A team of researchers has found a way to steer the output of large language models by manipulating specific concepts inside these models. The new method could lead to more reliable, more efficient, ...

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

Abstract: Recent developments in Large Language Models (LLMs) have created new possibilities to integrate integrate these models into robotics platforms, allowing unmanned aerial vehicles (UAVs) to ...

As AI deployments scale and start to include packs of agents autonomously working in concert, organizations face a naturally amplified attack surface.