Eric Olson, CEO and co-founder of Consensus, discusses how to use LLMs to help researchers get better answers faster from evidence-based journals
Eric Olson, CEO and co-founder of Consensus, is a collegiate athlete turned data scientist turned entrepreneur who needed faster access to reliable data while working at DraftKings. Consensus is a search engine that uses a large language model to find answers in peer-reviewed research articles. Eric's living proof that the best entrepreneurs start by solving a problem they've encountered. Hear how Eric's scratching his own itch.
Listen and learn...
- Why Google isn't the answer for scientists seeking evidence-based answers online
- Why a business model that relies on ads can't solve the "unbiased answer" problem for researchers
- How Consensus addresses the problem of conflicting information online from credible resources
- How to use labels to improve search retrieval accuracy... without introducing bias into results
- How to use extractive large language models (LLMs), to extract relevant portions of documents and match them to NLP questions
- Why generative AI like GPT-3 can't answer "what's the consensus opinion out there" when multiple potential answers exist
- Who is responsible if Consensus delivers answers that lead to harmful outcomes
- What Eric learned as a division I NCAA athlete (Go Wildcats!) that has helped him as a high-tech entrepreneur
References in this episode:
- Elon Musk launches the Optimus bi-pedal robot at AI day
- Dan Grunfeld, Stanford athlete and Lightspeed partner, on AI and the Future of Work
- Consensus
View all episodes
By Dan Turchin
4.9
2828 ratings
Eric Olson, CEO and co-founder of Consensus, is a collegiate athlete turned data scientist turned entrepreneur who needed faster access to reliable data while working at DraftKings. Consensus is a search engine that uses a large language model to find answers in peer-reviewed research articles. Eric's living proof that the best entrepreneurs start by solving a problem they've encountered. Hear how Eric's scratching his own itch.
Listen and learn...
- Why Google isn't the answer for scientists seeking evidence-based answers online
- Why a business model that relies on ads can't solve the "unbiased answer" problem for researchers
- How Consensus addresses the problem of conflicting information online from credible resources
- How to use labels to improve search retrieval accuracy... without introducing bias into results
- How to use extractive large language models (LLMs), to extract relevant portions of documents and match them to NLP questions
- Why generative AI like GPT-3 can't answer "what's the consensus opinion out there" when multiple potential answers exist
- Who is responsible if Consensus delivers answers that lead to harmful outcomes
- What Eric learned as a division I NCAA athlete (Go Wildcats!) that has helped him as a high-tech entrepreneur
References in this episode:
- Elon Musk launches the Optimus bi-pedal robot at AI day
- Dan Grunfeld, Stanford athlete and Lightspeed partner, on AI and the Future of Work
- Consensus
More shows like AI and the Future of Work: Artificial Intelligence in the Workplace, Business, Ethics, HR, and IT for AI Enthusiasts, Leaders and Academics
View all
The AI in Business Podcast
154 Listeners
a16z Podcast
981 Listeners
Data Skeptic
469 Listeners
Super Data Science: ML & AI Podcast with Jon Krohn
290 Listeners
The AI Podcast
283 Listeners
AI Today Podcast: Artificial Intelligence Insights, Experts, and Opinion
148 Listeners
Practical AI: Machine Learning, Data Science, LLM
170 Listeners
Last Week in AI
236 Listeners
Me, Myself, and AI
95 Listeners
AI Chat: ChatGPT & AI News, Artificial Intelligence, OpenAI, Machine Learning
133 Listeners
This Day in AI Podcast
164 Listeners
The AI Daily Brief (Formerly The AI Breakdown): Artificial Intelligence News and Analysis
342 Listeners
A Beginner's Guide to AI
24 Listeners
The TED AI Show
35 Listeners