This combo of speed+intelligence makes 3.5 Haiku a particularly good choice for long context tasks where the model needs to quickly ingest lots of info (e.g. a codebase/financial docs/etc) and provide high-quality outputs. Combined with prompt caching… you get the idea.
@alexalbert__
-
Claude 3.5 Haiku surpasses previous models on coding tasks
By
–
3.5 Haiku surpasses all previous Claude models (except the new 3.5 Sonnet) on coding and agentic tasks, while being significantly more affordable — a fraction of the cost of Sonnet and Opus.
-
Claude 3.5 Haiku Now Available Across Major AI Platforms
By
–
Claude 3.5 Haiku is now available on the Anthropic API, Amazon Bedrock, and Google Cloud's Vertex AI. Claude 3.5 Haiku is our fastest and most intelligent cost-efficient model to date. Here's what makes it special:
-
Questioning Model Choice and Refusal Behavior
By
–
which model are you using here? agree it should not refuse this
-
Anthropic Ships Major Features and Updates Throughout October and November
By
–
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
–
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.
-
Anthropic API Now Supports PDF Documents in Requests
By
–
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
–
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 Visual PDF Support Launch Across Platforms
By
–
It's a big day for Claude's PDF capabilities.
— Alex Albert (@alexalbert__) 1 novembre 2024
We're rolling out visual PDF support across claude dot ai and the Anthropic API.
Let me explain:pic.twitter.com/yYEE6wzPVqIt's a big day for Claude's PDF capabilities. We're rolling out visual PDF support across claude dot ai and the Anthropic API. Let me explain:
-
Community Projects: Open Source Initiative Highlighted
By
–
Not ours! These are the community's. Looks like the top one is open source: