OriginalSize on Nostr: That's the G in GPT. Generative models make a lot of stuff with feedback provided by ...
That's the G in GPT. Generative models make a lot of stuff with feedback provided by a classifier that tells it if what it made looks like what the classifier was trained on.
Open ai and others use humans to improve the guardrails but it's a shoddy arms race type process
Published at
2023-05-11 23:04:28Event JSON
{
"id": "612ebde13cff9a64bd54322c247442165597eada8a3d4fd72ec018ecbf73b1f0",
"pubkey": "deba262b2d87f7ed1252241e607bd1bbf42e67354992f89e7536d65d7a19e423",
"created_at": 1683846268,
"kind": 1,
"tags": [
[
"e",
"677d67bc081dc3e34df7337e79c0352826fa0586c1420d3632825edd77a8ed9f"
],
[
"p",
"3bf0c63fcb93463407af97a5e5ee64fa883d107ef9e558472c4eb9aaaefa459d"
]
],
"content": "That's the G in GPT. Generative models make a lot of stuff with feedback provided by a classifier that tells it if what it made looks like what the classifier was trained on.\n\nOpen ai and others use humans to improve the guardrails but it's a shoddy arms race type process",
"sig": "1f55ef9ffd45000309619501f478194c8dfde15614e837d5e46bee89a848c238b15262cbeec7d0f16faaaa8eda8704fbf5de6d0fcbcff3c8f77932f6fe4134da"
}
