최신 글

PyTorch 프로파일링 (1부): torch.profiler 초보자 가이드

Profiling in PyTorch (Part 1): A Beginner's Guide to torch.profiler

신뢰할 수 있는 제3자 평가를 위한 공유 플레이북

A shared playbook for trustworthy third party evaluations | OpenAI

OpenAI shares guidance on third-party AI evaluations, covering how to assess model capabilities, safeguards, and validity for frontier systems.

Claude Opus 4.8: "a modest but tangible improvement"

<p>Anthropic shipped <a href="https://www.anthropic.com/news/claude-opus-4-8">Claude Opus 4.8</a> today. My favourite thing about it is this note in the release announcement:</p> <…

LangSmith Engine 소개

Introducing Langsmith Engine

LangSmith Engine watches your production traces, clusters failures into named issues, and proposes targeted fixes and eval coverage. Stop manually triaging agent failures.

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…

LangSmith 엔진 구축 방법: 에이전트 개선을 위한 우리의 에이전트

https://www.langchain.com/blog/how-we-built-langsmith-engine-our-agent-for-improving-agents

쿠버네티스 기반 자체 호스팅 LangSmith를 위한 미션 컨트롤

Mission Control for Self-Hosted LangSmith on Kubernetes

How Mission Control helps teams operate self-hosted LangSmith on Kubernetes with in-cluster config, preflight checks, health views, releases, and diagnostics.

Add OpenSquilla: token-efficient microkernel agent harness with on-de… · ai-boost/awesome-harness-engineering@7a8cf3d · GitHub

<pre style="white-space: pre-wrap; width: 81ex;">Add OpenSquilla: token-efficient microkernel agent harness with on-device model routing OpenSquilla (May 2026) demonstrates harnes…

비동기 에이전트의 시대 — Cognition의 Walden Yan & OpenInspect의 Cole Murray

The Age of Async Agents — Cognition's Walden Yan & OpenInspect's Cole Murray

80% Devin Commits, Spec-to-PR Workflows, Full VMs, Agent Memory, and PMs Shipping Code

The Model Isn't the Agent Anymore - by AlphaSignal AI

A UC Berkeley paper argues that long-horizon agent performance now turns on six system components around the model, not just the model itself.

Google I/O 2026 주요 발표 및 업데이트 키노트 12개 영상 시청하기

Watch 12 Google I/O 2026 keynote videos of the top announcements and updates

The colorful I/O logo against a black background, surrounded by stills from the I/O keynote

2026년 4월: LangChain 뉴스레터

April 2026: LangChain Newsletter

April means we're officially counting down to Interrupt. We’ve got two more meetups on the agent improvement loop before April officially closes out in New York and San Francisco. …

프로덕션 에이전트 실패 수정: Interrupt 2026 회고 | LangChain 뉴스레터

Fixing agent failures in production: Interrupt 2026 recap | LangChain Newsletter

Recapping two days of Interrupt 2026 — LangSmith Engine, Sandboxes GA, LangChain Labs, and 23 talks from teams at LinkedIn, Rippling, Cisco, and more. Now on demand.

Endava가 Codex로 에이전틱 조직을 구축하는 방법

How Endava builds an agentic organization with Codex | OpenAI

Learn how Endava uses Codex to build an agentic organization, accelerating software delivery and reducing requirements analysis from weeks to hours.

[AINews] Cognition이 $26B 시리즈 D 펀딩라운드에서 $1B 조달

[AINews] Cognition raises $1B in $26B Series D

coding is an uncapped TAM market

MUFG, OpenAI와 함께 AI 네이티브 조직으로 전환 목표

MUFG aims to become AI-native with OpenAI | OpenAI

MUFG uses ChatGPT Enterprise to build an AI-native organization, improve workflows, and deliver new AI-powered financial services at scale.

OpenAI의 최첨단 거버넌스 프레임워크

OpenAI’s Frontier Governance Framework | OpenAI

Explore OpenAI’s Frontier Governance Framework and how our AI safety, security, and risk practices align with emerging EU and California regulations.

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&#8217;s Protein World Model: ESMC-6B, ESMFold2, 6.8B proteins, 1.1B structures, antibody design, SAEs, & the potential for programmable biology

I think Anthropic and OpenAI have found product-market fit

<p>Anthropic are <a href="https://techcrunch.com/2026/05/20/anthropic-says-its-about-to-have-its-first-profitable-quarter/">strongly rumored</a> to be about to have their first pro…

Perplexity's Bumblebee: a read-only supply-chain check for the developer laptop

A read-only inventory check for the developer laptop supply chain

Codex를 활용한 자체 개선 세금 에이전트 구축

Building self-improving tax agents with Codex | OpenAI

See how OpenAI, Thrive, and Crete built a self-improving tax agent with Codex, automating filings, improving accuracy, and accelerating workflows.

[AINews] 새로운 AI 인프라 데카콘들: Fireworks, Baseten (OpenRouter도 곧 나온다)

[AINews] New AI Infra decacorns: Fireworks, Baseten (with OpenRouter on the way)

it's funding news, but it's good news.

허브 버킷을 이용한 1조 파라미터 배포: TRL의 델타 가중치 동기화

Shipping a Trillion Parameters With a Hub Bucket: Delta Weight Sync in TRL

Reachy Mini 완전한 로컬 실행

Reachy Mini goes fully local

2026년 선거 정보 및 보안조치

Election information and safeguards in 2026 | OpenAI

Ahead of global elections, we’re helping people access information, supporting cyber defenders, and increasing AI transparency

Warp의 GPT-5.5 기반 오픈소스 구축 전략

Warp’s big bet on building open source with GPT-5.5 | OpenAI

Warp uses GPT-5.5 and OpenAI models to coordinate coding agents across local, cloud, and open-source development workflows.

The Third Way to Adapt a Frontier Agent - by AlphaSignal AI

Microsoft just trained an agent&#8217;s skill file like neural-network weights, with bounded edits, a held-out gate, and 52-of-52 wins across 6 benchmarks and 3 harnesses.

Add agent-device: MCP-native control layer for iOS and Android devices · ai-boost/awesome-harness-engineering@7b2a265 · GitHub

<pre style="white-space: pre-wrap; width: 81ex;">Add agent-device: MCP-native control layer for iOS and Android devices Fills a critical gap in the mobile-agent harness stack. Mos…

Import AI 458: 미래와의 대면; 그리고 특이점 이야기

Import AI 458: Reckoning with the future; and a singularity story

What AI-driven miracles will happen this year?