LLMS

→ View original post on X — @miketamir

Information Theory Fundamentals for AI and Machine Learning

By

@miketamir

–

01 November 2024 20h01

A brief tutorial on information theory https://
bit.ly/3XPOCcR #AI #MachineLearning #DeepLearning #LLMs #DataScience

Anthropic Ships Major Features and Updates Throughout October and November

By

–

01 November 2024 19h31

The real shiptober (plus one day) was at Anthropic: • 11/1 – Token counting API
• 11/1 – Multimodal PDF support across claude and the API
• 10/31 – Voice dictation in Claude mobile apps
• 10/31 – Claude desktop app
• 10/29 – Claude in Github Copilot
• 10/24 – Analysis tool

Anthropic Releases Free Token Counting Endpoint for API

By

–

01 November 2024 19h06

There's finally an easy way to count tokens with the Anthropic API. With our new token counting endpoint, you can send a request and get a token count back in response. This endpoint is free to use and doesn't affect your normal rate limits.

→ View original post on X — @alexandr_wang

Advanced AI Models Need World’s Expert Collaboration

By

@alexandr_wang

–

01 November 2024 18h13

AI models are getting smarter. o1 was a major breakthrough, and we don't expect that to stop. What's needed today are the world's most advanced experts (doctors, lawyers, PhDs, professionals) to help provide their expertise in advancing the models towards the frontier.

Anthropic API Now Supports PDF Documents in Requests

By

–

01 November 2024 17h55

We are also rolling out the ability to send Claude PDFs in the Anthropic API. With our new PDF support beta, you can directly include a PDF in your API request. For more details on how this works, check out our docs:

Claude now visually processes PDFs with text extraction

By

–

01 November 2024 17h55

Up until today, when you attached a PDF in claude dot ai, we would use a text extraction service to grab the text and send that to Claude in the prompt. Now, Claude can actually see the PDF visually alongside the text.

Claude’s Enhanced Ability to Analyze Complex Documents with Visual Content

By

AI Dynamics

–

01 November 2024 17h55

This allows Claude to more accurately understand complex documents, such as those laden with charts or graphics that aren't representable in text.

For example, I can now ask Claude questions about this PDF full of anatomy diagrams. pic.twitter.com/xEshVNmf87
— Alex Albert (@alexalbert__) 1 novembre 2024

This allows Claude to more accurately understand complex documents, such as those laden with charts or graphics that aren't representable in text. For example, I can now ask Claude questions about this PDF full of anatomy diagrams.