Agents
We tested Jev against LLM judges on accuracy, repeatability, latency, and cost to see whether System One models could offer a new approach t…
We tested Jev against LLM judges on accuracy, repeatability, latency, and cost to see whether System One models could offer a new approach to agent evaluation. https://x.com/i/article/2101448785255907
We tested Jev against LLM judges on accuracy, repeatability, latency, and cost to see whether System One models could offer a new approach to agent evaluation. https://x.com/i/article/2101448785255907328
Related
- We are starting to role out our Trace Judge model to early partners today Designed to detect errors in agent trajectories at 1/100th of the …
- 1/5 We’re seeing 4 common agent optimization methods for hitting the right accuracy-cost or accuracy-latency tradeoff. We tried them all out…
- ICYMI: SmithDB is our purpose-built data layer for agent observability + eval workloads. Supporting increasingly complex query patterns at l…
Source: Harrison Chase (X) | 2026-09-19