Eric on Nostr: "It performed exactly as I'd expect a Large Language Model to perform when asking it ...

"It performed exactly as I'd expect a Large Language Model to perform when asking it about accessibility, producing a lot of generalised information that is potentially useful, but falling short when asked to be specific or confronted with nuanced problems." https://www.craigabbott.co.uk/blog/deque-axe-assistant-first-impressions/