들어가며: NeurIPS 2025가 제시하는 차세대 AI 안전 가이드 생성형 모델은 점점 더 우리 생활에 깊숙히 들어오고 있습니다. LY Corporation에서도 다양한 AI 서비스를 개발해 제공하고 있는데 이런 서비스에 가드레일(guardrails)이 없으면 다양한 공격을 받고 유해한 답변이 노출되거나, 개인 정보나 기밀 유출과 같은 오작동이 발생할 수 있습니다. 즉, 가드레일은 AI를 실서비스에서 운영 가능하게 만드는 필수 인프라입니다. 저희 조직은 사용자가 보다 안전한 환경에서 AI 서비…
Published on: March 10, 2026 10 min read Automating detection gap analysis with GitLab Duo Agent Platform Learn how GitLab's Signals Engineering team uses our AI platform to automatically surface detection gaps from security incidents — no manual review required. security securi…
Andrew “Boz” Bosworth's 10 rules for navigating the next design paradigm Working Well Design Tips & inspiration Config Thought leadership Profiles & interviews
AWS Weekly Roundup: Amazon Connect Health, Bedrock AgentCore Policy, GameDay Europe, and more (March 9, 2026) Fiti AWS Student Community Kenya! Last week was an incredible whirlwind: a round of meetups, hands-on workshops, and career discussions across Kenya that culminated with…
We’re sharing the technical details behind how Advanced Browsing Protection (ABP) in Messenger protects the privacy of the links clicked on within chats while still warning people about malicious links. We hope that this post has helped to illuminate some of the engineering chal…
Senior Principal Researcher, Microsoft Research
Active defense: introducing a stateful vulnerability scanner for APIs 2026-03-09 John Cosgrove Alex Povel Malte Reddig Security is traditionally a game of defense. You build walls, set up gates, and write rules to block traffic that looks suspicious. For years, Cloudflare has be…
Fixing request smuggling vulnerabilities in Pingora OSS deployments 2026-03-09 Edward Wang Fei Deng Andrew Hauck In December 2025, Cloudflare received reports of HTTP/1.x request smuggling vulnerabilities in the Pingora open source framework when Pingora is used to build an ingr…
Complexity is a choice. SASE migrations shouldn’t take years. 2026-03-09 Warnessa Weaver For years, the cybersecurity industry has accepted a grim reality: migrating to a zero trust architecture is a marathon of misery. CIOs have been conditioned to expect multi-year deployment…
들어가며 지난 엔터프라이즈 LLM 서비스 구축기 1: 컨텍스트 엔지니어링에서는 260개의 도구와 수백 페이지의 문서를 다루는 환경에서 LLM에게 필요한 정보만 골라서 제공하는 '점진적 공개' 전략을 공유해 드렸습니다. 1편이 AI에게 '무엇을 전달할 것인가?'에 대한 답이었다면, 이번 2편은 그 다음 질문으로 넘어갑니다. 정제된 맥락을 전달받는 에이전트를 '어떻게 만들 것인가?'입니다. 본격적인 이야기에 앞서, 먼저 현재 Flava AI 어시스턴트(이하 FAA)의 실전 성적표를 공개합니다. 저희…
Every year at GDC, I find myself thinking about the same challenge: there are more games than ever, and for developers, that means earning a player’s time has never been more competitive. The average Steam player went from playing 13 titles a year in 2021 to 10 in 20241. On Disc…
Protect agentic AI applications with Datadog AI Guard
Published on: March 9, 2026 4 min read Navigate repositories faster with the file tree browser Learn all about this new collapsible feature to increase visibility and simplify navigation, available across GitLab.com, GitLab Self-Managed, and GitLab Dedicated. features product De…
Christoph Hamsen Kylian Serrania Christophe Tafani-Dereeper Cloud Security Researcher and Advocate At Datadog, our commitment to open source means operating transparently and accepting that our repositories will be probed by adversaries. A few months ago, we shared our approach…
