fokdelafons

Summary: https://lustra.news/en/us-congress/119/legislations/119_HR_8...

It is incredibly ironic that Josh Gottheimer, the bill's sponsor, is pushing for mandatory OS-level age verification while his own official contact site (https://gottheimer.house.gov/contact) returns a 404 error, making it impossible to reach him.

Tech Stack:

Frontend: Flutter (Web & Mobile Monorepo),

Backend: Firebase + Google Cloud Run,

AI: Vertex AI https://lustra.news/info/tech

License: PolyForm Noncommercial — source is available for inspection, learning, and non-commercial civic use. Commercial use would require a separate agreement.

I am looking for contributors. I have the US and Poland live. EU, UK, FR, DE in pipeline. I need help building Data Adapters for other parliaments (the core logic is country-agnostic). If you want to help audit the code or add a country, check the repo. The goal is to complete the database as much as possible with current funding. Please, fork it if you can.

Live App: https://lustra.news

Repo: https://github.com/fokdelafons/lustra

Dev Log: https://lustrainitiative.substack.com

The linked post details my engineering solution: a 'Generalizer-Judge-Surgeon' pipeline to remove hallucinations from legislation.

Using a "dumber/faster" model (Flash Lite) strictly as a Judge (comparing Source vs Summary) worked better than asking initial model to self-verify. It acts like a semantic regex.

Call for Contributors: The project is Source Available. I have the core architecture ready for scaling, but I need locals to help build the specific data adapters/scrapers for their parliaments. If you want to help fix the "legislative black hole" in your country, check the repo.

Happy to answer questions about the prompt engineering or the architecture.

Good question! I almost don't get problems with hallucinations. The worst case I had was oversimplification. I'm using mostly heuristic models, so they don't overthink; they just rely more on the source. If something is wrong, they usually mess up json, and it doesn't get through. Bills are typically long because of exposes, analyses, and predictions attached. I don't use it, as I'm focusing just on context sterilization and compression of info of the actual bill, not what it could be. Diffing would be wonderful! I have to think about it, thanks!

Thanks! Yeah, it's an artifact, as first parliament I introduced was Sejm. Maybe I'll switch to the "Politicians"? Because I'm going to introduce senators there too.

Thanks for flagging! Civic Projects just landed and are still in beta, so glitches might happen. I’ll look into it and get it fixed.

Absolutely, the model does the picking.

You can't strip it completely, totally agree. Any compression of information is already an interpretation. The problem becomes more prevalent, the more thinking and advanced models become. To mitigate it, I rely on some constraints:

1. No opinion space: the prompt forbids normative language and forces fact to consequence mapping only (“what changes, for whom, and how”), not evaluation.

2. Outputs are framed explicitly from the perspective of an average citizen of a given country. This narrows the context and avoids abstract geopolitical or ideological extrapolation.

3. Heuristic models over reasoning models: for this task, fast pattern-matching models produce more stable summaries than deliberative models that tend to over-interpret edge cases.

It’s not bias-free, but it’s more constrained and predictable than editorial framing.

Thanks, I’ll add clarification about the license in the description.

Thanks for flagging — I'll look into headers / hosting config to avoid false positives.