I’m trying to learn how to make use of ollama and local LLMs to do some co-processing for coding/doc review/etc so I’m not burning through tokens. But now I have to read about how this open-claw changes with Claude and having to pay-as-you-go tokens will affect ollama usage too
I want to start by saying how much I genuinely value your work. I'm a regular with your newsletter, podcast, and YouTube content — and I almost always walk away with something useful. That's not nothing.
I should be upfront: I'm not a coder or a technical user. I'm retired, and I've been using Claude — specifically Cowork and Dispatch — to help me write a book and manage personal projects. Cowork genuinely opened my eyes to what's possible, and your content has been part of that journey.
Here's my small ask: would you consider being a little more specific in your titles or descriptions about which version or interface of Claude you're covering? Whether it's Cowork, Dispatch, Chat, coding/terminal use — even a quick label would help less-technical folks like me self-select into the content that's most relevant. Right now I sometimes dive in and realize mid-way it's aimed at a more advanced or code-focused audience.
It's a minor thing, and I raise it only because I'm already a fan and want to get even more out of what you produce.
Thanks for everything you put into this. I look forward to each one.
Sabrina.. I am 55 year old mom from Indonesia and would like to earn 1 k - 5 k a month with digital business.. What do you think is the easiest way? Thank you
I am personally not a big fan of terminal/machine environment variables when they’re not required, they can have noticeable side effects, especially if you forget that & where you set them
I found this super helpful thanks! just added to my claude code (kind of a newbie, ish) and :
Total │ 18,269 │ 6,704 │ 63% cut
really great - thanks so much! now I need to figure out how to reduce additional API costs - currently on the $20 plan but keep having to top up API 1-2x a month....
This is helpful. I’ll try these out.
This is extremely helpful.
yay!
Merci!
That’s useful will try that.
Thank you for sharing. These Claude tips arrived on time 👌
Can these steps be applied to cowork?
Do /compact and put rules to not read every files !
Love this! Thank You so much!
I’m trying to learn how to make use of ollama and local LLMs to do some co-processing for coding/doc review/etc so I’m not burning through tokens. But now I have to read about how this open-claw changes with Claude and having to pay-as-you-go tokens will affect ollama usage too
So helpful, love it
Another point is to off unused connection! If you don’t use connection to jira - turn it off, for example. It will free space in context.
I think your tips are going to save me some money!!
Hi Sabrina,
I want to start by saying how much I genuinely value your work. I'm a regular with your newsletter, podcast, and YouTube content — and I almost always walk away with something useful. That's not nothing.
I should be upfront: I'm not a coder or a technical user. I'm retired, and I've been using Claude — specifically Cowork and Dispatch — to help me write a book and manage personal projects. Cowork genuinely opened my eyes to what's possible, and your content has been part of that journey.
Here's my small ask: would you consider being a little more specific in your titles or descriptions about which version or interface of Claude you're covering? Whether it's Cowork, Dispatch, Chat, coding/terminal use — even a quick label would help less-technical folks like me self-select into the content that's most relevant. Right now I sometimes dive in and realize mid-way it's aimed at a more advanced or code-focused audience.
It's a minor thing, and I raise it only because I'm already a fan and want to get even more out of what you produce.
Thanks for everything you put into this. I look forward to each one.
Cam
Sabrina.. I am 55 year old mom from Indonesia and would like to earn 1 k - 5 k a month with digital business.. What do you think is the easiest way? Thank you
Just curious: isn’t Step 4 equivalent to:
ollama launch claude --model qwen3-coder
If not, what are the differences?
I am personally not a big fan of terminal/machine environment variables when they’re not required, they can have noticeable side effects, especially if you forget that & where you set them
I found this super helpful thanks! just added to my claude code (kind of a newbie, ish) and :
Total │ 18,269 │ 6,704 │ 63% cut
really great - thanks so much! now I need to figure out how to reduce additional API costs - currently on the $20 plan but keep having to top up API 1-2x a month....