Breaking: Jev can detect AI misalignment
This is a AI post classified by Jev as Safety & policy (a tool drop), kept by the AI Radar because it carries real work, not commentary.
Breaking: Jev can detect AI misalignment I had it scan through real ChatGPT conversations to identify cases of misalignment, and it's blazing fast. It flagged about 6% of chat logs from a small sample. I believe this will be a great way for unbiased 3rd parties to conduct safety research on frontier LLMs.
Posted by Alex Wormuth (5.4k followers) 2 days ago · 5 likes · 926 views · view the original post on X. Kept by the AI Radar as Safety & policy.
More AI work like this
- I am all for sovereign AI, but ummm, this example is terrifying. Medical conditions are… — @zigelbaum
- Our opponents—a handful of Silicon Valley billionaires—are already highly organized,… — @AlexBores
- Should be something in here to annoy everybody: — @_AashishReddy
- How do you empower employees with AI choice while protecting sensitive data? — @CrowdStrike
- CTS co-founder @KonstantinPilz says China makes all its AI chips on Western DUV… — @MTSlive
- CTS co-founder @KonstantinPilz explains how he knows Chinese labs are distilling US… — @MTSlive
- CTS co-founder @KonstantinPilz on the first problem with pacing the frontier: nobody can… — @MTSlive
- X just pushed more For You code to GitHub. Credit to @XOpenSource. — @blankspeaker
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 27.2k posts from 4.8k X accounts over the last 14 days, 1.2k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:08 UTC. Full method.