We are thrilled to announce the official launch of Senti, our AI assistant to answer all your questions about animal ethics, wild animal suffering, and longtermism!
The talented team at Freeport Metrics gave us extensive pro bono services and support to bring Senti to you. They built the infrastructure, handled the technical aspects of the setup, and designed the beautiful UI. We prepared and added our documents, and then they did extensive testing using a wide array of question types, giving us the opportunity to tweak whatever we needed to along the way. They have also offered to continue to provide support. Thank you, Freeport Metrics! We could not have done it without you.
Senti is powered by Claude, Anthropic’s large language model (LLM), but reflects our views, not theirs. We provided Senti with a database of carefully curated documents about animal ethics and related topics. Almost all of them were written by Animal Ethics, and we are now adding more sources. When you ask a question, Senti searches through the documents and retrieves the most relevant information to form an answer. After each answer, there are links to the sources of information so you can read more. We continually update Senti, and we’d love to have your feedback on your experience!
Not sure what to ask? Choose from 24 preset questions and continue to follow the thread as Senti suggests new questions.
Senti rarely discusses topics that are not related to the wellbeing of all sentient beings, and we ask that you restrict your conversations to those related to helping animals and other sentient beings. When you chat with Senti for the first time, you’ll be presented with a consent form. It requests permission to save your conversation history. Saving your conversation history allows you and Senti to have a continuous conversation, with Senti remembering what you’ve already discussed. It also provides us with your chat history, which is anonymous. This will help us to improve the answers and know what new information to add. You do not have to give your consent in order to chat with Senti. If you decline, your chat history won’t be saved but you can still ask questions.
We also give our heartfelt thanks to the small dedicated team of volunteers who have been helping test new prompts, new document sets, and different settings such as how many pieces of information to retrieve in order to respond to each question. Senti is built and tested on Claude 2.0, but we’ve been running independent tests with the new Claude 3 models. So far, the results are good. We expect to deliver an update in the coming months that provides longer and more accurate responses.
We hope Senti helps you learn a lot and makes it easier for you to share the information with others. Thanks for sharing our concern for the wellbeing of all sentient beings.