qwen3.6-27b/35b 골든 스팟 (동적 양자화) 빌드와 크기 최적화 빌드를 동시에 작업 중인데, 애플 실리콘 16gb 는 말 그대로 클라이언트 머신으로만 써야할 운명
파라메터가 더 작은 걸 쓰면 상관 없긴 하겠지만, 아주 높은 기대 없이 외부 의존성 없이 자체 서빙하는 모델 하나로 범용적으로 해결하는 기대는 접어야 한다
Introducing @OpenKnowledge, the best markdown IDE for humans and agents.
Open source. Local and private. LLM-wiki ready.
Use with Claude, Codex, and your favorite agent today.
Google just dropped a 1-hour course on agentic engineering from scratch:
00:00 – How to build your first AI agent
08:24 – Build agent memory (short, persistent, long)
28:34 – Agentic loops, long-running AI agents
40:04 – How to build MCP (MCP vs API)
1:00:22 – Multi-agentic systems
This 1-hour watch will replace 10 paid agentic courses on the internet.
Watch it today, then read how to build a self-improving agentic system in the article below.
Two Hong Kong students just made Karpathy's loop 5x better - dropped 18-page PDF
The twist: the loop got 5x better the moment you put another loop on top of it
here's the whole method, step by step:
step 1 → Karpathy's loop gets stuck - the LLM keeps reproposing the same changes, falling back to its priors
step 2 → so they add an outer loop that reads the inner loop's code and finds where it's stuck
step 3 → the outer loop writes new search logic as Python and injects it live - 5x better, same model
how to steal this for your agents:
step 4 → write a second agent whose only job is to read the first one's logs and find where it's stuck
step 5 → let it rewrite the rules - workflow, skill, prompt - not just retry the task
step 6 → auto-revert every rewrite on failure, so a bad change never breaks your pipeline
the result: 5x better than Karpathy's loop alone - same LLM, no smarter model, it's the architecture
this 18-page PDF is what comes after the Karpathy loop
read it now - the full build workflow is in the article below ↓
If you dont know, you can use your Codex subscription inside Claude Code.
That means Fable 5 can call GPT 5.5 + 10 subagents to work together.
This will save you atleast 60% of your Fable 5 token consumption.
You just need to setup once. Here's how:
Step 1: Open Claude Code and install the Codex plugin
/plugin marketplace add openai/codex-plugin-cc
/plugin install codex@openai-codex
/reload-plugins
Step 2: Tell Fable 5 to finish the setup
Paste this prompt:
"Set up Codex inside this Claude Code environment. Use the official OpenAI Codex plugin that was just installed. Run /codex:setup. If Codex CLI is missing, install it. If Codex is installed but not authenticated, ask me to authenticate with my ChatGPT account. After auth is complete, verify that Codex works from inside Claude Code. Then confirm that the codex:codex-rescue sub-agent is available. Do not change any project code during setup."
Step 3: Authentication
Fable 5 will trigger the Codex setup.
You authenticate your ChatGPT/Codex account once.
After that, Codex runs from inside Claude Code using your Codex subscription.
Step 4: Tell Fable 5 how to delegate work
Paste this prompt:
"From now on, use this workflow:
You are the orchestrator.
> Use Fable 5 for planning, repo understanding, architecture decisions, task decomposition, and final review.
> Use codex-rescue as the executor when a task needs heavy implementation, debugging, test fixing, refactoring, or multi-file code edits.
When delegating to Codex, use /codex:rescue.
Prefer GPT 5.5 (xtra high) as the go to Codex model.
Keep Codex tasks focused and specific.
After Codex finishes, inspect the result yourself before accepting it.
Do not blindly trust Codex output."
Pro Tips:
1. Turn this into a skill (i named it Fable-GPT) and call that skill at the start of the session.
2. Use skill + goal to get the heavy tasks done. Goals are best for long horizon tasks.
3. If you're on Codex 20x pro plan, you can use subagents. I use 5-7 agents at one time and never hit 5-hour limit.
4. Context rot is real so clear the conversation after 4 compactions. Use /handoff skill to preserve context.
우리는 DESIGN.md 에서 한번 더 프로덕션 수준으로 나아갈 수 있음.
🖼️ Impeccable - 에이전트에게 없었던 디자인 언어
https://t.co/rSHFr8iNVa
DESIGN.md는 일종의 정적인 설계도예요. 에이전트가 읽긴 하지만, 그걸 지켰는지 검증하는건 또 다른 얘기죠.
Impeccable은 그 DESIGN.md를 더 제대로 작동하게 만들어요.
/impeccable init 이걸로 브랜드인지, 프로덕트인지 판단해서 톤, 컬러, 컴포넌트까지 고려해서 PRODUCT.md + DESIGN.md 생성해줍니다.
여기에 23개의 정밀한 커맨드에 45개의 AI slop 감지 규칙, 라이브 브라우저 이터레이션까지 갖춘 매우 강력한 스킬..
Claude Code, Codex 에서 hook 걸어서 코드 수정 시점에 바로 위반 사항을 감지하거나 아예 반영을 막아버리죠.
제작자 Paul Bakaus 이분도 구글에도 있었고.. 커리어가 엄청나십니다.
가장 좋은건 Impeccable 계속 버전 관리되고 있다는 점! 계속 발전해요. 그게 좋아요.
Andrej Karpathy quietly published 9 rules for building AI agents.
Rule 1: stop writing prompts.
"If you find yourself iterating on a single message at 3 in the morning, you are still in the prompting era."
A friend who runs agent infra at a trading firm read it once and deleted half the harness his team built last quarter.
The whole paper argues most agents die from a weak harness, not a weak model. Everything you added to compensate for the model becomes dead weight the moment the model improves.
The rule near the middle, about letting the loop delete its own work and start over, is the part he screenshotted. It contradicts how almost everyone builds right now.
The closing section on where the bottleneck goes next is the whole paper in one line.
He said he read it twice, second time with his own repo open beside it.
Everyone is still tuning prompts. Karpathy already moved on.
오... AI 에이전트 팀을 회사처럼 운영하게 해주는 툴이야.
최근 급성장 중이고 GitHub 스타도 많이 받음.
🌟 스타는 71k
예전에도 이런 종류의 툴들이 많이 있기도 했지만
사실 코덱스나 클로드 순정만 가지고 놀다보니 익숙해져서 굳이 저렇게 운영해야하나 항상 고민이였는데 품질도 좋아보이고
헤르메스도 마침 지원한다고하니
오늘 설치하고 대신 한번 써볼께
핵심 특징은 이렇타네
하나의 대시보드에서 에이전트들 Claude Codex Cursor OpenClaw 등 모아서 org chart 만들고 목표 할당하고 예산 관리하고 governance까지 다 함.
그냥 프롬프트 던지는 게 아니라 CEO처럼 팀 관리하는 느낌.
Build 1M ARR AI note app 같은 목표 주면 에이전트들이 알아서 일함.
Hermes가 내 repo 전체를 몇 분 만에 학습해서 SKILL.md로 뽑아내는 걸 봤는데, 이건 진짜 충격적임.
코드베이스, API 문서, PDF, 워크플로우 같은 걸 던져주면 자동으로 재사용 가능한 스킬로 만들어 저장함.
메모리는 사실만 기억하지만, 스킬은 “어떻게 일할지”를 기억한다는 점이 핵심.
Write Gate 켜놓으면 승인도 가능.
이제 에이전트가 “내 프로젝트 어떻게 다루는지”를 스스로 문서화하고, 다음에 똑같은 작업 들어오면 바로 활용할 수 있게 됨.
Claw3D repo를 예로 들어서 학습 과정 보여주는 영상 보니, 아키텍처, 모듈 구조, 최근 변경점, Quick Start까지 깔끔하게 정리해주네.