pull down to refresh

OpenAI o3 beats FrontierMath - because OpenAI funded the test and cheatedpivot-to-ai.com/2025/01/20/openai-o3-beats-frontiermath-because-openai-funded-the-test-and-had-access-to-questions/
366 sats \ 1 comment \ @StillStackinAfterAllTheseYears 19h tech
So that kinda-hyped test about how good OpenAI was with math compared to other models? Turns out they had access to the questions.
We are so living in the age of conmen.
write
preview
related posts
135 sats \ 0 replies \ @south_korea_ln 17h
We are so living in the age of conmen.
And it pays.
Reminds me of one of their older presentations where supposedly one could use ChatGPT effortless as a replacement teacher. It turned out to be scripted too. Yet they get away with it. For now.
reply