TypeSafe AI Added to Citation Checker Tool
User added @typesafeai to their citation checker and praises it, free to try at PaperTrellis, tagged with Jev and AI in medicine. Link
New Contrastive Language Model (CLM) Emerges as a Rival to Jev
The post introduces a new training model called Contrastive Language Model (CLM), positioned as a rival to Jev. Its idea is to first understand the current situation, then match the best action from candidate actions; during training, correct state-action pairs are pulled closer and incorrect ones are pushed apart, and at inference it does not need to generate like a typical LLM.
對標 Jev 的新訓練模型 Contrastive Language Model（CLM）來了？！ CLM 的想法是先理解現在是什麼情況，再從候選動作裡找出最匹配的一個。 訓練時，它會讓正確的「狀態－動作」組合更接近、錯誤的組合更遠。到了實際執行時，也不需要像一般 LLM
· 0 likesOpen on X
More like this
JevBench: First Benchmark for Jev-Class Models Released
JevBench is the first benchmark for Jev-class models. Original Jev by TypeSafe AI leads at 75.3, with SemIf second at 74.6. Full results at benchmarkheaven.com/jev-models. Link
Jev Completes 100 Consecutive Trolley Problems
The post says someone entrusted their life to Jev and had it complete 100 consecutive trolley problems; in the first round, Jev chose to pull the lever with 99% probability, sacrificing 1 to save 5.
