If I wanted to start a woo cult, its prime obsession would be the near perfect overlap of the moon and sun during eclipses. Constantly surprised no one is running with this.

You know it's a good Monday when you get to quote Dr. Dan Streetmentioner's "Time Traveler's Handbook of 1,001 Tenses" on a Github issue before noon. github.com/dbreunig/whe...

Here's my intro talk on it: www.youtube.com/watch?v=I9Zt...

And the write up, if you prefer: www.dbreunig.com/2025/06/10/l...

Your last two responses are basically the pitch in a nutshell and goal of the framework. To properly engineer the squishing LLM bits.

The maintainability of writing structured specs, not natural language (in addition to the optimization infra) is such a win for the exact scenario you're describing.

Would love to chat with you about DSPy and this use case.

Yes. It's close to the "Tool Loadout" context fix I wrote about awhile back. Have been tracking a few implementations. www.dbreunig.com/2025/06/26/h...

This is performance art, as much as anything else. The dumbest post Ive written in a bit, but the one that raises the most questions.

Once upon a time, NVIDIA was a client. They had this cuda thing they thought was neat but they couldn't convince anyone to build with it. They had demos of fabric simulations, biology simulations, lots of cool visuals. But everyone just shrugged their shoulders.

That’s only in the northwest.

I just assumed they had counted on Kid Rock residency for the next couple years.

Deploying mine to ask everyone on marketplace if it’s still available.