Saturn test: AI wrong on 57% of financial questions, Bittensor in focus
- —AI models failed 57% of 10,000 financial questions in Saturn's test
- —Error rates rise as money and savings queries grow more complex
- —After the AI shortfall, market attention turns to Bittensor (TAO)
Why it matters: Weak AI performance on financial questions strengthens the decentralized AI narrative and could support demand for tokens like TAO.
Source: Coinotag