20 сообщений в минуту

☝️ Примеры использования

– routine generation
– data validation

Прочее/ Полезности

– Devin уже работает на o1
– Пост Greg Brockman
– Статья Ethan Mollick

@how2ai #o1 #chatgpt