Grant Mills
21 posts


@ArislanbekInc Building several apps on dedicated to creating social media content for real estate agents
English

@omarvvvr Maintaining good quality context across all of your projects
English

Been experimenting with local LLMs lately. The idea of having unlimited access to a model running right on your own machine is such an appealing one.
The cost of compute is skyrocketing. I see local LLMs staying just slightly behind the cloud models.
But I also think at some point these models get so good that the small gap won’t matter as much. Depending on your use case, of course.
How are you using local LLMs? Are you investing in compute to run them?
English

I have used the last couple of days to take a step back from a few projects.
Awaiting Fable's return.
The scary part of the Fable shutdown isn’t that one model went dark. It’s that a government can pull a commercial AI model off the shelf in 3 days over an alleged jailbreak the company says exists in GPT-5.5 too. Every frontier lab just learned their release can be revoked overnight.
English

Fable 5 is the future but the future is going to be a pay to play.
Excited for more and more for where AI is heading.
Created my first loop having 4 different multiple agents on different models all working together continuously on a single goal.
I am going to bed while “Jarvis” is grinding on a /goal that is on a continuous loop.
So excited for the future.
English









