OpenAIs new embedding seems to really prefer earlier text. Cos(emb(t1), emb(t1+t2)) > Cos(emb(t1), emb(t2+t1)) ~97% of the time of the 1000 examples I tried. Interesting retrieval consideration

This holds true for Cos(emb(t2), emb(t1+t2)) < cos(emb(t2), emb(t2+t1)) as well. So the second string doesn’t matter.