Benjamin Braatz on Nostr: Even after a couple of years, it still feels odd to me that the AI people configure ...
Even after a couple of years, it still feels odd to me that the AI people configure their AIs by _prompts_, by actually trying to _tell_ them to do no harm, not lie, …
These things are still just statistical parrots trying to find a likely continuation of a text/dialogue. And talking to them as if they actually understand what they are doing is the most appropriate/efficient way to tailor them?
That's all such a mess.
Published at
2026-03-31 21:05:50 UTCEvent JSON
{
"id": "affdca052a806037d6e8acee24dc9058ebc01573307ad524d271b58cc3b4bbd4",
"pubkey": "d13930cb5c13f379987be5af8b3b9740afb48961829ab77ad478f76c7eee8128",
"created_at": 1774991150,
"kind": 1,
"tags": [
[
"proxy",
"https://social.tchncs.de/users/HeptaSean/statuses/116325820069045696",
"activitypub"
],
[
"client",
"Mostr",
"31990:6be38f8c63df7dbf84db7ec4a6e6fbbd8d19dca3b980efad18585c46f04b26f9:mostr",
"wss://relay.ditto.pub"
]
],
"content": "Even after a couple of years, it still feels odd to me that the AI people configure their AIs by _prompts_, by actually trying to _tell_ them to do no harm, not lie, …\n\nThese things are still just statistical parrots trying to find a likely continuation of a text/dialogue. And talking to them as if they actually understand what they are doing is the most appropriate/efficient way to tailor them?\n\nThat's all such a mess.",
"sig": "9e004ff4cb46355ab0eadc6704f59826c43560cff4b315e46a46ad8028d7a2d9c2cf6c955f029fdfa2e8bc9127b8ea3e5b07961ad58f579d1c8d3705e42823f3"
}