최신 글

Google I/O 2026에서 발표한 100가지

100 things we announced at Google I/O 2026

Image with the words "Ready, Set, I/O" and a colorful Gemini logo

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.

How OpenHuman Works, And How to Set It Up in 5 Minutes

The open-source desktop agent that crossed +20k GitHub stars in days, what’s inside, and the full walkthrough.

새로운 실험이 Google Beam의 그룹 회의를 개선

A new experiment brings better group meetings to Google Beam

A small group meeting featuring two in-room participants and three participants on-screen.

RAG and Long Context Aren't Enough for Agent Memory. δ-mem Is a Third Option

An 8×8 online state lifted Qwen3-4B from 46.79% to 51.66%, with the backbone untouched.

Add TencentDB-Agent-Memory: fully local hierarchical memory with symb… · ai-boost/awesome-harness-engineering@b9889a7 · GitHub

<pre style="white-space: pre-wrap; width: 81ex;">Add TencentDB-Agent-Memory: fully local hierarchical memory with symbolic short-term compression Tencent's April 2026 release demo…

[AINews] Google I/O 2026: Gemini 3.5 Flash, Omni (비디오용 NanoBanana), Spark (백그라운드 에이전트), Antigravity 2.0

[AINews] Google I/O 2026: Gemini 3.5 Flash, Omni (NanoBanana for Video), Spark (background agents), and Antigravity 2.0

Google has been busy!

OpenAI의 국가 교육 프로젝트 차기 단계

The next phase of OpenAI’s Education for Countries | OpenAI

OpenAI advances Education for Countries, expanding AI adoption in schools with new partnerships, teacher training, and tools to improve global learning outcomes.

OpenAI 모델이 이산 기하학의 중심 추측을 반박했다

An OpenAI model has disproved a central conjecture in discrete geometry | OpenAI

An OpenAI model solved the 80-year-old unit distance problem, disproving a major conjecture in discrete geometry and marking a milestone in AI-driven mathematics.

Ramp 엔지니어들이 Codex로 코드 리뷰를 가속화하는 방법

How Ramp engineers accelerate code review with Codex | OpenAI

How Ramp engineers use Codex with GPT-5.5 to review code and ship improvements, allowing them to get substantive feedback in minutes instead of hours.

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…

싱가포르를 위한 OpenAI

Introducing OpenAI for Singapore | OpenAI

OpenAI for Singapore launches a multi-year AI partnership to expand deployment, build local talent, and support businesses and public services with AI.

OlmoEarth v1.1: 더 효율적인 지구 관측 모델 시리즈

OlmoEarth v1.1: A more efficient family of Earth observation models

구글 I/O 2026: 뉴스 및 발표

Google I/O 2026: News and announcements

<img src="https://storage.googleapis.com/gweb-uniblog-publish-prod/original_images/Collection-Hero.gif" />At Google I/O 2026, we shared how we’re making AI more helpful for everyon…

Google AI 구독의 새로운 모든 것, 2026 I/O에서

Everything new in our Google AI subscriptions, fresh from I/O 2026

The image shows colorful icons. The copy reads: More magic in one plan. More power, more perks, same price.

구글 검색의 I/O 2026 업데이트: AI 에이전트 등

Google Search’s I/O 2026 updates: AI agents and more

Text that reads "The best of a search engine with the best of AI"

Gemini 3.5: 최첨단 지능과 실행 기능

Gemini 3.5: frontier intelligence with action

Gemini 3.5 text and multi-colored star icon on an abstract blue background.

Google I/O 2026: 순다르 피차이의 개막 기조 연설

Google I/O 2026: Sundar Pichai’s opening keynote

a series of colorful icons representing Google I/O against a black background

Google Workspace에서 새로운 방식으로 창작하고 일을 처리하는 방법

New ways to create and get things done in Google Workspace

Google Workspace

AI 모드가 사람들의 검색 방식을 어떻게 변화시키고 확장하고 있는가

How AI Mode is changing and expanding the way people search

A graphic features the text "How people are using AI Mode in the U.S." surrounded by colorful, stylized illustrations of a pencil, planet, banana, gift box, cursor, gamepad, and li…

11 Open-Source Repos Every AI Infra Engineer Should Bookmark

You built an AI agent this weekend. Have you thought about its infrastructure?

[AINews] 프론티어 랩에서 일자리를 얻는 방법 (사전학습 분야)

[AINews] How to land a job at a frontier lab (on Pretraining)

a quiet day before google i/o lets us amplify a notable blogpost

LangChain Labs 소개

Introducing LangChain Labs

LangChain Labs is a new applied research effort focused on continual learning for agents, with partners advancing open research on self-improving AI systems.

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…

Ettin Reranker 패밀리 소개

Introducing the Ettin Reranker Family

Co-Scientist: 세포 노화 연구 가속화 — Google DeepMind

Co-Scientist: Accelerating research on cellular aging — Google DeepMind

Biologists use Co-Scientist to find novel factors that successfully rejuvenate human cells.

Hermes Just Made Codex the Engine and Itself the Shell.

Opt-in beta in Hermes 2026.5. One slash command, three tool sources, four tools left behind.

PaddleOCR 3.5: Transformers 백엔드를 이용한 OCR 및 문서 파싱 작업

PaddleOCR 3.5: Running OCR and Document Parsing Tasks with a Transformers Backend