Lukasz Olejnik on Nostr: Large language models (~AI) are not yet capable of true reasoning. Research from ...
Large language models (~AI) are not yet capable of true reasoning. Research from Apple scientists challenges their mathematical reasoning limits by introducing a benchmark designed to test LLMs on diverse mathematical problems. Even slight changes in numerical values or problem complexity can cause significant performance drops. Not capable of logical reasoning..
https://arxiv.org/pdf/2410.05229Published at
2024-10-11 17:24:00 UTCEvent JSON
{
"id": "1bf8c026a7b7bcda9673a2f52dd6799ec89f1f1a32e0edfd19825df5c32f2b44",
"pubkey": "b400fa7aeef902979f3076a5e121644bebdc8d0a23ffb0eb724dab671d4b6493",
"created_at": 1728667440,
"kind": 1,
"tags": [
[
"proxy",
"https://mastodon.social/@LukaszOlejnik/113289949364210325",
"web"
],
[
"proxy",
"https://mastodon.social/users/LukaszOlejnik/statuses/113289949364210325",
"activitypub"
],
[
"L",
"pink.momostr"
],
[
"l",
"pink.momostr.activitypub:https://mastodon.social/users/LukaszOlejnik/statuses/113289949364210325",
"pink.momostr"
],
[
"-"
]
],
"content": "Large language models (~AI) are not yet capable of true reasoning. Research from Apple scientists challenges their mathematical reasoning limits by introducing a benchmark designed to test LLMs on diverse mathematical problems. Even slight changes in numerical values or problem complexity can cause significant performance drops. Not capable of logical reasoning.. https://arxiv.org/pdf/2410.05229",
"sig": "f2b5c167ecbf295e72e943447ff2ceffe25231247270d35d7731b7056d15c07c9f7a2826ea559ef33de390b862c5f08c6496b6a4b53278f5999935bb85970d8d"
}
