"Most AI benchmarks today test how good a model is at completing a task on its own, not on how well a model collaborates with a human. (This is likely part of the reason for the gap between benchmark performance and real-world usefulness)."
-Steering AI Beyond Automation, Gabriel Unger and Arvind Narayanan
https://www.normaltech.ai/p/steering-ai-beyond-automation
Cory Doctorow
npub1yx…75qvv
2026-10-15 05:13:13 UTC
Author Public Key
npub1yxzkmtuyctjw2pffp6e9uvyrkp29hrqra2tm3xp3z9707z06muxsg75qvvSeen on
wss://relay.mostr.pubPublished at
2026-10-15 05:13:13 UTCEvent JSON
{
"id": "d14c3f08f1b28c50bd4c1326ff15287495d376056a85369aeac791ee38393ff6",
"pubkey": "21856daf84c2e4e505290eb25e3083b0545b8c03ea97b89831117cff09fadf0d",
"created_at": 1792041193,
"kind": 1,
"tags": [
[
"proxy",
"https://mamot.fr/users/pluralistic/statuses/117443211681612137",
"activitypub"
],
[
"client",
"Mostr",
"31990:6be38f8c63df7dbf84db7ec4a6e6fbbd8d19dca3b980efad18585c46f04b26f9:mostr",
"wss://relay.ditto.pub"
]
],
"content": "\"Most AI benchmarks today test how good a model is at completing a task on its own, not on how well a model collaborates with a human. (This is likely part of the reason for the gap between benchmark performance and real-world usefulness).\"\n\n-Steering AI Beyond Automation, Gabriel Unger and Arvind Narayanan\n\nhttps://www.normaltech.ai/p/steering-ai-beyond-automation",
"sig": "c8fe57377c48d13d57acb83847c051eba13361418a55cfbd9acb080bcfd654ff4c3a2690a6407120974155a3153e2d6e2666a944509ce206925904e76f73d151"
}