How does AI handle insufficient information? 🤔 We tested an AI with questions about the Eiffel Tower, Big Ben, and the bastions of Valletta. The AI gave inconsistent answers when training data is limited or unclear. We also touch on AI poisoning, where AI models can be misled by fake data
▶️ https://buff.ly/yRDWPTf
#AI #InsufficientData #DataPoisoning #EiffelTower #BigBen #Valletta #TestingAI #Accuracy #TTMO
chribonn /
npub1um…exkj5
2025-03-21 16:30:00
Author Public Key
npub1umw5m74x3u0rx6pnf2f5nnf36hn5t92hgrtpc3u5dk8ctq4dv9sqfexkj5Published at
2025-03-21 16:30:00Event JSON
{
"id": "3b513cf40af80bd711684513de5c5be0e10a3c0b271f2dad3f15ce6539abf30f",
"pubkey": "e6dd4dfaa68f1e3368334a9349cd31d5e745955740d61c47946d8f8582ad6160",
"created_at": 1742574600,
"kind": 1,
"tags": [
[
"t",
"ai"
],
[
"t",
"insufficientdata"
],
[
"t",
"datapoisoning"
],
[
"t",
"eiffeltower"
],
[
"t",
"BigBen"
],
[
"t",
"valletta"
],
[
"t",
"testingai"
],
[
"t",
"accuracy"
],
[
"t",
"ttmo"
],
[
"proxy",
"https://twit.social/users/chribonn/statuses/114201369034188911",
"activitypub"
]
],
"content": "How does AI handle insufficient information? 🤔 We tested an AI with questions about the Eiffel Tower, Big Ben, and the bastions of Valletta. The AI gave inconsistent answers when training data is limited or unclear. We also touch on AI poisoning, where AI models can be misled by fake data \n▶️ https://buff.ly/yRDWPTf \n#AI #InsufficientData #DataPoisoning #EiffelTower #BigBen #Valletta #TestingAI #Accuracy #TTMO",
"sig": "6244be9e456a2500dc4dcd3f23745eaaeb4414449705cfdef57b319a73dcc6401d06efe015d3f13e7b67d16887ddeace335779127c46f83cfdb821893ab9c59b"
}