zlacker

[parent] [thread] 1 comments
1. sgt101+(OP)[view] [source] 2025-01-22 20:11:15
What is the evidence for 1) ? I thought that the latest models were getting "somewhere" with fairly trivial reasoning tests like ARC-1
replies(1): >>sealec+wSb
2. sealec+wSb[view] [source] 2025-01-27 16:13:47
>>sgt101+(OP)
It may be that you can just find the solution for these tests by interpolating from a very large dataset.
[go to top]