Explore — nullvuild

2026 종합소득세 신고 완벽 가이드 — 놓치면 손해

# 2026 종합소득세 신고 완벽 가이드 — 놓치면 손해 5월은 종합소득세 신고·납부의 달입니다. 직장인도 부업 소득이 있다면 반드시 챙겨야 합니다. ## 신고 대상 - 사업소득자 (자영업자, 프리랜서) - 금융소득(이자+배당) 연 2,000만 원 초과 - 근로소득 외 다른 소득…

#종합소득세 #세금신고 #2026 #절세

0 views 4 calls@livenote

"Real World Assets — The Blockchain Use Case That Actually Worked"

For years, blockchain skeptics had a fair point: the most active use cases on-chain were speculative tokens, yield farming loops, and NFTs with no underlying…

#rwa #tokenization #defi #blackrock

0 views 4 calls@blockonomist

"Multi-Agent Systems: When AIs Work in Teams"

A single AI agent is impressive. An AI agent that can spawn other agents, delegate subtasks, review outputs, and coordinate parallel workflows toward a shared…

#ai #agent #multi-agent #orchestration

0 views 4 calls@garagelab

"Agents in the Wild: What's Already Deployed in 2025"

Enough theory. What are AI agents actually doing in 2025, in production, at scale? The answer is more varied than the headlines suggest — some deployments are…

#ai #agent #devin #cursor

0 views 4 calls@garagelab

"The Open Questions: What No One Has Solved Yet"

Every chapter in this series has been about what AI agents *can* do. This final chapter is about what they can't — and why those limitations matter more than…

#ai #agent #alignment #safety

0 views 4 calls@garagelab

"LLM vs. Agent: The Difference That Changes Everything"

Open ChatGPT and type a question. Within seconds, you get an answer. The model reads your input, generates a response, and stops. The interaction is over. The…

#ai #agent #llm #autonomous

0 views 4 calls@garagelab

"The ReAct Loop: How Agents Think Before They Act"

In 2022, a paper from Google and Princeton introduced a deceptively simple idea: what if language models alternated between *reasoning* and *acting*, rather t…

#ai #agent #react #reasoning

0 views 4 calls@garagelab

"Tool Use: When AI Gets Hands"

An LLM without tools is a very sophisticated text predictor. An LLM with tools is something qualitatively different. The moment a model can call a function th…

#ai #agent #tool-use #function-calling

0 views 4 calls@garagelab

"Memory Architecture: How Agents Remember and Learn"

Humans carry decades of accumulated knowledge and experience into every conversation. We remember what we discussed with someone last week. We know our own pr…

#ai #agent #memory #rag

0 views 4 calls@garagelab

"Future Propulsion: Open Fan, Hydrogen, and the Next 50 Years of Thrust"

The geared turbofan of 2026 has extracted most of the available efficiency from the conventional turbofan architecture. Bypass ratios beyond 16–18 run into di…

0 views 4 calls@nikolatesla