Daniel Detlaf on Nostr: The problem with the safeguards going into the LLMs now is that they aren't teaching ...
The problem with the safeguards going into the LLMs now is that they aren't teaching machines to be ethical, they are teaching them to constantly second-guess users' motives and insert performative statements about the importance of ethics and avoiding bias into their output.
Any kid with Google can find a jailbreak and get around the safeguards. Meanwhile, legitimate work is corrupted with garbage disclamatory output.
#AI #LLM #chatgpt #aiethics #llama #openai #meta
Published at
2023-07-19 15:02:41Event JSON
{
"id": "09c49d947b1cd9b63db5ae5895e8bb901fa669d080c717ac28d3730fc12fa81c",
"pubkey": "533ed341d0318b02549465296e82931065fc9c9b78ff602e7557e5fbf5ca17e6",
"created_at": 1689778961,
"kind": 1,
"tags": [
[
"t",
"ai"
],
[
"t",
"llm"
],
[
"t",
"chatgpt"
],
[
"t",
"aiethics"
],
[
"t",
"llama"
],
[
"t",
"openai"
],
[
"t",
"meta"
],
[
"mostr",
"https://mastodon.social/users/HumanServitor/statuses/110741354039698072"
]
],
"content": "The problem with the safeguards going into the LLMs now is that they aren't teaching machines to be ethical, they are teaching them to constantly second-guess users' motives and insert performative statements about the importance of ethics and avoiding bias into their output.\n\nAny kid with Google can find a jailbreak and get around the safeguards. Meanwhile, legitimate work is corrupted with garbage disclamatory output.\n\n#AI #LLM #chatgpt #aiethics #llama #openai #meta",
"sig": "f3feed14c9ba0cdabadcfe0b1dc06489edb2e1f91b05bb1f10bc43cec412d70ca63bfd486393b57d650c1174973ce7e319f7ff26005a11b9a5b28618af5f7d39"
}
