DEVOCEAN @sk_devocean

개발자 커뮤니티 | SK 기술블로그 | 내외부 개발자 소통 채널 | DR(Developer Relations) 채널 devocean.sk.com Joined May 2021

Tweets

780
Followers

310
Following

242
Likes

192

감자 @nowlovepan

4 months ago

AI로 일 줄이고 싶은 직장인은 이 영상 보면 좋을 듯함 Claude 공식 올라온 영상입니다 (한국어 번역) 발표자는 Omni CTO Chris Merrick입니다 영상 핵심만 요약해서 17분으로 만들어 봤습니다 Omni는 AI 데이터 분석 플랫폼이고 이번 영상에서는 Claude를 실제 제품과 개발팀에 어떻게 붙였는지 보여줌 이 영상은 개발자만 볼 영상이 아님 AI로 회사 일을 줄이고 싶은 사람 엑셀이나 대시보드 자주 보는 사람 보고서 만들 때마다 데이터 확인하는 사람 AI로 자동화 만들고 싶은 사람 팀 업무를 AI로 바꿔보고 싶은 사람 이런 사람한테 더 추천하고 싶음

5 56 192 10K 251

View Details

Andrej Karpathy @karpathy

5 months ago

Fireside chat at Sequoia Ascent 2026 from a ~week ago. Some highlights: The first theme I tried to push on is that LLMs are about a lot more than just speeding up what existed before (e.g. coding). Three examples of new horizons: 1. menugen: an app that can be fully engulfed by LLMs, with no classical code needed: input an image, output an image and an LLM can natively do the thing. 2. install .md skills instead of install .sh scripts. Why create a complex Software 1.0 bash script for e.g. installing a piece of software if you can write the installation out in words and say "just show this to your LLM". The LLM is an advanced interpreter of English and can intelligently target installation to your setup, debug everything inline, etc. 3. LLM knowledge bases as an example of something that was *impossible* with classical code because it's computation over unstructured data (knowledge) from arbitrary sources and in arbitrary formats, including simply text articles etc. I pushed on these because in every new paradigm change, the obvious things are always in the realm of speeding up or somehow improving what existed, but here we have examples of functionality that either suddenly perhaps shouldn't even exist (1,2), or was fundamentally not possible before (3). The second (ongoing) theme is trying to explain the pattern of jaggedness in LLMs. How it can be true that a single artifact will simultaneously 1) coherently refactor a 100,000-line code base *and* 2) tell you to walk to the car wash to wash your car. I previously wrote about the source of this as having to do with verifiability of a domain, here I expand on this as having to also do with economics because revenue/TAM dictates what the frontier labs choose to package into training data distributions during RL. You're either in the data distribution (on the rails of the RL circuits) and flying or you're off-roading in the jungle with a machete, in relative terms. Still not 100% satisfied with this, but it's an ongoing struggle to build an accurate model of LLM capabilities if you wish to practically take advantage of their power while avoiding their pitfalls, which brings me to... Last theme is the agent-native economy. The decomposition of products and services into sensors, actuators and logic (split up across all of 1.0/2.0/3.0 computing paradigms), how we can make information maximally legible to LLMs, some words on the quickly emerging agentic engineering and its skill set, related hiring practices, etc., possibly even hints/dreams of fully neural computing handling the vast majority of computation with some help from (classical) CPU coprocessors.

Stephanie Zhan @stephzhan

5 months ago

@karpathy and I are back! At @sequoia AI Ascent 2026. And a lot has changed. Last year, he coined “vibe coding”. This year, he’s never felt more behind as a programmer. The big shift: vibe coding raised the floor. Agentic engineering raises the ceiling. We talk about what it

73 204 2K 1.6M 3K

376 808 6K 1.3M 6K

View Details

lucas @lucas_flatwhite

5 months ago

Claude Code와 함께한 웹 성능 개선 이야기 devocean.sk.com/blog/techBoard… 팀에 Claude Team Plan이 도입됐을 때, SK에서 고민한 내용이예요. 어느 기업이나 레거시는 있죠. 대상은 Java 클래스 380개, MyBatis Mapper XML 49개가 얽힌 10년 넘은 레거시 시스템.. Claude Code의 멀티 에이전트 4개를 병렬로 돌렸더니, 5분 만에 SQL Injection 취약점 14곳, DB를 46회 호출하는 N+1 문제 등의 다양한 내용이 담긴 보고서가 나왔다고 하네요. 속도와 범위에 대한 얘기를 참고해보셔도 좋으실 듯..

0 8 38 4K 42

View Details

Nav Toor @heynavtoor

5 months ago

If I had to land a $200K AI engineer job in 90 days, I would not get a degree. I would master these 10 GitHub repos. 1. awesome-llm-apps The production AI playbook. RAG, agents, multimodal apps, all in working code. 106K+ stars. Repo → github.com/Shubhamsaboo/a… 2. LangChain The foundational framework. Used in production by Klarna, Replit, Elastic, and most AI startups in 2026. Repo → github.com/langchain-ai/l… 3. LangGraph The orchestration layer powering production agents. The skill on every senior AI engineer job description. Repo → github.com/langchain-ai/l… 4. CrewAI Multi-agent coordination. The framework most Fortune 500 teams reach for first. Repo → github.com/crewAIInc/crew… 5. Ollama Run any open-source LLM on your own machine. The fastest way to learn how models actually work. Repo → github.com/ollama/ollama 6. awesome-mcp-servers MCP is the standard every major AI lab adopted in 2026. Knowing it puts you ahead of 99% of engineers. Repo → github.com/punkpeye/aweso… 7. Qdrant The vector database used for production RAG at scale. Embeddings and semantic search are non-negotiable for AI roles. Repo → github.com/qdrant/qdrant 8. AI-Agents-for-Beginners Microsoft's free 12-lesson course on building agents. Real code, real exercises, real prep. Repo → github.com/microsoft/ai-a… 9. system-design-primer Production AI is system design. The repo FAANG engineers use to prep for interviews. Repo → github.com/donnemartin/sy… 10. awesome-claude-code The playbook for the tool now used inside FAANG, OpenAI, Anthropic, and most YC startups. Repo → github.com/hesreallyhim/a… Here's the wildest part: A $200K AI engineer in 2026 isn't paid for a degree. They are paid for what these 10 repos teach. The market doesn't care where you learned it. It only cares if you can ship. 90 days. 10 repos. One portfolio that proves you can do the work. That's it. That's the whole game. Save this before you forget. 100% free. 100% open source.

75 495 3K 200K 6K

View Details

DEVOCEAN @sk_devocean

6 months ago

@unnnyong 오! 가십니까? ㅎㅎㅎ

1 0 0 44 0

View Details

화접 @0happyjin00

12 months ago

젠슨 황의 루틴 1. 새벽 5시에 기상. 하루 중 가장 중요한 일을 출근 전에 처리 (Priority first morning). 2. 매일 독서. 아무리 바빠도 매일 책, 연구 논문, 업계 리포트를 읽음. 창업 후 지금까지 단 하루도 빼먹지 않았다고 3. 경계가 없는 업무와 삶. 깨는 순간부터 잠들기 직전까지 일함. 물론 주말도 없음 4. 일요일 밤에는 스카치를 마시며 직원들이 보낸 메일 및 보고서를 읽음. 진정한 work & life alignment "위대함은 지능에서 나오지 않습니다. 위대함은 인격/character에서 나옵니다" 젠슨황은 "근면함"이 "똑똑함"보다 훨씬(× 100) 더 중요한 자질이라고 말한다 "당신이 얼마나 똑똑한지는 사실 중요하지 않습니 다. 왜냐하면 당신보다 더 똑똑한 사람은 항상 있기 때문이죠. 당신의 진짜 경쟁자들은 잠들지 않고 일하는 사람들입니다"