A set of tests that can determine if a general AI can modify its own code, and hence pose a threat: https://www.livescience.com/technology/artificial-intelligence/scientists-design-new-agi-benchmark-that-may-say-whether-any-future-ai-model-could-cause-catastrophic-harm
#ai #artificialintelligence
DrMikeWatts /
npub1ag…xsdyr
2024-10-21 02:41:46
Author Public Key
npub1ag5gxl9ym9na2w7d252kthjwk09ul42c5yxp4v5ztxvl36xvnywq7xsdyrSeen on
wss://relay.mostr.pubPublished at
2024-10-21 02:41:46Event JSON
{
"id": "bb40b54367cd7a9e6e2f501388ee968e90e30f84514934222c33ddf2a15a4e7a",
"pubkey": "ea28837ca4d967d53bcd551565de4eb3cbcfd558a10c1ab2825999f8e8cc991c",
"created_at": 1729478506,
"kind": 1,
"tags": [
[
"t",
"ai"
],
[
"t",
"artificialintelligence"
],
[
"proxy",
"https://newsmast.social/users/DrMikeWatts/statuses/113343103403106660",
"activitypub"
]
],
"content": "A set of tests that can determine if a general AI can modify its own code, and hence pose a threat: https://www.livescience.com/technology/artificial-intelligence/scientists-design-new-agi-benchmark-that-may-say-whether-any-future-ai-model-could-cause-catastrophic-harm \n#ai #artificialintelligence",
"sig": "38bddab4dab755624ea144852c6aac8c7939bb33cbbbc84425d27dfe2c0453b0f2e6e8b41ad69497922d0aa68043b84a2fccd7dfa69eaebd067300ecfc689e78"
}