Jev case: I increasingly think future software will combine

Combined 30 small Jev programs with a decision tree to route questions in a local course-website helper.

The original post

I increasingly think future software will combine code for control flow with small neural programs for "fuzzy" judgments.

That's what I've been exploring with ProgramAsWeights, which answers the question of where those neural programs come from: they are "compiled" from English descriptions.

For example, I combined 30 neural programs with a decision tree to build a course website helper that looks like a chatbot but runs locally. Each small program handles a question like "Which specialist answerer should this be routed to", and code controls the overall flow.

You can try building with it here:

Quoted post

C

@CompleteSkeptic34.5M views

source

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x

What the author linked

• programasweights.com
• PAW — Define functions in English, run them locally — ProgramAsWeights compiles natural language specs into tiny neural programs that run on your machine. Once compiled, they work as regular Python

Engagement when collected

Numbers are a snapshot taken from X when the case was added to the library (schema v1, collected 2026-09-19); they will not match today.