Terence Eden on Nostr: This was GPT-4o. It excels at producing authoritative *sounding* text. But it is ...
Published at
2024-09-04 22:07:37Event JSON
{
"id": "9e329a48186ed2deb6c7ff8cb1e627c60075ad66212a450c4304ebde23daefd1",
"pubkey": "fddf487eea9db57a6e320f80e5cb63de50bedf539695a41c0d447be6c23643e1",
"created_at": 1725487657,
"kind": 1,
"tags": [
[
"e",
"c0a9f13d6fb48c656511f7275ebed59fc915c1a110654e5ecc69223d171f3e23",
"wss://relay.mostr.pub",
"reply"
],
[
"proxy",
"https://mastodon.social/users/Edent/statuses/113081559115316943",
"activitypub"
]
],
"content": "This was GPT-4o. It excels at producing authoritative *sounding* text.\n\nBut it is utter rubbish. Its accuracy is 2.5/7. Even if you're being generous, it is wrong over half the time.\n\nSurely the AI bubble has to burst soon?\n\nhttps://chatgpt.com/share/adf43713-a55c-47be-91e2-4c2de994a739",
"sig": "d4fe63b4364cc2891db5efa47ed0802d650584c28353b51c3f2eb6472087f57d6592d394a3c771f4214d0733cf1839d05f66f624837c01070c071965d5302d90"
}