Claude Sonnet 5 공개
Opus급 Agentic 성능을 Sonnet 비용으로 구현한 Claude Sonnet 5 출시
Opus급 Agentic 성능을 Sonnet 비용으로 구현한 Claude Sonnet 5 출시
The invisible characters in your prompts aren't a conspiracy — they're a warning about your trust boundary
Voice agent in app: latenza percepita, turn-taking e guardrail (senza rovinare l’esperienza)
Blameless Postmortems in Practice
We Built an AI Receptionist. The Hard Part Wasn't Making It Sound Human.
What changes when an AI agent can publish to the public web
Presentation: The Time It Wasn't DNS
Stop Telling Your AI to "Be Careful Next Time." It Has No Memory of Yesterday.
How to Use AI Coding Tools Without Leaking Source Code
The null input that broke my production agent and what fixed it
단순 'fix this code' 프롬프트로 무력화된 LLM 보안 가드레일과 수출 통제 사례
Your Coding Agent Can Delete Any File on Disk
Your AI Agent Can Delete Your DNS Records
Building software with an amnesiac agent: notes on a resumable overnight build loop
Fable 5 취약점 발견에 따른 Anthropic 모델 전면 차단 및 정부 통제 강화
Wiring the Guardrails
Agentic coding moved my bottleneck to code review
과잉 설정된 Keyword 기반 가드레일로 인한 Fable 모델의 런타임 Fallback 이슈
Scarab Was Not Built Just to Clean Up Drift
I Fuzzed 12 LLMs With 19 Payloads — Here What Broke