Use the vitals package with ellmer to evaluate and compare the accuracy of LLMs, including writing evals to test local models.

OpenAI launches Lockdown Mode and Elevated Risk warnings to protect ChatGPT against prompt-injection attacks and reduce data-exfiltration risks.

Robot boxing drew paying fans in San Francisco as VR pilots controlled Unitree G1 humanoids, hinting at a future league of heavier, full-height fighters.