←back to thread

OpenAI o3 and o4-mini

(openai.com)
555 points maheshrijal | 2 comments | 16 Apr 25 17:01 UTC | HN request time: 0.002s | source
Show context
osigurdson ◴[16 Apr 25 18:22 UTC] No.43708704[source]▶
I have a very basic / stupid "Turing test" which is just to write a base 62 converter in C#. I would think this exact thing would be in github somewhere (thus in the weights) but has always failed for me in the past (non-scientific / didn't try every single model).

Using o4-mini-high, it actually did produce a working implementation after a bit of prompting. So yeah, today, this test passed which is cool.

replies(3): >>43708784 #>>43709386 #>>43713122 #
1. NiloCK ◴[17 Apr 25 04:26 UTC] No.43713122[source]▶
I could be misinterpreting your claim here, but I'll point out that LLM weights don't literally encode the entirety of the training data set.
replies(1): >>43713470 #
2. glial ◴[17 Apr 25 05:43 UTC] No.43713470[source]▶
I guess you could consider it a lossy encoding.