A new study has revealed that the much-hyped 90th-percentile figure was actually skewed toward repeat test-takers who had already failed the exam one or more times — a much lower-scoring group than those who generally take the test. The researcher published his findings March 30 in the journal Artificial Intelligence and Law
#AI #tech #technology #chatgpt
https://www.livescience.com/technology/artificial-intelligence/gpt-4-didnt-ace-the-bar-exam-after-all-mit-research-suggests-it-barely-passed
Jürgen /
npub1dj…mvvqx
2024-06-02 16:35:55
Author Public Key
npub1dj2slwt7ztpgf2jf9276wm456nfwvsxunzrg7vnxnqhz5h00sqmq4mvvqxPublished at
2024-06-02 16:35:55Event JSON
{
"id": "e750eafbe7d357c3ae46bfeb157f6007a2cec499bc327b1c26dea7ca588c8dbe",
"pubkey": "6c950fb97e12c284aa492abda76eb4d4d2e640dc98868f3266982e2a5def8036",
"created_at": 1717346155,
"kind": 1,
"tags": [
[
"t",
"chatgpt"
],
[
"t",
"technology"
],
[
"t",
"tech"
],
[
"t",
"ai"
],
[
"proxy",
"https://mastodon.nl/users/Jigsaw_You/statuses/112547997668706401",
"activitypub"
]
],
"content": "A new study has revealed that the much-hyped 90th-percentile figure was actually skewed toward repeat test-takers who had already failed the exam one or more times — a much lower-scoring group than those who generally take the test. The researcher published his findings March 30 in the journal Artificial Intelligence and Law\n\n#AI #tech #technology #chatgpt\n\nhttps://www.livescience.com/technology/artificial-intelligence/gpt-4-didnt-ace-the-bar-exam-after-all-mit-research-suggests-it-barely-passed",
"sig": "26cc47b1a530ce3a6059677c1c8d42e3c854fd040408a6b53cb124f5a19bea927ebcd594f8395ecefc99a76e17503e41baa21382fb8310e6573cfeda7a0177a0"
}