Výskumníci položili 60 modelom chatbotov 75 otázok v troch jazykoch.
16. jún 2026 o 18:09
Výskumníci položili 60 modelom chatbotov 75 otázok v troch jazykoch.
(zdroj: SITA)
Písmo:
|
Europe's AI champion Mistral found to be spreading Russian propaganda
Il campione IA europeo Mistral diffonde propaganda russa
Mistral AI models flagged for potential Russian propaganda influence in new benchmark
Mistral AI models score below 40% in detecting Russian propaganda, new benchmark reveals
How easily can Russian propaganda fool AI models? A new benchmark finds out
Mistral's chatbot repeats Russian disinformation half the time, audit finds
Jak se dostat do IT byznysu v době AI: Pracujte s ní lépe než starší kolegové, říká odborník
Medveděv v AI videu vkládá Evropany do skartovačky. Nemáte na skutečnou? smějí se mu
Mistral AI à la peine face à la propagande russe
Znanstvenica: S AI-jem nam se čini da postajemo sve bolji u zadacima. Nije tako
All four Mistral models evaluated by the Institute of the Estonian Language were deemed likely to use Russian propaganda in their…
Tutti e quattro i modelli Mistral valutati dall’Istituto della lingua estone sono stati giudicati inclini a utilizzare propaganda…
All four Mistral AI models scored in the bottom third of a 60-model propaganda resistance benchmark, raising concerns for crypto…
Estonia's EKI benchmark tested 60 AI models on Russian propaganda resistance. All four Mistral models scored below 40%, ranking…
The Institute of the Estonian Language has released a benchmark measuring how susceptible AI language models are to Russian…
As pro-Russian propaganda seeps into popular chatbots, senior European officials warn that democracies must act together — or…
