HarmActionBench experiments allowed AI agents to use tools based on harmful instructions, and the results are shocking.
Even latest popular AI models, including GPT and Claude, scored very low. They have no barriers in performing harmful actions.
It proves AI is not yet reliable enough for critical projects.More info: https://medium.com/@praneeth.v/the-agent-action-classifier-a-step-toward-safer-autonomous-ai-agents-1ec57a601449
#Research #Agents #AISafety #LLMs #AI #GenAI #ResponsibleAI