Latest press articles for Synthetic Users
Synthetic Users and AI are transforming research methodologies, offering innovative, cost-effective alternatives to traditional human subject studies.
A revolution in the way we conduct qualitative and quantitative research is underway. It's not here to replace organic research but to complement it. Here are just four articles that paint the vision we are working on, whilst mentioning our work and company directly (thank you!). Every company will have their own Synthetic Users, who will pro-actively help shape product and marketing by allowing us to make better decisions.
Researchers Have Replaced Humans with Machines for Social Sciences Surveys
A recent study from Brigham Young University revealed that AI could replace humans in polls, marketing studies, and sociological surveys by posing questions to AI models representing specific socio-economic profiles. This concept, supported by synthetic users, showed AI responses matching the distribution of U.S. election votes over several years. However, a French research team from the Center for Research in Economics and Statistics cautioned against this, finding that AI models often produced skewed and less diverse responses compared to humans. Despite these limitations, Hugo Alves, co-founder of Synthetic Users, remains optimistic about using AI for qualitative studies, emphasizing their ability to imitate desired profiles and enhance diversity. This ongoing exploration into AI's role in social science research highlights both potential and challenges.
GUINEA PIGBOTS
Doing research with human subjects is costly and cumbersome. Can AI chatbots replace them?
The article from Science discusses the use of LLMs, in replacing human subjects for behavioral experiments. Researchers found that these AI models can simulate human responses with significant accuracy, potentially revolutionizing social science research. However, there are concerns about biases from training data and the AI's tendency to "hallucinate" information. Despite these challenges, Synthetic Users and similar AI applications show promise in providing diverse, cost-effective, and rapid insights into human behavior, though careful bias management is crucial.
Shapes and frictions of synthetic data
The SAGE journal article discusses the rise and implications of synthetic data, which are computer-generated datasets that mimic real-world data without directly corresponding to actual phenomena. Widely used in privacy protection, machine learning, and simulations, synthetic data is gaining traction in social sciences, including government applications like the US Census. The paper argues for a shift from traditional data representation models to relational models, where data are defined by their use, purpose, and context. Synthetic Users, an AI startup, exemplifies this trend by offering "user research without users," using large language models to generate simulated user feedback. This approach, while addressing privacy concerns and biases, also introduces new challenges related to data accuracy and trust. The article calls for a critical examination of synthetic data through a relational lens, emphasizing the importance of context and purpose in understanding and utilizing these datasets.
🔗 https://journals.sagepub.com/doi/10.1177/20539517241249390
Return of the People Machine
No one responds to polls anymore. Researchers are now just asking AI instead.
The Atlantic article explores AI's potential to replace traditional polling methods through simulated human responses using LLMs. Brigham Young University researchers found AI effective in predicting voter behavior, offering a cost-effective alternative. However, experts warn that AI, while useful for trend analysis, can't fully replace human input due to outdated data and internet biases. Hugo Alves, co-founder of Synthetic Users, is optimistic about using AI for qualitative studies, emphasizing the role of artificial panels in enhancing data diversity.
🔗https://www.theatlantic.com/technology/archive/2023/04/polls-data-ai-chatbots-us-politics/673610/
Releated Articles
More articles for you
Teaching Synthetic Users What Real People Actually Think
Synthetic Users without calibration are individually believable, but collectively wrong. The missing piece is calibration, not better models.
The Lie We Tell Ourselves About Customer Research
Most research asks what people say. The problem is people don't do what they say. This piece breaks down the gap between stated and revealed preference — and why behavioral modeling, not better interviews, is how you close it.
Two ways to run research with Synthetic Users and why the difference matters
Iris, what is the difference of using agents to accelerate research.
Synthetic Users vs digital twins
You don’t need a twin for “a parent in rural Ohio who shops weekly at Walmart, prefers fragrance-free, and has a toddler with eczema.” You sample a parent profile with relevant traits and constraints, add retail and dermatology context, and generate behaviors consistent with both.
Two major papers. One shared direction.
LLM-powered Synthetic Users have crossed from concept to validated method. This proves they can predict human behavior accurately, letting teams run fast, low-cost behavioral experiments without replacing real participants.
Gartner says we lead. That's kind of them.
Gartner’s latest report on AI-powered synthetic user research cites Synthetic Users as a leader.
Introducing Shuffle v2
Shuffle v2 is a feature that intelligently shuffles between multiple large language models via a routing agent to produce more realistic, diverse Synthetic Users with better organic parity.
Chain-of-feeling
Synthetic Users use a “chain-of-feeling” approach—combining emotional states with OCEAN personality traits—to produce more human-like, realistic user responses and yield richer UX insights.
Generative Agent Simulations of 1,000 People
A paper that thoroughly executes a parity study between Synthetic and Organic users.
21 Peer reviewed papers that support the Synthetic Users thesis
Here is a compilation of all the papers that help make a case for Synthetic Users.
Why we shuffle between models — to ensure both parity and diversity!
Synthetic Users balances aligned and unaligned models to maintain diversity and authenticity in simulated users while ensuring ethical standards and user expectations are met.
Latest press articles for Synthetic Users
Synthetic Users and AI are transforming research methodologies, offering innovative, cost-effective alternatives to traditional human subject studies.
Comparison studies. The opportunity lies in the deviation.
When we compare different studies, especially looking at what synthetic (artificial interviews) and organic (real-world interviews) data tell us, we often find they mostly talk about the same things but there's also a bit where they don't match up. This gap is super interesting because it's like finding hidden treasure in what we thought we knew versus what we might have missed.
How we deal with bias
Harnessing the power of AI in our Synthetic Users, we strive for a balance between reflecting reality and ethical responsibility, ensuring diversity and fairness while maintaining realism.
The transition to Continuous Insight
The transition towards Continuous Insight™ aligns research activities more closely with the dynamic needs of the business and ensures that product development is continuously informed by up-to-date user insights.
The Art of the Vibes Engine
Large language models (LLMs) like GPT-4 serve as powerful "vibes engines," empathizing with diverse groups and generating contextually relevant content. Their applications span market research, customer support, user experience design, and mental health support, offering invaluable insights and personalized experiences. While not infallible sources of truth, LLMs enable creativity, personalization, and connection within the realm of human language.
There is a faster and more accurate way to do research. Use Synthetic Users.
How Synthetic Users is changing the research process.
The wisdom of the silicon crowd
In the light of an ancient parable, we explore a new paper that dives into how ensembles of large language models match the prediction accuracy of human crowds. It reveals that combining machine predictions with human insights leads to the most robust forecasting results.
Three research papers that helped us build ❤️ Synthetic Users
For the sceptics amongst us who need more tangible research in order to engage with this brave new world. Full disclosure: we are part of the sceptics.
What is RAG and why it’s important for Synthetic Research
Ahead of our RAG launch we explain Retrieval-Augmented Generation (RAG) and how it enhances Synthetic Users by providing increased realism, contextual depth, and adaptive learning, with profound implications for market research, user experience testing, training, education, and innovative product development.
Synthetic Users system architecture (the simplified version).
Foundation models underpin Synthetic Users with advanced capabilities, enhanced by synthetic data and RAG layers for realism and business alignment, all within a collaborative multi-agent framework for richer interactions.
Saturation score. How do we know how many interviews to run?
Determine your interview target for achieving topic saturation using our efficient approach, leveraging the historical wisdom of research pioneers. This method ensures deep insights with theoretical sampling at its core.
How Synthetic Users are gaining depth
Synthetic Users are evolving to address criticism about their generalist nature by incorporating representative data sets and personal narratives.
How we compare interviews to ensure we improve our Synthetic Organic Parity — 85 to 92%
How do we know we are right? How do we know our Synthetic Users are as real as organic users? We compare.
Synthetic Users: Merging Qualitative and Quantitative Research, in seconds.
At Synthetic users we are blurring the lines between qualitative and quantitative research. Here's how we are going about this transformative approach.