양수열(Soo yeol, Yang)
@javaoracle
Ex Treasure data engineer/Java Champion,Oracle ACE pro /JCO 3th chairman/Doctor of Veterinary Medicine
Bunları beğenebilirsin
ChatGPT의 메모리 시스템을 리버스 엔지니어링한 분의 글을 읽었는데, 벡터 DB + RAG로 하겠지 라고 생각했던게 아니라는걸 알게 됨. 결론부터 말하면, ChatGPT는 거의 RAG를 안 쓴다. 벡터 임베딩도, 유사도 검색도, 리트리벌 비용도 거의 없다. 대신 훨씬 더 단순하고, 훨씬 더 영리한 4단계…
I spent the last few days prompting ChatGPT to understand how its memory system actually works. Spoiler alert: There is no RAG used manthanguptaa.in/posts/chatgpt_…
중국 비즈니스맨한테 들은 충격적인 얘기를 해줄게, "한국을 망하게 하는 건 너무나 쉽다. 마포구나 성동구 같은데 아파트 매매가 2배로 올려서 한 채만 사주면, 다 따라 오르고 중산층 붕괴되고 청년층은 의욕상실로 일 안하고, 직장인들 의욕은 반으로 꺽인다."
you must read Harvard’s AI Research Experience if you’re a student/researcher. A free course book which covers the essentials and tips on doing research: > VSCode, Git, Conda > PyTorch, W&B > AWS, colab > LLMs and VLMs > reading AI papers > research progress and organization
PYTHON is difficult to learn, but not anymore! Introducing "The Ultimate Python ebook "PDF. You will get: • 74+ pages cheatsheet • Save 100+ hours on research And for 48 hrs, it's 100% FREE! To get it, just: 1. Like & RT 2. Reply "Python" 3. Follow @Ronycoder [MUST]
![Ronycoder's tweet image. PYTHON is difficult to learn, but not anymore!
Introducing "The Ultimate Python ebook "PDF.
You will get:
• 74+ pages cheatsheet
• Save 100+ hours on research
And for 48 hrs, it's 100% FREE!
To get it, just:
1. Like & RT
2. Reply "Python"
3. Follow @Ronycoder [MUST]](https://pbs.twimg.com/media/Gr4SVOrWoAApwDf.jpg)
PYTHON is difficult to learn, but not anymore! Introducing "The Ultimate Python ebook "PDF. You will get: • 74+ pages cheatsheet • Save 100+ hours on research And for 48 hrs, it's 100% FREE! To get it, just: 1. Like & RT 2. Reply "Py" 3. Follow @Ronycoder [MUST]
![Ronycoder's tweet image. PYTHON is difficult to learn, but not anymore!
Introducing "The Ultimate Python ebook "PDF.
You will get:
• 74+ pages cheatsheet
• Save 100+ hours on research
And for 48 hrs, it's 100% FREE!
To get it, just:
1. Like & RT
2. Reply "Py"
3. Follow @Ronycoder [MUST]](https://pbs.twimg.com/media/Gp3afbyXcAAciqy.jpg)
5 AI to convert APIs to MCP servers in just a few minutes. 1. FastAPI-MCP exposes your FastAPI endpoints as MCP servers in one line of code with native auth support. 100% opensource.
All Docker Command Essentials.
💎 SQL Cheat Sheet Find the HQ link inside:
If you're building AI agents, read this twice: There’s a new invisible OS being written for the autonomous future. It’s built on two emerging protocols: • Model Context Protocol (MCP) • Agent-to-Agent Protocol (A2A) Here’s why they’re a big deal—and why you need to care:
Flow – AI 에이전트 제작을 위한 경량 태스크 엔진. 동적 태스크 큐 기반으로 병렬 실행, 동적 스케줄링, 스마트 의존성 지원. 명시적 쓰레딩 없이 복잡한 워크플로우 간소화, OpenTelemetry 추적 지원. 경량 설계와 쓰레드 안전한 상태 관리 제공 news.hada.io/topic?id=18127
news.hada.io
Flow - AI 에이전트 제작을 위한 경량 태스크 엔진 | GeekNews
전통적인 Node-Edge 기반 워크플로우 대신 Dynamic Task Queue 시스템을 사용하여 간결성과 유연성을 중시3가지 원칙동시 실행: 작업이 자동으로 병렬 실행동적 스케줄링: 작업 실행 중 새 작업 추가 가능스마트 의존성: 이전 작업의 결과를 기다려서 처리모든 태스크의 결과는 쓰레드 세이프한 Context에 저장됨이 태스크 기반 아키텍처는 복잡한
A Cheatsheet on Comparing Key-Value Stores
성공가능성이 희박한 석유시추는 재정자금으로 해야 한다던 자들이, 재정자금을 투입해 AI 대기업을 만들고 국민들이 30% 지분을 갖게 하자는 말에는 ‘반시장적 사회주의’라고 악을 씁니다. ‘손실의 공공화, 이익의 사유화’는 자본주의 원리도 아닙니다. 도둑놈들이 국민을 등쳐먹는 수법일 뿐입니다.
Grok 3 is absolutely WILD Here are 17 insane ways it's being used. Learn how to 10x your productivity using Grok 3: 👇
AI Agents 101: 𝗔𝗜 𝗔𝗴𝗲𝗻𝘁 𝗠𝗲𝗺𝗼𝗿𝘆. In general, the memory for an agent is something that we provide via context in the prompt passed to LLM that helps the agent to better plan and react given past interactions or data not immediately available. It is useful to group…
My Cheat Sheet on Database Transactions. Enjoy!
DeepSeek [1] uses elements of the 2015 reinforcement learning prompt engineer [2] and its 2018 refinement [3] which collapses the RL machine and world model of [2] into a single net through the neural net distillation procedure of 1991 [4]: a distilled chain of thought system.…
![SchmidhuberAI's tweet image. DeepSeek [1] uses elements of the 2015 reinforcement learning prompt engineer [2] and its 2018 refinement [3] which collapses the RL machine and world model of [2] into a single net through the neural net distillation procedure of 1991 [4]: a distilled chain of thought system.…](https://pbs.twimg.com/media/Gioh8G8X0AAOdx8.jpg)
United States Trendler
- 1. Knicks 58.2K posts
- 2. #NBACup 4,981 posts
- 3. Wemby 25.2K posts
- 4. Clarkson 6,593 posts
- 5. Tyler Kolek 4,332 posts
- 6. Brunson 16.4K posts
- 7. Mariah 20.7K posts
- 8. Mitchell Robinson 3,098 posts
- 9. #WWENXT 17.1K posts
- 10. Josh Hart 2,687 posts
- 11. Dylan Harper 1,839 posts
- 12. Mike Brown 3,361 posts
- 13. Harrison Barnes 1,435 posts
- 14. Thug 17.5K posts
- 15. Stephon Castle 2,420 posts
- 16. Thea 12.4K posts
- 17. Blake 21.5K posts
- 18. Adam Silver 2,401 posts
- 19. Thibs N/A
- 20. Taylor Rooks 2,006 posts
Bunları beğenebilirsin
Something went wrong.
Something went wrong.