←back to thread

GPT-4 and professional benchmarks: the wrong answer to the wrong question

(aisnakeoil.substack.com)
340 points agomez314 | 5 comments | 21 Mar 23 13:12 UTC | HN request time: 0s | source
Show context
ChancyChance ◴[21 Mar 23 13:58 UTC] No.35246181[source]▶
"10/10 pre-2021, 0/10 post-2021"

I guffawed. Hasn't there been ANY update to the Turing test since it was proposed? I suspect the answer to the benchmarking issue was address by philosophers long before we got here.

replies(2): >>35246541 #>>35248367 #
enono ◴[21 Mar 23 16:19 UTC] No.35248367[source]▶
Why is your username green?!
replies(1): >>35249917 #
schrodinger ◴[21 Mar 23 17:59 UTC] No.35249917[source]▶
New account
replies(1): >>35253224 #
YeGoblynQueenne ◴[21 Mar 23 22:01 UTC] No.35253224{3}[source]▶
Yes, but why green? In particular?
replies(1): >>35256757 #
1. wrycoder ◴[22 Mar 23 04:13 UTC] No.35256757{4}[source]▶
Greenhorn. Look it up.
replies(1): >>35258656 #
2. YeGoblynQueenne ◴[22 Mar 23 09:24 UTC] No.35258656[source]▶
Who says that's the association? Citation please.
replies(1): >>35275408 #
3. wrycoder ◴[23 Mar 23 14:31 UTC] No.35275408[source]▶
LOL you’d have to ask PG, probably. But, you asked for a plausible reason behind an arbitrary choice.

What color would you choose?

replies(1): >>35277428 #
4. YeGoblynQueenne ◴[23 Mar 23 16:41 UTC] No.35277428{3}[source]▶
Green.
replies(1): >>35277941 #
5. wrycoder ◴[23 Mar 23 17:13 UTC] No.35277941{4}[source]▶
+1 !