-
-
Deep Agents v0.6의 새로운 기능
New in Deep Agents v0.6
Deep Agents 0.6 ships a code interpreter, harness profiles, streaming v3, delta channels, and ContextHub, making agents faster, cheaper, and more scalable.
-
델타 채널: 장시간 실행 에이전트를 위한 런타임 진화
Delta Channels: How We’re Evolving our Runtime for Long-Running Agents
Long-running agents have a storage problem: checkpointing full state at every step grows at O(N²). DeltaChannel is a new primitive in LangGraph 1.2 that checkpoints only the diff e…
-
.png)
법률 에이전트를 위한 효율적인 검증기 설계
Designing Efficient Verifiers for Legal Agents
A Harvey and LangChain Labs study on making LLM verifiers cheaper and more reliable for legal-agent evaluation and post-training.
-
루브릭 소개: 자신의 작업을 평가하고 수정하는 에이전트 구축
Introducing Rubrics: Build Agents that Evaluate and Correct Their Work
Deep Agents' RubricMiddleware adds a self-evaluation loop to your agent runs. Set a rubric, configure a grader, and get reliable outputs on tasks where correctness matters.
-
.png)
-
[AINews] Anthropic이 Series H에서 9650억 달러 모금, Opus 4.8 및 Dynamic Workflows/ultracode 출시
[AINews] Anthropic raises $965B Series H, releases Opus 4.8 and Dynamic Workflows/ultracode
Total Anthropic victory!
-
LangSmith 샌드박스가 정식 출시되었습니다
LangSmith Sandboxes are Generally Available
Run AI agents safely with LangSmith Sandboxes (GA): kernel-isolated microVMs with snapshots, parallel forks, service URLs, and auth proxies. Built for coding agents, CI agents, and…
-
Lyft가 LangGraph와 LangSmith로 구축한 자체 서빙 AI 에이전트 플랫폼
How Lyft Built a Self-Serve AI Agent Platform with LangGraph and LangSmith
Lyft used LangGraph and LangSmith to build a self-serve AI agent platform for customer support, cutting agent development from months to weeks.
-
🔬 ESMFold2: 단백질에 대한 쓴 교훈이 온다 - 알렉스 라이브스, 바이오허브
🔬 ESMFold2: The Bitter Lesson is Coming for Proteins - Alex Rives, BioHub
Biohub’s Protein World Model: ESMC-6B, ESMFold2, 6.8B proteins, 1.1B structures, antibody design, SAEs, & the potential for programmable biology
-
Datasette 에이전트
Datasette Agent
<p>We just <a href="https://datasette.io/blog/2026/datasette-agent/">announced the first release of Datasette Agent</a>, a new extensible AI assistant for Datasette. I've been work…
-
레일웨이: 에이전트-네이티브 클라우드 — 제이크 쿠퍼
Railway: The Agent-Native Cloud — Jake Cooper
3M Users, 100K Signups/Week, Own-Metal Data Centers, $200K+ Coding Agent Spend, and the Death of PRs
-
딥 에이전트의 인터프리터: 도구 호출과 샌드박스 사이의 코드
Interpreters in Deep Agents: Code Between Tool Calls and Sandboxes
Deep Agents now supports interpreters: small embedded runtimes where agents write code to coordinate tools, hold working state, and decide what enters model context.
-
Gemini 3.5 Flash: 더 비싸지만 구글이 모든 곳에 사용할 계획
Gemini 3.5 Flash: more expensive, but Google plan to use it for everything
<p>Today at Google I/O, Google <a href="https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-5/">released Gemini 3.5 Flash</a>. This one skipped the <co…
-
다양한 모델에 맞춰 딥 에이전트 조정하기
Tuning Deep Agents to Work Well with Different Models
Deep Agents was previously designed in a generic way to work well across model families. Today we’re adding model-specific profiles to adjust prompts, tools, and middleware. We shi…
-
Interrupt에서 공개한 모든 제품들
Everything we shipped at Interrupt
From autonomous debugging to one-line deploys, here's every product LangChain launched at Interrupt 2026 to help teams build, test, and ship agents in production.
-
지난 6개월 LLM의 모든 것을 5분으로
The last six months in LLMs in five minutes
<p>I put together these annotated slides from my five minute lightning talk at PyCon US 2026, using the <a href="https://tools.simonwillison.net/annotated-presentations">latest ite…
-
FOD#152: AI Agent Skills: Why Skill Curation Is the Next Bottleneck
This Week in Turing Post:
-
.png)
딥 에이전트, LangSmith, 병렬 처리를 사용한 회사 실사 에이전트 구축
https://www.langchain.com/blog/building-a-company-due-diligence-agent-with-deep-agents-langsmith-and-parallel
-
Open SWE: 내부 코딩 에이전트를 위한 오픈소스 프레임워크
Open SWE: An Open-Source Framework for Internal Coding Agents
Built on Deep Agents and LangGraph, Open SWE provides the core architectural components for internal coding agents.
-
오픈 모델이 임계점을 돌파했다
Open Models have crossed a threshold
Open models like GLM-5 and MiniMax M2.7 now match closed frontier models on core agent tasks — file operations, tool use, and instruction following — at a fraction of the cost and …
-
LLM 0.32a0 주요 하위 호환성 유지 리팩토링
LLM 0.32a0 is a major backwards-compatible refactor
<p>I just released <a href="https://llm.datasette.io/en/latest/changelog.html#a0-2026-04-28">LLM 0.32a0</a>, an alpha release of my <a href="https://llm.datasette.io/">LLM</a> Pyth…
-
이제 폐지된 OpenAI-마이크로소프트 AGI 조항의 역사 추적
Tracking the history of the now-deceased OpenAI Microsoft AGI clause
<p>For many years, Microsoft and OpenAI's relationship has included a weird clause saying that, should AGI be achieved, Microsoft's commercial IP rights to OpenAI's technology woul…
-
딥씨크 V4 - 거의 최고 수준의 성능, 저렴한 가격
DeepSeek V4 - almost on the frontier, a fraction of the price
<p>Chinese AI lab DeepSeek's last model release was V3.2 (and V3.2 Speciale) <a href="https://simonwillison.net/2025/Dec/1/deepseek-v32/">last December</a>. They just dropped the f…
-
웹 브라우저에서 LiteParse로 PDF 텍스트 추출하기
Extract PDF text in your browser with LiteParse for the web
<p>LlamaIndex have a most excellent open source project called <a href="https://github.com/run-llama/liteparse">LiteParse</a>, which provides a Node.js CLI tool for extracting text…
-
Import AI 453: AI 에이전트 붕괴, 미러코드 그리고 점진적 무력화에 대한 열 가지 관점
Import AI 453: Breaking AI agents; MirrorCode; and ten views on gradual disempowerment
Was fire equivalent to a singularity for people at the time?
-
ImportAI 449: LLM이 다른 LLM을 학습시킴; 72B 분산 학습 실행; 컴퓨터 비전은 생성 텍스트보다 더 어렵다
ImportAI 449: LLMs training other LLMs; 72B distributed training run; computer vision is harder than generative text
Will AI cause a political interregnum