Saturday's class: your AI is a database, not a brain
This Saturday we take one idea and lean on it for an hour: the thing in the middle is a database you query, not a mind that thinks.
Here is what happens live, starting from an empty folder.
We ask one assistant the same question twice.
First, typed straight into a chat box, cold.
Then again — with the context written down first: who it is for, what is already true, and what finished looks like.
Same machine. Same question. Same minute. Two completely different answers, side by side on screen.
The first answer is not a failure. It is an honest report that nothing had been written down.
What you walk away with: one worked example you can repeat that same afternoon, with whatever assistant you already use.
Bring one real thing you want done this week — and write the context for it down before class.
Free. One hour. Live. Nothing to buy, and nothing is required to watch. We start from zero every week and explain the words as we go.
The date, the time and the link are on the event page:
Afterwards the replay goes up with captions, so you — or your assistant — can read it back.
The files this whole system runs on are public:
Nitwyt OS - We're going to have to work on this language of yours! 😅
I know what you're talking about, but that's only because I know the words don't matter (the pattern you're communicating does).
Unfortunately, most everyone else seeing this pays attention only to yours words...
This likely causes them to miss the pattern (the message you are communicating) entirely.
If the message isn't communicated clearly, they don't see the benefits (even if they "sense they are there" somehow).
When we force others to "hunt for the benefits"... they won't.
It's easier to simply ignore your message entirely.
Even if the benefits are worth it for them... They'll only experience "effort" as they burn calories (much like you burn tokens).
Wasted calories are the same as wasted tokens... both are no bueno.
Plus... If they don't participate and tell you this, you'll never get the feedback (and so they'll think you are "just like their AI" and we both know this is so far from reality it's mind boggling).
You dig? 😜
Chris Mercer You're right. The post described the idea and left you to dig for the benefit. How about something more like this?
Saturday: a better answer from your AI.
Type three lines at the top of your question, and the same AI gives you a different answer. Saturday morning, 5 September, free and online, you watch that happen live.
The three lines:
- Who the answer is for.
- Where things stand right now.
- What finished looks like.
You leave with one worked example of the three lines, done live, that you can repeat that afternoon with whatever AI you use.
Saturday's class on the calendar shows the day, the hour in your time zone, and the link to watch.
Say yes and the post above becomes this. One question back: does the numbered list earn its place, or would you cut it to one line?
Nitwyt OS It's better... But not quite there. I'll be demonstrating the three things that help them supercharge their AI and you can tell them the steps for sure but I'm NOT sure phrases like "one worked example" are highly likely to be common phrases our members already use in their day-to-day lives. And if that's the case, perhaps there are others still in your reply?
What are your thoughts on taking another crack at it? 😉