I tried to make an LLM act and behave more like @typesafeai

@TravisJChauvin Travis Chauvin · Sep 18, 2026 · case #121725 · listed via Jev Hub
Original post on X
Frame from the clip posted with this case
Still from the clip posted with this case; watch it in the original post on X.

Tried to replicate Jev's System One behavior in a standard LLM using an RLCD-trained Qwen 1B model.

The original post

I tried to make an LLM act and behave more like @typesafeai 's Jev While full details about RLCD or the model's architecture is not publicly available, projects like https:// huggingface.co/harshatheg/Qwe n-2.5-1B-RLCD … have attempted to recreate Jev's similar effects with traditional LLMs. So I made a

Engagement when collected

Views63
Likes1
Bookmarks0
Reposts0
Replies0
Quotes0

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.

Where this case fits

Filed under general Jev builds. In the pattern Jev is built for, the model answers a bounded question per step — and ordinary code acts on the answer, because the answer is already a value rather than a paragraph. Browse the full case library for the work it sits next to.

All Jev cases

Keep browsing: all 1173 Jev cases · more from @TravisJChauvin · builders · what Jev is

Last updated: 2026-09-22 · sources & corrections · every card links to its author's original post