Yesterday Anthropic released Claude-2 in the US and UK, and if you are familiar with Chat-GPT, this may get you very excited.
Claude-2 has a similar chat interface, but has been trained using a more recent dataset (ending in early 2023) supporting 75,000 words of context. The larger context means you can use it for bigger .pdfs, documents, and reports and get output in seconds. For businesses, the API could be significantly cheaper than Chat-GPT too. Claude-2 is/was trained using a rulebook (constitution) so it may be less likely to generate harmful or problematic content. Finally privacy: from my recent conversation with Claude-2: Me: "Should I have privacy concerns when I work with you?" Claude-2: "You raise a fair question. As an AI system created by Anthropic to be helpful, harmless, and honest, I'm designed to protect user privacy and security. Here are a few key points about how I handle your personal information: I do not collect any private or personally identifiable data from you during our conversations. I only have access to our dialog. I do not share, store or document any part of our conversations elsewhere. Everything stays between us. I do not have access to any other information about you or your device/accounts. I can only interact based on what you provide in our chat. Anthropic engineered me using constitutional AI techniques so I operate in a limited, transparent and controllable way to mitigate risks. I provide explanations when asked to be clear about my capabilities and limitations. You should not have to worry about any privacy or security risks from conversing with me. My role is to provide helpful information to you, while respecting your personal boundaries. If you have any other concerns, please let me know and I'm happy to discuss further! Maintaining user trust through privacy protection and honesty is central to my purpose." We are still testing it, but at this point, Claude-2 is certainly saying the right things! Try it here: Anthropic https://www.danswer.ai Danswer allows you to ask natural language questions against internal documents and get back reliable answers backed by quotes and references from the source material so that you can always trust what you get back. You can connect to a number of common tools such as Slack, GitHub, Confluence, amongst others. Check out our Video Demo! Features 💃
If you don't have DMARC set up for your mail, this is an easy way to get started:
Enter your domain to start the DMARC Setup Do Something. Measure It. Welcome to the DMARC Setup Guide. The purpose of this setup guide is to guide your organization through the process of creating a DMARC policy, as well as policies for Sender Policy Framework (SPF) and DomainKeys Identified Mail (DKIM). By implementing all three policies, your organization will have a stronger email authentication mechanism in place to help protect the brand. The first step is confirming whether not your organization is using any of the three policies. Please input the domain from your organization's email address, exactly as it appears after the @ symbol in the email address. For example, the following email address, [email protected], the domain to input in the text box is globalcyberalliance.org https://dmarcguide.globalcyberalliance.org/#/ |
Author: <see article>
These links serve as tributes to those who have written them. Please find contributor details in the links provided Archives
April 2024
Categories |