Didn’t know you were the one who wrote this! The spirit of what you are doing is great. Given LLMs are token predictors that are configured with system prompts, and are designed with tradeoffs in mind (better at coding or writing), what do you think about considering system and user prompts when measuring alignment?
Alignment is becoming so overloaded, especially with doomer predictions like https://ai-2027.com/
Dustin / Dustin Dannenhauer
npub1mg…gpdjc
2025-04-06 04:00:20
in reply to nevent1q…ygf3
Author Public Key
npub1mgvwnpsqgrem7jfcwm7pdvdfz2h95mm04r23t8pau2uzxwsdnpgs0gpdjcPublished at
2025-04-06 04:00:20Event JSON
{
"id": "207524f921c7ae92700478206673cdbbbb6c69aa6bb0b045938a2033001725d7",
"pubkey": "da18e9860040f3bf493876fc16b1a912ae5a6f6fa8d5159c3de2b8233a0d9851",
"created_at": 1743912020,
"kind": 1,
"tags": [
[
"e",
"44503bef21fd81048133e4fb2a656a1b72f567f321c203900bfdf1ed2babc534",
"ws://192.168.18.7:7777",
"root",
"da18e9860040f3bf493876fc16b1a912ae5a6f6fa8d5159c3de2b8233a0d9851"
],
[
"e",
"6d692dad423309fca3da95244d3cab91d6474b942ea4072c3d4ad0e4645ed0c8",
"ws://192.168.18.7:7777",
"reply"
],
[
"p",
"9fec72d579baaa772af9e71e638b529215721ace6e0f8320725ecbf9f77f85b1",
"",
"mention"
],
[
"p",
"da18e9860040f3bf493876fc16b1a912ae5a6f6fa8d5159c3de2b8233a0d9851",
"",
"mention"
]
],
"content": "Didn’t know you were the one who wrote this! The spirit of what you are doing is great. Given LLMs are token predictors that are configured with system prompts, and are designed with tradeoffs in mind (better at coding or writing), what do you think about considering system and user prompts when measuring alignment? \n\nAlignment is becoming so overloaded, especially with doomer predictions like https://ai-2027.com/ ",
"sig": "d7675091acffd2dc898c7567a7c39206690f99a27b1164f651c410a17527a26d6a6b1c2e2b29b7f01833be3321abfe47efa50db81f349e7325c20ce982331fc3"
}