coco | Xangle

@dambyworld 심지어 에이전트 구현 찾아볼 때 codex app server같은 걸 오픈 소스로 풀어놓는 걸 보고 헉 하기도 했었다지요 ☺️

@xangle_coco 서빙 안정성, 리커버리 속도 같은 것도 상대적으로 견고하지만 문제나 장애, 오류에 대한 투명성과 피드백 수렴, 다양한 연동 기능과 UI/UX/DX 가 모두 우수해욤☺️

결국 이렇게 수렴한것 같다 👀 codex > claude > kimi 아직 grok build 사용전

@dambyworld 좋네요,, 4월까지만 해도 클로드 스테이터스 페이지를 켜본 게 한두번이 아니지 말이에요 🫪 코덱스로는 토큰 리밋도 아쉬운 적이 없었는데,,

@xangle_coco 모델 성능이 비슷하다면 관건은 서빙의 경쟁력에 있는데 오아이가 눈부신 행보를 보이고 있어영🥹 회사에서도 claude max 걷어내고 codex pro 로 이관한 상태네영

@dambyworld 요즘와서는 모델은 대개 비슷한 것 같지만 클라이언트나 에이전트 소프트웨어로서는 너무 만족스러운 거 있죠 ☺️ 회사에서 클로드 안 썼으면 Superset도 안 쓰고 코덱스만 썼을 텐데!

@xangle_coco 슈퍼그록+그록빌드도 궁금킨하지만 현존 월드 1등 코덱스 정도로 끌릴순 없졍🙂‍↔️

You can now use X Premium subscriptions in Hermes Agent, and Hermes Agent can now search X posts. x.ai/news/grok-herm…

@dambyworld 요즘 월 $300인 슈퍼그록 헤비 60% 할인한다고 하는데 그럴거면 ChatGPT Pro 하나 더 라는 생각밖에는 🤔

@xangle_coco 저는 프리미엄+ 라면 슈퍼그록 쓰니까 다 쓰는줄 알았어요. 그런데 슈퍼그록에도 등급이 또 있었다는 ㅋㅋ

HERMES 🔥: X Premium+ accounts can now use their subscription with Grok in Hermes Agent! Besides that, they can also use X search tool, which puts Hermes into a quite unique position now. It is not just OpenClaw vs Hermes anymore. It is OpenAI vs xAI once again 👀

@dambyworld 생일 축하드려요 !!

누추한 여자의 생일을 축하해주는 트위터 고마워

SpaceXAI and @cursor_ai are now working closely together to create the world’s best coding and knowledge work AI. The combination of Cursor’s leading product and distribution to expert software engineers with SpaceX’s million H100 equivalent Colossus training supercomputer will allow us to build the world’s most useful models. Cursor has also given SpaceX the right to acquire Cursor later this year for $60 billion or pay $10 billion for our work together.

@hyewoooons @aultblockchain @Xangle_official 맞나요 쓴거 사람이?

AULT 블록체인은 나스닥 상장사 Hyperscale Data의 자회사 Ault Capital Group이 개발하는 금융 시장에 특화된 네트워크입니다. RWA 토큰화의 패러다임에서 가장 주목 받고 두각을 나타낼 수 있는 블록체인이라는 생각 @aultblockchain @Xangle_official

🚀 Xangle data is now LIVE on NAVER. Price data, project updates, and Asset Profile content from Xangle are now delivered to NAVER Stock via API — bringing institutional-grade digital asset information to one of Korea's largest retail finance platforms. 🚀 쟁글의 데이터가 이제 네이버에서 제공됩니다. 쟁글이 제공하는 가격 정보, 프로젝트의 주요 소식, 종목 개요 콘텐츠가 API를 통해 네이버 증권에서 제공됩니다. 이제 더 많은 투자자들이 네이버 증권에서 기관 수준의 디지털 자산 정보를 확인할 수 있습니다. 🔗 m.stock.naver.com/crypto

@alvinsng Thank you very much :D

@xangle_coco Yes! But also can't stop anyone from doing that!

🤯BREAKING: Alibaba just proved that AI Coding isn't taking your job, it's just writing the legacy code that will keep you employed fixing it for the next decade. 🤣 Passing a coding test once is easy. Maintaining that code for 8 months without it exploding? Apparently, it’s nearly impossible for AI. Alibaba tested 18 AI agents on 100 real codebases over 233-day cycles. They didn't just look for "quick fixes"—they looked for long-term survival. The results were a bloodbath: 75% of models broke previously working code during maintenance. Only Claude Opus 4.5/4.6 maintained a >50% zero-regression rate. Every other model accumulated technical debt that compounded until the codebase collapsed. We’ve been using "snapshot" benchmarks like HumanEval that only ask "Does it work right now?" The new SWE-CI benchmark asks: "Does it still work after 8 months of evolution?" Most AI agents are "Quick-Fix Artists." They write brittle code that passes tests today but becomes a maintenance nightmare tomorrow. They aren't building software; they're building a house of cards. The narrative just got honest: Most models can write code. Almost none can maintain it.

🚨 This Python tool just made vector databases optional for RAG. It's called PageIndex. It reads documents the way you do. No embeddings. No chunking. No vector database needed. Here's the problem with normal RAG: It takes your document, cuts it into tiny pieces, turns those pieces into numbers, and searches for the closest match. But closest match doesn't mean best answer. PageIndex works completely different. → It reads your full document → Builds a tree structure like a table of contents → When you ask a question, the AI walks through that tree → It thinks step by step until it finds the exact right section Same way you'd find an answer in a textbook. You don't read every page. You check the chapters, pick the right one, and go straight to the answer. That's exactly what PageIndex teaches AI to do. Here's the wildest part: It scored 98.7% accuracy on FinanceBench. That's a test where AI answers real questions from SEC filings and earnings reports. Most traditional RAG systems can't touch that number. Works with PDFs, markdown, and even raw page images without OCR. 100% Open Source. MIT License.

Big news: You can now add unlimited team members and create multiple organizations on the free plan. 🚀 This helps you isolate your projects, collaborate with ease, and never worry about "per-seat" pricing. Check out what’s new in the console! 👇

나이 들수록 깨닫는 게 하나 있어요. 
운이란 결국 노출(exposure)의 문제라는 거예요. 같은 의자에 앉아서, 같은 루틴 반복하고, 같은 사람들하고만 이야기하면
새로운 일은 절대 안 생겨요. 세상을 직접 건드려야 이긴다는 거죠. •낯선 사람과 이야기하기 •새로운 커피숍 가보기 •소셜 미디어에 포스팅 해보기 •사이드 허슬 시작하기 세상은 움직이는 사람에게 보상을 줍니다. 기회는 가만히 앉아서 찾는 게 아니라, 
부딪히면서 마주치는 거예요.

Spotlight on Hanwha Investment & Securities, Title Sponsor of CIS 2026! 🇰🇷 Hanwha Investment & Securities is among the fastest-moving traditional financial institutions transforming into a digital asset–focused securities firm, building on the trust and expertise it has established in traditional finance. Through strategic partnerships with leading players across the digital asset ecosystem, including @Xangle_official, the firm is strengthening its on-chain financial capabilities. With its Abu Dhabi entity in the UAE serving as a strategic hub, HISC is advancing toward its vision of becoming a global No.1 RWA Hub and shaping the future of finance. 📅 April 17–19, 2026 📍Plaza Hotel | S-Factory, Seoul 🔗 Get your ticket: wallet.moove.live/event/cis2026

Today, we're releasing shadcn/cli v4. It packs a ton of features: shadcn/skills, presets, dry-run, monorepo and more. If you're using shadcn/ui with coding agents or need better control over the defaults, this is for you. Here's everything new: