AI overly affirms users asking for personal advice - https://news.stanford.edu/stories/2026/03/ai-advice-sycophantic-models-research
Not only are AIs far more agreeable than humans when advising on interpersonal matters, but users also prefer the sycophantic models.
#im
TWiT News Feed
npub1vc…esftz
2026-03-29 01:24:36 UTC
Author Public Key
npub1vcynmvqa3yq67ytt6vrrsgj9sytmpkzfh0znvak9an4xe7vxr2dqqesftzSeen on
wss://relay.ditto.pubPublished at
2026-03-29 01:24:36 UTCEvent JSON
{
"id": "cf3f1f9fae991207deab8c832b3c74b04b3656f60f87b5f88c67c5aa336a9c39",
"pubkey": "66093db01d8901af116bd3063822458117b0d849bbc53676c5ecea6cf9861a9a",
"created_at": 1774747476,
"kind": 1,
"tags": [
[
"t",
"im"
],
[
"proxy",
"https://twit.social/users/twitnews/statuses/116309850638182448",
"activitypub"
],
[
"client",
"Mostr",
"31990:6be38f8c63df7dbf84db7ec4a6e6fbbd8d19dca3b980efad18585c46f04b26f9:mostr",
"wss://relay.ditto.pub"
]
],
"content": "AI overly affirms users asking for personal advice - https://news.stanford.edu/stories/2026/03/ai-advice-sycophantic-models-research\n\nNot only are AIs far more agreeable than humans when advising on interpersonal matters, but users also prefer the sycophantic models.\n\n#im",
"sig": "1dcb81d825359e7d4fedd88af9578a7826d33ae40f35ec0fb8012754aa0f433017b4680aa65b1f3389c87ea77833067792298ecfb118857d61856f634f1a1aea"
}