Deep Thought

AI, AI Models, ai tools - July 12, 2023

Microsoft’s Automatic Prompt Optimization Improves Prompts to Boost LLM Performance

The recent rise of powerful large language models (LLMs) has revolutionized the field of natural language processing (NLP). The performance of these generative models is largely dependent on users’ prompts, which are becoming increasingly detailed and complex. A Google Trends search reveals a hundredfold increase in popularity for the term “prompt engineering” over the last six months, and social media is teeming with novel prompting tips and templates. Is trial-and-error really the best approach, or could there be a more efficient way to develop effective prompts? In the new paper Automatic Prompt Optimization with “Gradient Descent” and Beam Search, a Microsoft...

Read more

AI, Deep Thought - July 03, 2023

How to teach AI to imitate human thought and action

Artificial intelligence systems can mimic some aspects of human intelligence with impressive results, including detecting objects, navigating environments, playing chess, or even generating text. But cloning human behavior has its limitations. Without backing actions with thought, AI systems can become brittle and make unpredictable mistakes when faced with novel situations. One recent project by scientists at the University of British Columbia and Vector Institute shows the benefits of getting AI systems to think like humans. They propose a technique called “Thought Cloning,” which trains the AI on thoughts and actions at the same time. Thought cloning can enable deep learning models to...

Read more

AI, GPT-4, Minecraft, Nvidia - June 19, 2023

Minecraft AI - NVIDIA uses GPT-4 to create a SELF-IMPROVING Autonomous Agent

We introduce VOYAGER, the first LLM-powered embodied lifelong learning agent in Minecraft that continuously explores the world, acquires diverse skills, and makes novel discoveries without human intervention. VOYAGER consists of three key components: 1) an automatic curriculum that maximizes exploration, 2) an ever-growing skill library of executable code for storing and retrieving complex behaviors, and 3) a new iterative prompting mechanism that incorporates environment feedback, execution errors, and self-verification for program improvement. VOYAGER interacts with GPT-4 via blackbox queries, which bypasses the need for model parameter fine-tuning. The skills developed by VOYAGER are temporally extended, interpretable, and compositional, which compounds...

Rethinking AI benchmarks: A new paper challenges the status quo of evaluating artificial intelligence

In recent years, artificial intelligence (AI) has made remarkable progress in performing complex tasks that were once considered the domain of human intelligence. From passing the bar exam and acing the SAT to mastering language proficiency and diagnosing medical images, AI systems such as GPT-4 and PaLM 2 have surpassed human performance on various benchmarks. Benchmarks are essentially standardized tests that measure the performance of AI systems on specific tasks and goals. They’re widely used by researchers and developers to compare and improve different models and algorithms; however, a new paper published in Science challenges the validity and usefulness of many existing benchmarks for evaluating AI systems. The...

Read more

AGI, AI, AI Ethics, GPT-4, Sam Harris - June 13, 2023