AI Dynamics

Global AI News Aggregator

About

Model trained to ‘see through’ typos may misrecognize words

It does it even if you start with “monologue” etc. where there’s no real word with a q instead. I think that’s a plausible theory why it happens though — it’s trained to “see through” some apparent typos, like “How how many q’s in plague?”, and the recognition isn’t perfect

→ View original post on X — @goodside