Deep Dive into Kernels, RL, and Agent Reward Hacking

AI Engineer · youtube · 2026-07-11

Daniel Han from Unsloth hosted an advanced workshop titled *Kernels, RL, and Agent Reward Hacking*. The presentation focused on low-level technical optimization and Agent training mechanisms, exploring the Reward Hacking problem encountered when building autonomous agents, along with related underlying implementation details.

Related event: Daniel Han Explores Kernels, RL, and Agent Reward Hacking(2 posts)→

Original post →

More from coding & agent

coding & agent channel →