젬

[delost @thedelost]

THIS IS PURE F*CKING GOLD

Anthropic just shared one of the best tricks for Claude Code.

The idea: run Sonnet, Haiku and Opus 5.5 at the same time, each one doing only what it's best at.

Better results and way fewer tokens, because every task lands on the right model.

You just start Claude Code like this:

claude --model sonnet --advisor opus

here's how it splits:

→ Sonnet 5 runs the session and writes the code
→ Haiku 5.5 explores files and docs in parallel
→ Opus 5.5 stays on call as advisor for the big decisions
→ you stop burning Opus context on tasks that don't need it

Opus only steps in at three moments:

→ before a plan locks
→ when the same error hits twice
→ before calling it done

Sonnet builds. Haiku explores. Opus reviews.

JEV engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to JEV in milliseconds, and the big models only see the ones that split

the full tree
> Sonnet 5 runs the main session and edits code
> search maps the repo on Haiku 5.5
> grep finds call sites on Haiku 5.5
> docs pulls the API reference on Haiku 5.5
> Opus 5.5 on call as advisor, reads the full transcript when consulted
> JEV routes micro-forks in milliseconds

paste the tree and this prompt into Claude Code ↓

"Reconfigure my Claude Code setup around this tree:
1. Run the main session on Sonnet 5 with Opus 5.5 as advisor.
2. Create three read-only Haiku 5.5 subagents: search (maps the repo), grep (finds call sites), docs (pulls the API reference).
3. Add one rule to CLAUDE.md: consult the advisor before locking a plan, after the same error twice, and before calling a task done.
4. Route fast deterministic forks (tool choice, path selection, retries) through JEV.
Show me every change as a diff first. No edits until I say go."

↳ https://t.co/xb2zLxaR2C

save it, it'll come in handy.

[개또옹 @tdoong6124]

데이식스😽
겨간이있어겨간이… ㅠㅠ

[돈벌고영 @Dontgiveup_26]

결국 비디오 생성 AI 판에서도 '괴물 오픈소스'가 터져버렸음.

5초만 넘어가면 화면이 녹아내리던 고질병을 끝내고, '수 분짜리 롱테이크 영상'을 왜곡 0%로 뽑아내는 13.6B 모델이 나와버림.

심지어 구글 Veo3급 퀄리티인데 코드와 모델 가중치까지 'MIT 라이선스(상업적 100% 무료)'로 통째로 털어버림.

메이투안이 기습 공개한 비디오 AI 끝판왕 'LongCat-Video' 핵심 요약 👇 (타래)

영상은 롱캣 비디오로 생성된 영상인데 이제 오픈소스로도 이정도 뽑음..

[프론(상태:보완수사권폐지반대) @pre_son8]

얘들아 진짜...
귀찮다고 저장만 하지 말고 진짜 연결해 봐

나 솔직히 파워 게으르미라서..
이렇게 챗gpt나 클로드에 연결하라는 거
맨날 저장만 하고 안 했단 말임???

근데 이번에 어도비 연결하자마자
내가 그동안 얼마나 미련하게 산 건지 깨달음을 얻어버림...
그러니까 >> 자주 사용하거나 조금이라도 사용하는 툴 <<

전부 연결해..

일단 연결만 해
나중에 사용해도 되니까 ㅠㅠ
일단 있는 건 다 연결해 버려 제발..

연결하면 내가 하나하나 손으로 미세 ���정하고 딸깍거리던 거
그냥 챗gpt나 클로드에 찡찡대면 다 해줌...

[LOOPY @VibeEverything]

디자인 레퍼런스부터 AI 제작 도구까지 모아둔 웹사이트

디자인 영감을 얻을 수 있는 갤러리와
UI 컴포넌트, 개발 도구, 비주얼 소스, 유틸리티가
카테고리별로 정리돼 있음

흩어진 링크들을 한곳에 모아둬서
여기저기 북마크하고 뒤질 일이 줄어듦

[숙이 @sook_ee_]

‼️‼️Ai 관심있는 사람들‼️‼️
여깁니다!!!!!!!! 여기에요!!!!!!!!!!

이번에 나온 클로드 Opus 5.5 모션그래틱 프롬프트 싹다 오픈함!!!!!!!!!!!!!!!!!!!!

[チャエン | デジライズ CEO《重要AIニュースを毎日最速で発信⚡️》 @masahirochaen]

速すぎる…

なんとChatGPT Dotsのオープンソース版「Open Dots」が早くも公開される。

セルフホストでき、どのagent harnessとも組み合わせられるのが面白い。土日に色々と触ってみます。

・ブラウザ/ターミナル/ファイル操作までこなすComputer use搭載
・チャット/通話/Slackの3経路を横断して同じAIが対応
・Channels SDKでSlack・Teams等に常駐可能
・プロジェクト単位の"Spaces"とドキュメント"Pages"、Web/モバイル両対応

↓詳細

[David Marco💡 @David_TornAI]

🚨 Now Claude Code can read complete documentation without spending a single token.

You just need to connect Claude Code to Google’s NotebookLM via MCP.

Here’s how to do it 👇

[Mr. Buzzoni @Mr_Buzzoni]

paste this Jev prompt into Claude and let it audit you

it installs Jev, studies how you actually work, and shows you exactly where the hours and the money slip away

then it rebuilds your whole setup around the leaks it found

same $20 subscription
and you end up running it better than 95% of the people paying for the same model

the full prompt 👇

[テツメモ｜AI図解×検証｜Newsletter @tetumemo]

📝Anthropicのチームが社内で大人気のSkills「ELI5」ですが、5歳児でもわかるレベルで図解中心にHTML形式で解説してってSkills。これ個人的には自分の手持ちのHTML化Skillsと組み合わせて調整が良い感じ。引用元の手書き風アイコンをMCPで引っ張るとよりわかりやすい！　↓

[Mahax @Mahaximus_]

Jev + Opus 5.5, side by side.

same agent. same task. same 60 decisions.

Opus-only: $2.24 - 3m 37s
Jev + Opus: $0.43 - 1m 15s

the difference is who makes the small calls:

which tool runs next - Jev
is this output good enough - Jev
is the goal met - Jev
rewrite the refund handler - Opus

57 of 60 decisions never touched Opus.

what you're watching:

left routes every decision through Opus 5.5. right asks Jev first, Opus only fires when the task needs real reasoning.

per decision: $0.032 -> $0.00025.

watch the cost counters, not the output. the output is identical.

full setup in the post below ↓

[codila @0xCodila]

Send this Apple-style prompt to Opus 5.5

It will create the best motion design ever...

Try it now with my GrokBot below. Don't forget me later:

[Avid @Av1dlive]

jev + sonnet 5.5 is f**king insane.

my entire workflow got 4x faster after adding these 6 lines to CLAUDE.md.

[with jev connected, paste this👇]

1. Before you start a Claude worker, ask Jev once to select a host-approved profile with one or two sessions. The profile must specify each session’s model and effort level. If Jev makes no selection, use the host default.

2. The host must check Jev’s selection. The host must set the model and effort before each session starts. Keep these settings fixed during the session. The host controls permissions and approvals.

3. Use Sonnet 5.5 at medium effort for clear coding tasks. Use higher effort for complex reasoning or JSON tasks. Use a second Claude only for independent research or a review that the user requested.

4. Give the second Claude the task, applicable files, limits, and completion requirements. Return its findings and evidence to the lead.

5. Complete the requested work. Ask the user only when you cannot continue without input or before an action that needs approval. Do not add features, tests, files, documentation, refactors, or review rounds that the user did not request. When the work is complete and checked, stop. Report the result.

6. Before you report completion, run a test, build, type check, or command that checks the code change. If no check can run, identify the missing check. Explain why it cannot run.

same task. two timers. watch the difference.

[こじか🦌｜教師のObsidian×AI @kojika_edu]

Obsidianに蓄積しすぎて、
第一の脳がフリーズする問題🫠

Hearthで「見返す動線」を作った。

繰り返し目に入るから、記憶に残る。
覚えてるから、そこから思考も深められる。

今まで使ったダッシュボード系の中で、
操作性も機能性も抜群にいい。

思考を止めないために、UIは軽視しちゃダメだな👀

[돈벌고영 @Dontgiveup_26]

최근 Jev와 Kev로 개발자 판이 발칵 뒤집히더니, 결국 '끝판왕'이 나와버렸음.

LLM 호출 97% 삭감하고 속도를 10배 올리는 의사결정 모델을, 마치 'Ollama'처럼 내 맥북 로컬에서 명령어 한 줄로 돌리는 오픈소스 'Ollaya'.

클라우드 API 비용 0��, 몇 밀리초 만에 에이전트 판단 끝내는 치트키 👇 (타래)

[太田賢一／Design Mgr @kenichiota0711]

Claude Slidesとても良いですね。Opus5.5で生成したスライドをClaude Code上で編集できる。UIもスマートで分かりやすい。
——-
公式記事
https://t.co/SYF8LQvfT1

[Zenith @ZenithcoreAi]

🚨BREAKING: Claude can now create Premium Logo!

Like a top branding agency (for free).

Here are 7 Claude prompts that replace $500K logo designers (Save for later):

[Charlie Hills @charliejhills]

Claude Opus 5.5 can (finally) generate motion graphics

16 motion graphics in Claude Code (my 3 steps):

1. Pick one motion, like a chart that morphs.
2. Show Claude a reference and name every state.
3. Ask for HTML and SVG, then fix it round by round.

Download them all here:

https://t.co/pjMv8ExvWx

Repost ♻️ to help someone in your network.

[Anthony Kroeger @kr0der]

i was able to test Grok 4.7 a few days early (very thankful)

it built the whole golden gate bridge in Blender without downloading any meshes/textures online

it took 17 minutes, here was the prompt:

"use the blender MCP to make a detailed model of the golden gate bridge. do not pull in assets from the web."

then it made this video

[카민 @HUUK72670323]

저장 필수각

이거 쓰니까 개편함!