The token math at message 30 stopped me. I never thought of it as Claude re-reading 29 full exchanges before even getting to my new question. The edit button trick too. I was typing "actually, change X" constantly without realizing I was just feeding the furnace.
I really enjoy reading your AI articles and then implementing what I understood. You explain complex tasks in a very interesting and simple way. Thanks for sharing your precious wisdom with us for free! 😊
I think what you’re doing is great. A lot of people have no idea how to use AI effectively most just zero shot a model and go. I’ve been using AI for quite a while, your one posting about interviewing yourself with your own voice was eye opening for me and I haven’t looked back since.
Right now I run Cowork as the conductor and I have 4-6 Claude codes running in parallel fixing and work on projects. This approach you’ve shared for non-coders and people with a software background is a massive help.
I've been working on this app, so I'm going to try to generate the summary as you suggested and place that in the instructions or create a .md file. Because when I created a new chat in the project, it didn't remember all the details we had already worked through.
Really interesting. Please send prompt library, I've only been on this journey in-depth for the past month. I'd used different models sporadically but none really seemed to 'meet' the imagination like this does, but keen to learn more and minimise tokens/ spend all whilst educating myself and learning through the research
Wow I loved that article. There is so much information that i would never have thought about . This feels like when we had to pay for minutes on a phone plan years ago and Claude and all AI are using tokens. So how quickly will the features change and make the token idea old news. I think its already annoying people.
Great content, useful and practical. Provided me with imporant insights on token consumption. Thanks! P.S. I am a subscriber, I'd like to know how to access your library.
I’ve been learning so much reading your newsletter. I am a Founder and I have a small team in my Company. I’ve been applying your tips to set up claude and it is been very useful. Great job ! I share and recommend How to use AI newsletter for all my friends to want to use AI
The token math at message 30 stopped me. I never thought of it as Claude re-reading 29 full exchanges before even getting to my new question. The edit button trick too. I was typing "actually, change X" constantly without realizing I was just feeding the furnace.
edit button is the fix for lazy corrections
new chat is the fix for topic drift
I really enjoy reading your AI articles and then implementing what I understood. You explain complex tasks in a very interesting and simple way. Thanks for sharing your precious wisdom with us for free! 😊
thanks for reading :)
you implementing it puts you ahead of 95% of readers who just bookmark and move on
Another stellar report!
I got a lot out of this.
Thank you!!!
Really.
🪄✨⋆✴︎˚｡⋆👍😊💖
appreciate the support :)
try them out this week
Wanna know what I was super excited about?
doc.new in the search tab .... amazing. for realz.
I look forward to reading posts every Wednesday and Sunday this has been a massive help thank you!!
that means a lot - any ideas on what i should cover next? :)
I think what you’re doing is great. A lot of people have no idea how to use AI effectively most just zero shot a model and go. I’ve been using AI for quite a while, your one posting about interviewing yourself with your own voice was eye opening for me and I haven’t looked back since.
Right now I run Cowork as the conductor and I have 4-6 Claude codes running in parallel fixing and work on projects. This approach you’ve shared for non-coders and people with a software background is a massive help.
Great article. Although could you please explain why you turn Memory off? You said it's "odd", but in what what? Thanks!
AI ends up doing what I call “overfitting” - trying too hard to tell you it knows about you.
I agreed with everything in the article except this one, so would love more clarification since memory seems like an important and helpful thing.
Also wondering the same
Great tipps. Some of them I haven't heard before at all. Will try to utilize them!
really glad to know, Tom - let me know how it goes :)
The blog I was waiting for!!
i featured you!!!
I'm really here for the prompt library, and thank you for doing the lord's work for us
hi David -
1/ search for ruben@substack.com in your email to find my welcome email (also check spam/promotion).
2/ make sure to click the “Step 1 - Get Prompt Library” button. it will send me an automatic email then you’ll receive the How to AI library.
Prompt library comment.
1/ search for my welcome email ruben@substack.com
2/ reply with “I’m not a robot.”
3/ you’ll receive a new email from me.
And if ever there's no welcome email - dm me :)
Thanks Ruben. :)
Thanks for this. I've been burning through usage limits all weekend.
did you try the tricks? :)
I've been working on this app, so I'm going to try to generate the summary as you suggested and place that in the instructions or create a .md file. Because when I created a new chat in the project, it didn't remember all the details we had already worked through.
Really interesting. Please send prompt library, I've only been on this journey in-depth for the past month. I'd used different models sporadically but none really seemed to 'meet' the imagination like this does, but keen to learn more and minimise tokens/ spend all whilst educating myself and learning through the research
hi,
1/ search for ruben@substack.com in your email to find my welcome email (also check spam/promotion).
2/ make sure to click the “Step 1 - Get Prompt Library” button. it will send me an automatic email then you’ll receive the How to AI library.
Wow I loved that article. There is so much information that i would never have thought about . This feels like when we had to pay for minutes on a phone plan years ago and Claude and all AI are using tokens. So how quickly will the features change and make the token idea old news. I think its already annoying people.
tokens aren't going away anytime soon - LLMs charge based on input tokens.
that's why I wrote this guide. understand how this works today then be years ahead when it all gets easier tomorrow :)
Thanks for your reply.
I no longer have the welcome email.
Could you kindly resend it to me?
sent you a dm!
Great content, useful and practical. Provided me with imporant insights on token consumption. Thanks! P.S. I am a subscriber, I'd like to know how to access your library.
hi,
1/ search for ruben@substack.com in your email to find my welcome email (also check spam/promotion).
2/ make sure to click the “Step 1 - Get Prompt Library” button. it will send me an automatic email then you’ll receive the How to AI library.
Please send me your prompt library. I have subscribed. Thank you.
hi,
1/ search for ruben@substack.com in your email to find my welcome email (also check spam/promotion).
2/ make sure to click the “Step 1 - Get Prompt Library” button. it will send me an automatic email then you’ll receive the How to AI library.
I’ve been learning so much reading your newsletter. I am a Founder and I have a small team in my Company. I’ve been applying your tips to set up claude and it is been very useful. Great job ! I share and recommend How to use AI newsletter for all my friends to want to use AI
hi Patricia - thanks for doing so :)
i will work hard to keep on writing better newsletters for you and your friends