Hi all, I just returned from being out of town for work. Glad to be back and to plan our first workshop! AI Beginner Workshop Friday, September 4th 11am - 12pm PDT Agenda: 30 minutes — getting set up and going over basic best practices 30 minutes — beginning workflows My hope is to get people comfortable in their set up and excited about what can be done. Feel free to share with friends! ❓Please LMK which model you are working with: Claude, Chat GPT or Gemini. Also mention if there is anything in particular you want to cover. 👇 Here is the link for the workshop. https://meet.google.com/xnr-qbig-wtr

I have been out of commission on work travel and clients but finally have some time tonight to put thought into something I think you may be curious (or frustrated) about — "memory" in AI models.... Two different things get called "memory," and mixing them up causes real confusion. So I thought we would separate them. 1. MEMORY IN A CHAT Term to know: "context window". This is the tool's short-term memory for the chat you are in right now. Everything you have typed sits inside it. Once the conversation gets long enough, the earliest parts begin slipping as if they were lost. That is why a chat that started sharp can drift into sloppy. It is not getting tired. It is losing the beginning. What to do: start a fresh chat for each new task, and paste back in the details that still matter. Easiest way is to ask the model for a "handoff" file to paste into a new project or chat. 2. MEMORY ACROSS CONVERSATIONS ->Claude is the only AI with memory per-Project separation. In other words, your memory from one project won't leak to another project. -> Gemini has the most memory settings scattered across many places, so it is the easiest one to misconfigure without realizing. I think Google has some work to do to make things easier to configure. -> ChatGPT is the one where deleting memories does not fully undo things if the chats remain. So if you are bothered by Chat GPT bringing up "old information", you should delete old chats. More details: Claude. Everything Claude remembers sits in a list of files under Topics in Memory settings, where you can read, edit, or delete each one. Sensitive subjects — health, race, religious beliefs, politics, gender identity and similar are not stored by default, though you can turn them on. Each Project has its own separate memory space, so context in one Project stays separate from other projects and from non-project chats. Turning it off gives you two choices: pause, which keeps existing memory but stops using or making new ones, or reset, which permanently deletes everything including project memories.

One of the questions I get often is, "Which is the best AI model to use?". The answer ----> it is less about which model to use (they are rapidly changing and building out capabilities daily), and more about how to build out your workflows so that if you need to change AI models tomorrow, it is like flipping a switch. Why is this important? There are many reasons. Token usage: when you get into big projects, it costs more tokens/money. If you are in an organization, once you have AI working, your next evaluation is how much is this costing? Also, what happens if a model goes away and you are deeply embedded? And last, you will get different results with different models- learning how to test between models is the new AB test that can have an affect on the quality of your work. Not being too reliant on any one model is not only advantageous, it is truly best practices in building AI native systems. Do you feel stuck within one particular platform and not sure how to build out a portable workflow? If you are still using AI to chat, but haven't built a recurring task or workflow, comment below and I can host a free class. 👇

Hi everyone, I am taking a poll for topics this week. Let me know what you would like to learn. Feel free to add anything else in the comments. Your feedback helps me make relevant content 💫