写作
评测
筛选文章 评测
评测
第 3 页 · 5 / 29 按发布时间浏览
完整归档 →
-
Agentic search missed an incident. Test the eval too The Anthropic incident review shows why automated monitors and LLM graders need coverage, independence, and tests for their own failure modes.
-
AI agent engineering reading list | 2026-09-04 to 09-10 AI agent engineering readings for September 4 to 10, 2026, with key findings, engineering implications, suggested sections, and primary sources.
-
OpenAI agent workdays and shifting builder bottlenecks OpenAI organization-level data suggests that more coding-agent use shifts bottlenecks to task decomposition, concurrency, harnesses, evaluation, and selection.
-
AI Engineering Harness: verifiable delivery for AI code A multi-agent engineering workflow uses isolated worktrees, CI, cold-start review, evidence gates, and layered context to control delivery of AI-generated code.
-
Loop Engineering Harness: controlling agent iterations Break down planning, execution, evaluation, state management, and stopping rules to keep multi-step agent tasks controlled and traceable.