Papers2

#jailbreak detection

Building Production-Ready Probes For Gemini

János Kramár, Joshua Engels et al.Jan 16arXiv

The paper shows how to build tiny, fast safety checkers (called probes) that look inside a big AI’s brain activity to spot dangerous cyber-attack requests.

#activation probes#misuse mitigation#long-context robustness

Why LLMs Aren't Scientists Yet: Lessons from Four Autonomous Research Attempts

Intermediate

Dhruv Trehan, Paras ChopraJan 6arXiv

The authors built a simple six-agent system to see if today’s AI models could plan, run, and write a research paper mostly on their own.

#autonomous research pipeline#implementation drift#training data bias