Are You Smarter Than An AI?
walzr.com · 138 words · saved by 2 readers
Humans can do evals, too.
LEADERBOARD RANKMODEL👍 Think you can outsmart AI? How do we know if an AI is actually intelligent? Researchers use something called "evals" (short for evaluations) to find out. These are carefully designed questions and challenges that test an AI's reasoning, knowledge, and problem-solving abilities. They're the closest thing we have to an IQ test for machines. Now you can take the same tests yourself. Answer the questions, see your score, and find out how you measure up against the latest models. Some might surprise you with how easy they are. Others might leave you stumped on…
saved by
related reading
- Demystifying evals for AI agents \ Anthropicanthropic.com
- A statistical approach to model evaluations \ Anthropicanthropic.com
- [1911.01547] On the Measure of Intelligencearxiv.org
- AI Model & API Providers Analysis | Artificial Analysisartificialanalysis.ai
- Your AI Product Needs Evals – Hamel's Blog - Hamel Husainhamel.dev
- LLM evaluation: a beginner's guideevidentlyai.com
- Challenges in evaluating AI systems \ Anthropicanthropic.com
- Agent Evaluation: A Detailed Guidecameronrwolfe.substack.com
- What is intelligence?theoriesofintelligence.substack.com
- Artificial General Intelligence Is Already Herenoemamag.com
- A starter guide for evals — AI Alignment Forumalignmentforum.org
- What will more intelligence actually do for us?noahpinion.blog