News for hackers. Stuff that matters.

A comment on Introducing LFM3: Every Modality for Specialized Intelligence. Parent comment

Re:Introducing LFM3: Every Modality for Specialized Intellig... by agairola on Wednesday October 28, 2026 @09:22AM (#50273126)
on moderation, we run an open guardrail benchmark at raxIT Labs and the hosted d1 models do well. d1.1 is #1 of 30 at checking model output for harmful content (94.4 balanced accuracy), d1-ultra is #1 on harmful user requests (88.2). we haven't run the new 2B open weights yet so no number for those. results and method: https://dm-as-guardrails.raxitlabs.com
[ Parent | on HN ]
Re:Introducing LFM3: Every Modality for Specialized Intellig... by CMay on Wednesday October 28, 2026 @09:42PM (#50283496)
This tracks with my experience with their models. Nice work. It would be interesting to see what they could do if they optimized even more for moderation like this without going so far as to hurt the model performance overall.
[ Parent | on HN ]