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
Experimenting with Jev in a Retrosynthesis Agent: Fast Decisions vs. Full Reasoning
The author tried Jev in a retrosynthesis agent to explore which decisions need a full reasoning pass from a general-purpose LLM and which can be handled by a fast decision model like Jev.
We recently tried Jev in a retrosynthesis agent. The question behind this small experiment was simple: which decisions deserve a full reasoning pass from a general-purpose LLM, and which could be handled by a fast decision model like Jev? Retrosynthesis involves many recurring
· 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.
