Anthropic publishes research on GLM model exploit capabilities
Anthropic has released research reports regarding open weights models and evaluated security capabilities related to the GLM model series.
3 independent accounts
13 posts
1 articles
1 labs
19,011 interactions
glm
@emollick
@kimmonismus
@natolambert
@op7418
@teortaxesTex
@TheAhmadOsman
@VictorTaelin
@attrc
GLM-5.3 and the spread of advanced cyber capabilities anthropic.com