John Records
@johnrecords.bsky.social
AI x Nonprofits
• 21 years as Executive Director of a Bay Area nonprofit.
• Empowering nonprofits with AI tools that feel like superpowers to save time, stretch budgets, amplify impact.
• Let's connect!
• 21 years as Executive Director of a Bay Area nonprofit.
• Empowering nonprofits with AI tools that feel like superpowers to save time, stretch budgets, amplify impact.
• Let's connect!
Reading Bee Speaker now. Irae may be a predecessor of Worsel...
October 14, 2025 at 7:47 PM
Reading Bee Speaker now. Irae may be a predecessor of Worsel...
Now we need the librarian.
October 11, 2025 at 3:50 PM
Now we need the librarian.
Very nice! And the MLX community has released a version that will run on your 64 gig Mac.
September 17, 2025 at 5:07 AM
Very nice! And the MLX community has released a version that will run on your 64 gig Mac.
Simon, iirc you have a 64 gb Mac. As you may know it's possible to run OSS 120-b on that, using the Unsloth q2 model. Thanks for your wonderful posts!
August 7, 2025 at 4:36 AM
Simon, iirc you have a 64 gb Mac. As you may know it's possible to run OSS 120-b on that, using the Unsloth q2 model. Thanks for your wonderful posts!
Ethan, I appreciate your posts enough that I will rejoin LinkedIn to continue seeing them regularly. And of course I read and enjoy your newsletter.
May 26, 2025 at 7:43 PM
Ethan, I appreciate your posts enough that I will rejoin LinkedIn to continue seeing them regularly. And of course I read and enjoy your newsletter.
Peter Kenny narrating Iain M. Banks’ writing is luscious, and not to be missed.
May 17, 2025 at 5:02 PM
Peter Kenny narrating Iain M. Banks’ writing is luscious, and not to be missed.
please keep posting here.
April 26, 2025 at 9:41 PM
please keep posting here.
What a cool idea! I'm trying this idea with a Project Gutenberg book and have asked for a text-based adventure.
April 11, 2025 at 7:35 PM
What a cool idea! I'm trying this idea with a Project Gutenberg book and have asked for a text-based adventure.
Thanks for Moonbound!
March 31, 2025 at 4:32 AM
Thanks for Moonbound!
No, haven't tried that.
March 10, 2025 at 12:13 AM
No, haven't tried that.
Maybe a smaller model with large context window (haven't tried this myself). One example: Llama 3.1 8b has 128K context window.
March 9, 2025 at 11:53 PM
Maybe a smaller model with large context window (haven't tried this myself). One example: Llama 3.1 8b has 128K context window.
Similar experience, gave up on it.
March 3, 2025 at 10:08 PM
Similar experience, gave up on it.
I deeply appreciate your contributions to a better life and better health for many people. Regarding world hunger, ChatGPT has some advice for you. chatgpt.com/share/67b9e9...
ChatGPT - Mark Cuban Hunger Solutions
Shared via ChatGPT
chatgpt.com
February 22, 2025 at 3:15 PM
I deeply appreciate your contributions to a better life and better health for many people. Regarding world hunger, ChatGPT has some advice for you. chatgpt.com/share/67b9e9...
Thanks for the nudge on MLX models, Simon. They seem to be more memory efficient on Macs than GGUF versions.
February 15, 2025 at 10:22 PM
Thanks for the nudge on MLX models, Simon. They seem to be more memory efficient on Macs than GGUF versions.
I like how one can tick a box in LM Studio search and find only MLX models. I haven't tried the option Simon mentions.
February 15, 2025 at 8:08 PM
I like how one can tick a box in LM Studio search and find only MLX models. I haven't tried the option Simon mentions.
a chain of thought model it seems from the name.
February 12, 2025 at 1:20 AM
a chain of thought model it seems from the name.
Indeed. The Viture Pro does as you suggest. So all one needs is a lightweight display in glasses.
February 2, 2025 at 4:52 AM
Indeed. The Viture Pro does as you suggest. So all one needs is a lightweight display in glasses.
"Let there be pudding!" I'm in for the pudding potluck.
January 30, 2025 at 5:08 PM
"Let there be pudding!" I'm in for the pudding potluck.
Thanks, looking forward to the ggufs
January 30, 2025 at 5:05 PM
Thanks, looking forward to the ggufs
that's pretty awful
January 28, 2025 at 5:10 PM
that's pretty awful
Any thoughts on the 70b model, quantized?
January 28, 2025 at 4:17 AM
Any thoughts on the 70b model, quantized?