Building confidence in Simile | Simile
simile.com · 2,328 words · saved by 1 readers
Behind the scenes into Simile's proprietary confidence model.
Introduction At Simile, we train a model that simulates how an individual or population will act in a particular situation. Our model takes a prompt in natural language that describes the population, situation, and set of valid actions, and it returns a distribution over the actions that the population will take. We train on a variety of data: transactions from grocery stores and delivery apps that show us what people do, and AI-led voice interviews and surveys on our in-house platform that help us understand why they do it. For example, we can ask our model what brand of chips elderly…
saved by
related reading
- Simulating human behavior | Similesimile.com
- Today, we are releasing a research preview of our user model, along with a set of evaluations designed to measure how faithfully user models capture human behavior.persimmon.humansand.ai
- Persimmon v0.1 Model Cardpersimmon.humansand.ai
- Predicting model behavior before release by simulating deployment | OpenAIopenai.com
- confessions_paper.pdfcdn.openai.com
- Predicting LLM Safety Before Release by Simulating Deploymentcdn.openai.com
- gpt-4.pdfcdn.openai.com
- How confessions can keep language models honest | OpenAIopenai.com
- Announcing Our Series Bsimile.com
- AI Model & API Providers Analysis | Artificial Analysisartificialanalysis.ai
- Simulation | Aaruaaru.com
- User awareness in frontier modelstransluce.org