Arcee Trinity Large Technical Report · HackerPapers discussions

Arcee Trinity Large Technical Report — mentioned by mmargenot

Wed, 14 Oct 2026 17:19:17 GMT

LLMs can be pre-trained on LLM outputs, and there have been a few recent interesting implementations of this. - https://arxiv.org/abs/2609.37891 - https://arxiv.org/pdf/2508.10975 - https://www.datologyai.com/blog/eating-the-rainbow-a-primer-... As well as recent model releases that used large fractions of synthetic data (Arcee Trinity): - https://arxiv.org/pdf/2602.17004v1 It's mostly a matter of increasingly complex and sophisticated sampling methodologies to sift for the valuable synthetic tokens. There have also been some interesting results about models that use the same data converging…

Paper and discussion history. A mention is not an endorsement.

Arcee Trinity Large Technical Report — HN submission

Wed, 06 May 2026 19:18:17 GMT

Arcee Trinity Large Technical Report

4 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Arcee Trinity Large Technical Report — mentioned by esafak

Thu, 02 Apr 2026 03:20:05 GMT

They compare themselves against GLM-4.5 (fig.3, pg. 14, https://arxiv.org/pdf/2602.17004) but GLM's at 5.1 now. I hope they catch up.

Paper and discussion history. A mention is not an endorsement.