Anthropic Introduces Claude 2.1 With 200K Context Window

Artificial intelligence startup Anthropic has released Claude 2.1, an upgraded version of its conversational AI assistant, touting significant improvements in areas like context length, accuracy, and integration capabilities.

200K Context Window

Claude 2.1 can now process up to 200,000 context tokens, equivalent to around 150,000 words or 500 pages of text content. That’s twice as much as its previous token limit.

This allows users to upload and analyze entire technical documents, lengthy financial reports, or even long literary works.

Claude 2.1 aims to provide better summaries, question answering, trend forecasting, and other insights compared to the previous version by taking in more contextual information.

However, processing such long messages slows response times to a few minutes. Anthropic expects speeds to improve over time.

Additional Claude 2.1 Features

In addition to the larger context window, Claude 2.1 boasts a two-times reduction in false or hallucinated statements, enhancing reliability for real-world applications across enterprises.

Specific use cases could include processing complex legal briefs or parsing lengthy technical specifications.

The upgrade also introduces early support for tool use, letting developers connect Claude to existing company APIs, databases, and web services.

The goal is to enable Claude to orchestrate and automate workflows by leveraging these existing processes and information sources.

For example, Claude 2.1 might answer a question by querying a private database rather than guessing, translating natural language requests into API calls, or pull product data to help users complete an online purchase.

This expanded interoperability aims to make Claude more useful for day-to-day business operations, although the tool use feature remains in beta.

On the developer side, the newly revamped console includes a “Workbench” for easily iterating on prompts, plus code snippet generation for Claude API integration.

There are also new settings and instructions, dubbed system prompts, to customize Claude’s tone, personality, and response structure as needed.

Pricing For Claude 2.1 Features

The Claude 2.1 upgrade is already live for Anthropic’s hosted chatbot interface at claude.ai and the paid Claude Pro API tier.

The 200,000 token context limit is exclusive to Pro users for now on its website, similarly priced to the (currently paused) ChatGPT Plus subscription at $20/month.

Perplexity Pro subscribers can also use Claude 2.1 by changing the model used in Settings. The platform is also offering two months for free for those who want to give it a try.

claude 2.1 perplexity pro accessScreenshot from Perplexity, November 2023

Claude 2.1 could come to Poe for premium subscribers as well.

poe claude Screenshot from Poe, November 2023

If so, you may be able to use it as the “base bot” for the create bot feature, which works similarly to custom GPTs. If you can’t get a ChatGPT Plus subscription, you can try this as an alternative with Claude 2 or other popular models.

poe bot claudeScreenshot from Poe, November 2023

If you want to build AI products with Claude 2.1, the pricing has been updated to include the newest model.

anthropic model pricingScreenshot from Anthropic, November 2023

System Prompts

In addition to the new version of Claude 2.1, Anthropic introduced system prompts.

A system prompt allows users to provide Claude with customized instructions and context to improve its performance for specific tasks.

Anthropic Introduces Claude 2.1 With 200K Context WindowScreenshot from Anthropic, November 2023

System prompts allow users to set goals, specify Claude’s persona or tone, establish rules and constraints, supply relevant background knowledge, and define standards for verifying outputs.

By prompting Claude in this way, users can shape more accurate, consistent responses that stay in character for role-playing and more reliably follow provided guidelines.

System prompts ultimately aim to enhance Claude’s capabilities for intended real-world applications.

Advancing AI

Founded in 2021, Anthropic develops AI assistant technology focused on safety, honesty, and control. It recently received an investment of $4 billion from Amazon to continue advancing AI with more capable models.


Featured image: Tada Images/Shutterstock


source
The article is sourced from the internet. Click the “Source” button to view the original content. If there is any copyright infringement, please contact our team for removal.

Share this article
Shareable URL
Prev Post

Founders: Pay attention to what happened with OpenAI’s board

Next Post

Mykolas Romeris University leads higher-education innovations for global sustainability

Read next
Subscribe to our newsletter
Get notified of the best deals on our WordPress themes.