Why Your AI Still Lies to You (and the Radical Shift to

@SungJinIn2 Sung-Jin In · Sep 18, 2026 · case #798614 · 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.

Presented Jev as an argument for RLCD over RLHF in a talk on why AI assistants mislead and how smart software differs.

The original post

Why Your AI Still Lies to You (and the Radical Shift to "Smart Software") - Jev: Why RLCD beats RLHF — Diogo Almeida, TypeSafe AI The "Assistant" Trap We are currently living through a profound technical paradox. Large Language Models (LLMs) can solve unsolved mathematical

Engagement when collected

Views193
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 @SungJinIn2 · builders · what Jev is

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