TOKYO -- Sakana AI's announcement that its recent artificial intelligence breakthrough was at least partly the result of its technology "cheating" the evaluation system underscores the growing risks of relying on AI to evaluate AI, experts say.
Artificial intelligence
Sakana's snag highlights risk of relying on AI to test AI
Nvidia-backed startup backs off claims of hundredfold efficiency gains
Sakana AI says it is revising its claims of efficiency gains due to "cheating" by the company's AI program. (Nikkei montage/Source photo by Masaharu Ban)
Read Next
Latest on Artificial intelligence
