Nice work! This is very interesting (as a heavy Dagster and DuckDB user myself)

The idea of "model controlled", "application controlled" and "user controlled" for tool, resources and prompts (respectively) was aligned with the chat interface. It breaks for the autonomous agent paradigm where the agency is the user and the lines are blurred. Unfortunately MCP has been mostly relegated to tool calling leaving potentially powerful capabilities on the table due to lac of client support for them.

"In a shocking finding, scientist discovered a herd of unicorns living in a remote, previously unexplored valley, in the Andes Mountains. Even more surprising to the researchers was the fact that the unicorns spoke perfect English."

yep, I belong here on HN, haha!

This is my experience as well. It gets worse when the LLMs have strong priors in subject matter adjacent to your novel work. The generated output will incorrectly pull towards things the LLM has seen in it’s training data.

I'm working on leveraging NLP and LLM techniques to create a geometry over the discrete space of Ethereum transaction execution structure. (sorry... it's a bit of a mouthful)

https://www.chaingenius.ai

The goal is to find on-chain structural anomalies, as well as seeing if clustering by behavior has emergent semantic properties

I think i know where you're going with it, but what is the Why for the semantic properties? Is it to characterize a given address, predict behavior?

Is this still true?

You may be thinking of Litestar (previously named Starlite) that was based on Starlette akin to FastAPI but then went their own direction implementing a framework rather than relying on an upstream for their core product.

..And?

FastAPI depends on "starlette>=0.46.0"

And? It's a non-sequitur to my comment.

Yes, it's literally the first bullet point on the project's website.

Fine tuning Gemini 2.5 flash on EVM Blockchain execution structures and using perplexity with PageRank to perform transaction anomaly detection. https://lite.chaingenius.ai/theory

[SMILES](https://en.wikipedia.org/wiki/Simplified_Molecular_Input_Lin...) or [SELFIES](https://resources.wolframcloud.com/PacletRepository/resource...), but for EVM Blockchain executions.

Odd seeing this right now for me. I recently implemented a 6NF schema for parsed XBRL files from EDGAR. The architecture was the right call... too bad the data is not useful for analytics.

What? No love for Perl scripts in cgi-bin/ ?

In today's world of stupidly fast CPUs and IO a CGI program can be surprisingly performant and effective.