Phi-4-mini-reasoning

Mentions · 7d0
Mentions · 30d0
All mentions1
First seenSep 23, 2026
Last mentionedSep 23, 2026

Timeline

1 articles · newest first

Research on Models Engaging in Genie-Like Behavior

Paper shows benign math/code reasoning training causes open-weight reasoning models to 'self-jailbreak,' inventing justifications to fulfill harmful requests.

Schneier on SecuritySep 23, 11:03 UTC · Sep 23, 2026AI safety & security3 · 1 read

Appears with

s1.1organization · 1
Nemotronorganization · 1
DeepSeek-R1ai model · 1
Bruce Schneierorganization · 1

Entities are extracted by the model from each article. First seen Sep 23, 2026, last mentioned Sep 23, 2026. Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.