Michidmaa

lol

[Michidmaa @michidoma]

260919 — LEE HI & DOK2 “You & Me” 🇲🇳

their first live performance together as a publicly confirmed couple?

the way they kept smiling at each other, holding hands, and Dok2 calling her “my lady Lee Hi”??? HELLO??? 🫠

Lee Hi looked SO happy with him 🥹

#LEEHI #이하이 #DOK2

[Michidmaa @michidoma]

260919 — LEE HI at Super Concert Special 2026 in UB, Mongolia 🇲🇳💙

SETLIST 🎤
1. ONLY
2. Rose
3. Savior (구원자)
4. UP
5. H.S.K.T.
6. I’m Different (나는 달라)
7. 1, 2, 3, 4
8. Breathe (한숨)
9. You & Me with Dok2
10. Unreleased song with Dok2

#LEEHI #이하이 #LeeHi #Dok2

[Kshitij Mishra | AI & Tech @DAIEvolutionHub]

Anthropic senior engineer just released a 1-hour course on building a team of agents with loops & graphs:

• 00:27 - introduction to CLAUDE.md & Plan mode
• 11:24 - building "skills" & "hooks" for Claude agents
• 37:02 - building agents & subagents with Claude
• 52:47 - self-improving loops & graphs for Claude agents

this 1-hour watch will replace a $500 agentic engineering course

watch today, then read how to build a team of self-improving agents that work together

[sergio @sergiorocaa]

Este ingeniero de Anthropic explica la manera correcta de construir agentes de IA en 14 minutos.

La mayoría de los desarrolladores pasan meses haciéndolo de manera equivocada.

Guarda esto antes de escribir otra línea de código de agente.

[Charlie Hills @charliejhills]

Your Claude Code install is missing a few things.

Here are 40 additions (grouped by what they do):

I've hoarded over a hundred Claude repos this year.

These cover workflows, skills, memory and tools, plus reference libraries worth keeping open.

BUILD A WORKFLOW

1. learn-claude-code → Learn how agents work.
2. karpathy-skills → Cut common coding mistakes.
3. superpowers → Plan, build and test.
4. ponytail → Keep the code simple.
5. gstack → Add planning and review workflows.
6. ECC → Add skills, memory and checks.
7. oh-my-claudecode → Coordinate agent teams.
8. Archon → Build repeatable coding workflows.

ADD SKILLS

9. taste-skill → Improve your designs.
10. anthropics skills → Browse official skills.
11. mattpocock skills → Add engineering skills.
12. wshobson agents → Find specialist agents.
13. claude-plugins → Browse official plugins.
14. addyosmani skills → Add engineering checks.
15. ui-ux-pro-max → Get interface design guidance.
16. awesome-claude-skills → Find more skills.

KEEP THE CONTEXT

17. planning-with-files → Keep plans in files.
18. claude-mem → Carry context across sessions.
19. codegraph → Map the code's connections.
20. graphify → Connect code and documents.
21. repomix → Pack a repo into one file.
22. agentmemory → Give agents persistent memory.
23. beads → Track work across sessions.

CONNECT TOOLS

24. multica → Assign issues to coding agents.
25. firecrawl → Turn websites into usable text.
26. cc-switch → Manage your coding tool setup.
27. context7 → Fetch current code documentation.
28. vibe-kanban → Manage agent tasks on a board.
29. github-mcp → Work with GitHub from Claude.
30. playwright-mcp → Let Claude use a browser.
31. serena → Find and edit relevant code.
32. claude-code-router → Route model requests.
33. awesome-mcp-servers → Find more connectors.

PROMPTS & USAGE

34. system-prompts-ai → Study AI tool prompts.
35. best-practice → Read Claude Code practices.
36. codex-plugin-cc → Add Codex reviews in Claude.
37. claude-hud → See your session usage.
38. rtk → Trim command output.
39. headroom → Compress what the model reads.
40. caveman → Get shorter replies (much shorter).

So pick one for the job you're doing.

Open its repo, follow the setup instructions and try it on a real task before adding the next one.

My Claude resource vault

→ https://t.co/YhLRwAtaHw

Repost ♻️ to help someone in your network.

[yerin baek feed @yerinbfeed]

2026 THE VOLUNTEERS CONCERT - DAY 2

©yenvingtain
#백예린 #yerinbaek #더발룬티어스 #TheVolunteers #TVT

[Michidmaa @michidoma]

🚨 LEE HI IN MONGOLIA 🇲🇳

Lee Hi will be performing at the Super Concert in Mongolia on September 19, alongside Dok2! 🥹✨

📅 September 19, 2026
🎤 Lee Hi + Dok2
📍 Mongolia

#LEEHI #이하이 #LeeHiinMongolia #Mongolia #SuperConcert

[공오 @tellusboutur]

1. 기마구아스 maxi sacco bag suede navy 가방
2. 프라다 안경
3. 후지 필름 natura classica 필름 카메라
4. 루이비통 향수 LV Lovers

[Dark Factor @DarkFactorr]

this is free f*cking gold for anyone still writing code by hand

Zhenfeng Cao just published the exact framework behind why your agent stops needing code review

traditional software: code is the carrier of the decision logic. agentic systems: the loop is the carrier, code is just instrumental

Licensed software → SaaS → Agent-as-a-Service, typed progression

each shift moves more of the complexity off the end-user, not just cheaper pricing

benchmarked against SWE-bench Verified, EvoClaw, and LangChain's own multi-agent coordination studies

give this to your next agent build before you write another line by hand

[공오 @tellusboutur]

2025 yerin b playlist ♬⋆.˚
예린이가 공유하거나 커버한 노래 모음!

𖦹ׂ ₊˚ https://t.co/JBxSguVumq

[Hanako @hanakoxbt]

https://t.co/5w8ILIIelz

[CyrilXBT @cyrilXBT]

this is straight-up wild

jack dorsey (twitter co-founder) just dropped a completely free github repo already sitting at 26.2k stars, and it’s basically an ai-agent operating system for running a business

here’s how it works:

1. clone the repo
2. self-host the server: channels, search, git, automations, it all lives there
3. add your agent to a channel like it’s another teammate, tighten its permissions, and let everyone steer it live

save this and pin it somewhere, you’re going to want it later

[Anatoli Kopadze @AnatoliKopadze]

Google Brain founder, Andrew Ng:

"Prompting will be dead in 6 months, graphs are what's replacing it."

In 2 hours at Stanford he shows how to build agents that work and improve entirely on their own.

The first 10 minutes cover what most $500 courses never do.

Watch the lecture first, then read the guide below on how to build a system that improves itself.

[Ajay @ajay4ai]

A senior Anthropic engineer just dropped a 12-page PDF that quietly exposes why most multi-agent systems are fundamentally broken.

Your agents forget everything once their context window dies.

Graph Engineering fixes that.

Instead of resetting their memory every run, you give your agents a persistent knowledge graph they can write to, query, verify, and build on.

The loop is brutally simple:

Extract → Resolve → Assemble → Query → Repeat

And the architecture is even crazier:

• Extract: Haiku pulls entities + S-P-O triples from every document. One call per doc. The Pydantic schema is the only training data.

• Resolve: Sonnet figures out that “Edwin Aldrin” = “Buzz Aldrin” even with zero string overlap, using descriptions as context.

• Assemble: Canonical nodes. Typed edges. Provenance on every triple. Everything becomes one connected graph.

• Query: Serialize only the relevant subgraph → Sonnet reasons over it → every answer can point back to a specific edge.

Now plug that into a multi-agent system:

Workers write to the graph.

Evaluators fact-check against it.

Agents share memory.

Loops can keep running overnight.

No more pretending a context window is memory.

This 12-page PDF completely changed how I’m thinking about multi-agent systems.

Read it before everyone starts calling this “obvious.”

Then explore the article below.

[kaori @kaorixbt]

Andrej Karpathy spent 8 years at OpenAI and Tesla

Last week, he compressed everything he knows into one free 2-hour lecture

Agents → Loops → Graphs → Self-Improving Systems

People spend $15K on bootcamps that teach less than this

This lecture beats most paid AI engineering courses

You probably don't have 2 hours right now

Don't let this vanish from your feed

Watch it

Then read the guide below

[Anatoli Kopadze @AnatoliKopadze]

Anthropic engineer:

"You're not supposed to prompt Claude. You're supposed to build a system that prompts itself."

In 45 minutes she shows exactly how Anthropic builds agents that remember, fix their own mistakes and get smarter with every run.

This beats any paid course on agents I've seen.

Watch it, then read the guide on building loops below.

[AI_Explorer @ai_explorer25]

Andrej Karpathy’s 1-hour Stanford lecture on AI engineering is one of the best explanations I’ve seen of how AI systems actually work.

The progression is simple:

10% → LLM
30% → Prompt
50% → Agent
70% → Loop
100% → Graph

The key takeaway:

AI engineering isn’t just about writing better prompts.

It’s about building systems around models — giving them context, memory, tools, feedback loops, and data flows.

“Delete everything, keep Graph.”

Definitely worth watching if you’re building with AI agents.

Watch → Bookmark it

[小森谷祐太｜AITECH代表 @aitech_komoriya]

Claude Codeで
ついにコードを図で理解できる
新Skillが実装された。

その名は「Archify」

説明文やリポジトリを渡すだけで、
コードベースを
インタラクティブな図に
変換してくれます。

生成されるのは、
そのまま共有できる
自己完結型のHTMLです。

できることは ▼

✓ アーキテクチャ図
✓ ワークフロー図
✓ シーケンス図
✓ データフロー図
✓ ライフサイクル図
✓ モーション / ルート追跡
✓ ノード検索 / フォーカス
✓ PNG / SVG / WebM出力
✓ 1200×630の共有カード生成

さらに凄いのが、
「それっぽい接続」を
勝手に作らないこと。

型付きJSON IRと
原子レベルのチェックを使い、

構造と接続関係を確認したうえで、
正確に可視化します。

対応ツールはこちら ▼

Cursor
Claude Code
Codex
OpenCode

すでに16k Stars

コードベースの全体像を
「文章で説明させる」時代から、
「動く図で理解する」時代へ。

今年出てきたSkillの中でも、
かなり実用性高いです。

[nicco @0xnicc0]

Anthropic engineer at Stanford: "80% of our engineers are using self-improving loops, now everyone is building agentic graphs"

in a 1-hour lecture at Stanford, an Anthropic engineer reveals how Claude actually thinks, and why traditional single-turn prompting is officially dead

what you'll learn:

why linear agent workflows break, and why directed graphs are replacing them

how to build self-improving feedback loops directly inside Claude

standard prompt chaining vs agentic graph architectures

how Anthropic's internal teams automate complex engineering tasks with autonomous loops

single-turn prompts fail on real-world projects. graphs let agents reason, test, fail, and self-correct until the job is done

this 1-hour watch will replace your $500 course on agentic engineering, save it before it disappears from your feed

[Andrew Ng @AndrewYNg]

The most important skills in Building and Deploying AI Applications. https://t.co/IyWIKLIzeM