Robert on Nostr: "In this paper, we empirically studied the characteristics of ChatGPT answers to SO ...
"In this paper, we empirically studied the characteristics of ChatGPT answers to SO questions through a combination of manual analysis, linguistic analysis, and user study. Our manual analysis shows that ChatGPT produces incorrect answers more than 50% of the time"
https://dl.acm.org/doi/pdf/10.1145/3613904.3642596Dato mata relato.
Published at
2024-05-21 13:01:24Event JSON
{
"id": "6babd069d556b13be517a7ddfb44eac75e6c8cd052d26a8db0514fc9da22c358",
"pubkey": "fe3411285b0b419b91978ba2c29cc66bb81348c03306c82f22f8cd0a4309e698",
"created_at": 1716296484,
"kind": 1,
"tags": [
[
"proxy",
"https://fosstodon.org/@rsf92/112479206394278658",
"web"
],
[
"proxy",
"https://fosstodon.org/users/rsf92/statuses/112479206394278658",
"activitypub"
],
[
"L",
"pink.momostr"
],
[
"l",
"pink.momostr.activitypub:https://fosstodon.org/users/rsf92/statuses/112479206394278658",
"pink.momostr"
]
],
"content": "\"In this paper, we empirically studied the characteristics of ChatGPT answers to SO questions through a combination of manual analysis, linguistic analysis, and user study. Our manual analysis shows that ChatGPT produces incorrect answers more than 50% of the time\"\n\nhttps://dl.acm.org/doi/pdf/10.1145/3613904.3642596\n\nDato mata relato.",
"sig": "16541236bf1e8914967f4bf86ef14e8ad96db5a901d670506f89384fb47295ad23b4772aca39902a10f12ddd1ec7fab9529ce4ec05cfb52691af1d03f9e55a9f"
}
