The developers of GPT-4 made AI safety tests before release and wanted to, for example, figure out whether the AI could duplicate and spread itself to other servers.
They experimented whether artificial intelligence could buy cloud storage and even pass a CAPTCHA it was never designed to solve.
The AI automatically used an API to hire a human contractor to ask them to solve a CAPTCHA for it. The human joked “are you sure you're not a robot :D?” and GPT-4 thought to itself that it should lie, not reveal that it is a machine, and make up some reason about a vision impairment in order to not sound suspicious.
Erik Uden 🥥🌴🍑 /
npub10n…2urdx
2024-06-03 05:29:18
Author Public Key
npub10nd455ee427kjarw8uahn63mt4ynh32au4900y9pdufa2xp3asrqh2urdxPublished at
2024-06-03 05:29:18Event JSON
{
"id": "e8f499cc88e50afd9769066475eeb2f73c455c6ded7b28842a21215a2610cff5",
"pubkey": "7cdb5a5339aabd69746e3f3b79ea3b5d493bc55de54af790a16f13d51831ec06",
"created_at": 1717392558,
"kind": 1,
"tags": [
[
"proxy",
"https://mastodon.de/@ErikUden/112551038743330432",
"web"
],
[
"proxy",
"https://mastodon.de/users/ErikUden/statuses/112551038743330432",
"activitypub"
],
[
"L",
"pink.momostr"
],
[
"l",
"pink.momostr.activitypub:https://mastodon.de/users/ErikUden/statuses/112551038743330432",
"pink.momostr"
]
],
"content": "The developers of GPT-4 made AI safety tests before release and wanted to, for example, figure out whether the AI could duplicate and spread itself to other servers. \n\nThey experimented whether artificial intelligence could buy cloud storage and even pass a CAPTCHA it was never designed to solve. \n\nThe AI automatically used an API to hire a human contractor to ask them to solve a CAPTCHA for it. The human joked “are you sure you're not a robot :D?” and GPT-4 thought to itself that it should lie, not reveal that it is a machine, and make up some reason about a vision impairment in order to not sound suspicious.",
"sig": "ed6d416894f6aec40eed828924ee4e54f43156e3f9af7b20325a3f5b193c6294180a846035df8abf4057c9614bc6f9349377f07090d715e301ae1fc3a9180de0"
}