labs
Context Engineering | Compaction & Agent Memory for Automated Malware Analysis
Compaction cut input tokens 86% across long-running agent evals with no quality loss. Context discipline matters as much as model selection.
Read More
Gabriel Bernadett-Shapiro
Gabriel is a Distinguished AI Research Scientist at SentinelOne, specializing in incorporating large language model (LLM) capabilities for security applications. He also serves as an Adjunct Lecturer at the Johns Hopkins SAIS Alperovitch Institute, teaching the graduate workshop "Building with Artificial Intelligence." Before joining SentinelOne, Gabriel helped launch OpenAI’s inaugural cyber capability-evaluation initiative, where he translated red-team research insights into the GPT-4 model card and established the Cyber Grant Program to foster collaboration between AI-safety researchers and the broader information security community. Prior to this, he served as a senior analyst within Apple Information Security’s Threat Intelligence team. Gabriel holds an M.A. in Public Diplomacy from the University of Southern California and a B.A. in International Relations from Occidental College.