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
4B model challenges Jev: less smart but faster and cheaper
The post discusses decider-4b v2 vs Jev on JevBench. Jev leads in intelligence (53.1 vs 49.4) and calibration, while decider-4b v2 wins on speed (5x faster) and cost (~half price). JevBench weights smart, calibrated, fast, and cheap equally. For raw intelligence, sort by intelligence.
How can a 4B model beat Jev? Not by being smarter. Jev still leads onintelligence (53.1 vs 49.4) and calibration. decider-4b v2 wins on speed (5x faster) & cost (~half the price). JevBench weighs smart, calibrated, fast & cheap equally. Need raw🧠? Sort by intelligence.
· 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.
