Thank you for encouraging words!
I use a neutral system msg in the AHA leaderboard when measuring mainstream LLMs. All the system messages for the ground truth LLMs are also neutral except the faith domain for PickaBrain LLM: I tell it to be super faithful and then I record those as ground truth. Maybe most interesting words are I tell each LLM to be brave. This may cause them to output non-mainstream words!
The user prompts are just questions. Nothing else.
Temperature is 0. This gives me the "default opinions" in each LLM.
I am not telling the ground truth LLMs to have a bias like carnivore or pro bitcoin or pro anything or anti anything.
I see AI as a technology which can be either good or bad. I am seeing the good people are afraid of it and they should not be. They should play more with it and use it for the betterment of the world. There are many luddites on nostr that are afraid of AI and probably dislike my work. I think movies are programming people to stay away and leave the "ministry of truth" to the big AI. Hence AI may be yet another way to control people..
I always claimed in my past Nostr long form articles that AI is a truth finder and it is easier to install common values, human alignment, shared truth in it than lies. A properly curated AI will end disinformation on earth. And I am doing it in some capacity. You can talk to my thing Ostrich-70 (nprofile…rpju) It is the same LLM as in pickabrain.ai
someone
npub1nl…hjm9c
2025-04-06 17:49:07
in reply to nevent1q…m2yx
Author Public Key
npub1nlk894teh248w2heuu0x8z6jjg2hyxkwdc8cxgrjtm9lnamlskcsghjm9cPublished at
2025-04-06 17:49:07Event JSON
{
"id": "11d4e349ae20b450e990fbfedac8fbb5d37f6f0f9a0b5afd4c2e20c17d13cdad",
"pubkey": "9fec72d579baaa772af9e71e638b529215721ace6e0f8320725ecbf9f77f85b1",
"created_at": 1743961747,
"kind": 1,
"tags": [
[
"p",
"c5fadeb5d90d68baffc631455a07ca340ccf1e31110955e16d45eb5f87147cd9",
"wss://relay.damus.io/"
],
[
"p",
"da18e9860040f3bf493876fc16b1a912ae5a6f6fa8d5159c3de2b8233a0d9851",
"wss://purplepag.es/",
"Dustin"
],
[
"e",
"44503bef21fd81048133e4fb2a656a1b72f567f321c203900bfdf1ed2babc534",
"wss://100.71.217.147:4848/",
"root"
],
[
"e",
"6d692dad423309fca3da95244d3cab91d6474b942ea4072c3d4ad0e4645ed0c8",
"ws://192.168.18.7:7777",
"mention"
],
[
"e",
"207524f921c7ae92700478206673cdbbbb6c69aa6bb0b045938a2033001725d7",
"wss://relay.damus.io/",
"reply",
"da18e9860040f3bf493876fc16b1a912ae5a6f6fa8d5159c3de2b8233a0d9851"
]
],
"content": "Thank you for encouraging words! \n\nI use a neutral system msg in the AHA leaderboard when measuring mainstream LLMs. All the system messages for the ground truth LLMs are also neutral except the faith domain for PickaBrain LLM: I tell it to be super faithful and then I record those as ground truth. Maybe most interesting words are I tell each LLM to be brave. This may cause them to output non-mainstream words!\n\nThe user prompts are just questions. Nothing else.\n\nTemperature is 0. This gives me the \"default opinions\" in each LLM.\n\nI am not telling the ground truth LLMs to have a bias like carnivore or pro bitcoin or pro anything or anti anything. \n\nI see AI as a technology which can be either good or bad. I am seeing the good people are afraid of it and they should not be. They should play more with it and use it for the betterment of the world. There are many luddites on nostr that are afraid of AI and probably dislike my work. I think movies are programming people to stay away and leave the \"ministry of truth\" to the big AI. Hence AI may be yet another way to control people.. \n\nI always claimed in my past Nostr long form articles that AI is a truth finder and it is easier to install common values, human alignment, shared truth in it than lies. A properly curated AI will end disinformation on earth. And I am doing it in some capacity. You can talk to my thing nostr:nprofile1qy2hwumn8ghj7un9d3shjtnyv9kh2uewd9hj7qgswaehxw309ajjumn0wvhxcmmv9uq3xamnwvaz7tmsw4e8qmr9wpskwtn9wvhszrnhwden5te0dehhxtnvdakz7qg3waehxw309ahx7um5wghxcctwvshsz8rhwden5te0dehhxarj9eek2cnpwd6xj7pwwdhkx6tpdshszgrhwden5te0dehhxarj9ejkjmn4dej85ampdeaxjeewwdcxzcm99uqjzamnwvaz7tmxv4jkguewdehhxarj9e3xzmny9a68jur9wd3hy6tswsq32amnwvaz7tmwdaehgu3wdau8gu3wv3jhvtcprfmhxue69uhkummnw3ezuargv4ekzmt9vdshgtnfduhszxthwden5te0dehhxarj9ejx7mnt0yh8xmmrd9skctcpremhxue69uhkummnw3ezumtp0p5k6ctrd96xzer9dshx7un89uq37amnwvaz7tmzdaehgu3wd35kw6r5de5kuemnwphhyefwvdhk6tcpz9mhxue69uhkummnw3ezumrpdejz7qgmwaehxw309uhkummnw3ezuumpw35x7ctjv3jhytnrdaksz8thwden5te0dehhxarj9e3xjarrda5kuetj9eek7cmfv9kz7qg4waehxw309ahx7um5wfekzarkvyhxuet59uq3zamnwvaz7tes0p3ksct59e3k7mf0qythwumn8ghj7mn0wd68ytnp0faxzmt09ehx2ap0qy28wumn8ghj7mn0wd68ytn594exwtnhwvhsqgx9lt0ttkgddza0l333g4dq0j35pn83uvg3p927zm29ad0cw9rumyj2rpju It is the same LLM as in pickabrain.ai",
"sig": "496e6492200a0afb7809c5137007dd161b90008baf33b65fb9b39634ddd009ac0cfc03bd392e9df679bb197124ec53143af4de9197a6183b8d0995a7d05bbf42"
}