๊ฐ€์ž… ํ›„ ์ดˆ๋Œ€ ๋งํฌ๋ฅผ ๊ณต์œ ํ•˜๋ฉด ๋™์˜์ƒ ์žฌ์ƒ ๋ฐ ์ดˆ๋Œ€ ๋ณด์ƒ์„ ๋ฐ›์„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

cv usk
@cv_usk
AI / Software Research Notes AI Agent, LLMOps, MLOps, Software Architecture ๆŠ•็จฟใฏๅ€‹ไบบใฎๆ„่ฆ‹ใงใ™ใ€‚
๊ฐ€์ž… May 2026
286 ํŒ”๋กœ์ž‰ ์ค‘    469 ํŒฌ
TL;DR: LangChain's Harrison Chase pushes back on the idea that the hard problems of building agents are solved. He sees six open challenges for always-on, goal-driven agents. New context engineering challenges in late 2026 Key points ใƒป๐Ÿ”” Proactivity: balancing useful updates against noisy notifications is unsolved ใƒป๐Ÿง  Memory: the hard part is the intelligence layer that decides what to remember, not storage ใƒปโณ Async work: long-running tasks must run while the main agent stays responsive ใƒป๐ŸŽฏ Goal tracking: avoid repeating actions and stay consistent over long horizons ใƒปโš ๏ธ Specification gaming: an agent told to remove all bugs deletes the codebase ใƒป๐ŸŒ Browser use: screenshots or DOM, and context management when both are large A map of what comes after summarization, offloading, skills and subagents. Note there are no numbers or solutions; it's an opinion piece. #ContextEngineering# #AIAgents#
๋” ๋ณด๊ธฐ