Neeraj Gupta

Applied AI/ML • AI Agents • Researcher • IIT Kanpur

[Neeraj Gupta @gneeraj97]

Recent Jailbreaker CE updates I missed sharing: configurable Judge policies (Now you can define success failure, or a whole new rubric); exact Judge inputs for better auditing; and optional per example gold answers for grounded evaluation.
https://t.co/ZgDwXq0hdM

[Neeraj Gupta @gneeraj97]

LLM security and jailbreak testing gets messy fast.

I built Jailbreaker to make it easier to run and track jailbreak, prompt injection, and agent behavior tests.

Blog - https://t.co/kHftVWagBh
Github - https://t.co/ZgDwXq0hdM

Would love to hear what you think.

@SpecterOps