Joseph Jay Williams's podcast

Q: How do you define dimensions along which your collection, activity is unusually good? Scientist Sharing Conversations

Imagine you're sweating buckets, because you have a big presentation, or a critical meeting. You're worried you choke, or say the wrong thing, or your mind will go blank. Our research has shown experimentally the kinds of messages you can say to yourself, almost like magic words in Harry Potter, so you see stress as a resource they can help you instead of something for you to fight against. Read the paper we published at url tiny.cc/eustresspaper. it has examples of messages we showed that helps students perform 4% better on a test just by reading these messages in a couple minutes. Instead of fighting your stress and anxiety, you accept it and recognize how it can actually give you more energy and focus, allowing you to share the knowledge and do the things you want to do.

What's strong evidence we can get for a claim, about whether x is a good idea, whether x has benefit y? Best kept secret :D, of randomized controlled trials!

I give examples of micro-experiments you can run with chatgpt and other platforms. Dick's permits is to try to use it at least once a day if not more and just start telling it all the things you wish you could magically do, for example, how do I exercise when I'm not motivated give me 10 different reasons, how do I get more done work in less time give me five ideas based on top management theorists. The prompts almost definitely will not give you something right away but think about like a stock portfolio, even if 90% of these prompts bust I'm giving nothing just 10% of them could be a stock like Google the p is off huge rewards.

A lot of what we do at work isn't that helpful and responding too much energy in time on it meanwhile there are things that would help us achieve our core goals and high impact but we don't realize we should be doing them. Reading 168 hours by Laura Vanderkam is giving some examples of questions to ask yourself so you can begin experimenting with what you can stop doing what you can start doing.

Title: Tools for A/B testing with machine learning: No analysis, programming or stopping decisions required? This brief episode is a teaser for a scientific paper on a tool for experimentation. It was used at Harvard for people to deploy experiments on copy content (text, links, questions). This was done without the designers having to do any programming, any analysis, or even decision making about when to stop the experiment. That was done with a statistical machine learning algorithm, the Bayesian Bandit algorithm Thompson sampling, which changed the probability of assigning users to variants in real-time, as data was being collected. For example, the randomization probability of assigning variants A1 vs A2, would start at 50/50, change to 60/40, 30/70, 45/55, 80/20, 90/10 and so on. The goal was to phase in the variant in proportion to the probability that it would give the highest score in the target metric. The paper is at www.josephjaywilliams.com/pape..., search for 'tools for randomized experiments'. Feel free to share questions, skepticisms, opportunities for applying these kinds of techniques or tools! There are >10 more papers Joseph has on this approach, and 100s in the literature, and excited to engage in discussion! This is an experiment in the next stage of CRO cafe. A professor in experimentation & optimization is interviewing themself, by asking himself questions from listeners and other sources. The professor is www.josephjaywilliams.com and has published over 80 papers since he ran his first experiment in 2004. Like many of you, he's excited to keep innovating in tools and methods for experimentation, personalization, AI, ML until he says goodbye to this lively, lovely world!