sedia tumbal proyek

This page intentionally left blank

[Maxim Kuznetsov @disarto_max]

Some dashboard designs from 2025

[obicle @obicle_]

VPS FREE 3 BULAN

Mayan buat ngulik
https://t.co/3JpvWF0udJ

[Emil Kowalski @emilkowalski]

New skill: /find-animation-opportunities

Search your UI for places that would genuinely benefit from motion, while also telling you what not to animate.

https://t.co/zEnLEjkvIp

[Kepala Warga Tai. @handierawan]

Banyak yang berfikir kalau setelah pengumuman S&P akan langsung mentrigger inflow asing, padahal sepengalaman gua di pasar uler, biasanya ada urutannya:

1. Pergerakan rupiah setidaknya stabil dalam kurun waktu tertentu.
2. Tunggu ada perpindahan flow asing dari bonds/RSBI ke equity perlahan.
3. Perlahan masuk dengan konsisten setelah melihat pasar cukup stabil.

Perlu kalian ketahui:

1. Asing insti besar tidak akan masuk di bottom, mereka akan masuk ketika hampir semua faktor terlihat stabil.
2. Asing flow kalau itu isinya cuma AK BK, ya ga valid, apa lagi AK BK hari ini inflow, besok outflow.

apa yang jadi patokan saat ini?
LIKUIDITAS, jika perlahan stabil di atas 15T selama seminggu - dua minggu kedepan, maka ini signal bagus.

[Tech with Mak @techNmak]

An 82K-star GitHub repo is built around one painfully obvious idea:

Your coding agent should map the codebase once, not grep it forever.

Graphify turns an entire project into a queryable knowledge graph.

Functions, classes, files, SQL schemas, infrastructure, docs, PDFs, images and videos become connected nodes that an agent can traverse instead of repeatedly opening files and reconstructing the architecture.

So instead of:
→ search for authentication
→ open twelve files
→ follow imports manually
→ lose the trail as the context fills up

The agent can ask:
> What connects authentication to the database?
> Trace the path from UserService to DatabasePool.
> Explain RateLimiter.
> Which concepts does everything flow through?

Graphify returns the relevant subgraph and the path connecting the concepts, not another list of keyword matches.

For source code, this is not RAG:
→ No embeddings
→ No vector database
→ No LLM required
→ Code is parsed locally using tree-sitter
→ Calls, imports and inheritance become graph edges

Every relationship is also marked as EXTRACTED, INFERRED, or AMBIGUOUS, so the agent can distinguish what exists explicitly in the source from what Graphify resolved or guessed.

The cleverest part is what happens next.

Graphify can install hooks or persistent instructions for Claude Code, Codex, Cursor, Gemini CLI, Copilot and 20+ other assistants.

Before the agent starts blindly grepping or reading files one by one, it is nudged to query the existing graph first.

The graph can be committed to Git, automatically rebuilt after commits, shared across the team and exposed through MCP.

Long context windows help agents read more code.

A persistent knowledge graph helps them know where to look.

The next improvement in coding agents may not come from stuffing more files into the prompt.

It may come from making them stop rereading the repository.

Here's the GitHub Repo: https://t.co/4ify3X8urp

[Kilauai_ @qc35_]

A call to the supporters in a speech of resistance

I create this on @YouArtStudio and @PixVerse_

[codila @0xCodila]

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 ↓

[Oikon @oikon48]

もしかしてClaude Codeの /advisor コマンドで、指定のモデルをアドバイザーにできる機能が標準搭載されているの知られていない？？

[CJ Zafir @cjzafir]

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.

[Vijay Tupakula @vijaytupakula]

🤯 Wow I can't believe I'm open sourcing the email platform we built internally.

Self-hosted, runs on your own AWS SES. You pay @awscloud $0.10 per 1,000 emails instead of a SaaS markup, and your email data never leaves your infra.

MIT licensed. Here's what it does 🧵

[Putu Prema @putupurema]

Homelab saya, versi 4.0

ISP: Plat merah 150 (DL) / 50 (UL) Mbps
Router: UniFi Express 7
Switch: MikroTik hEX S (sebetulnya ini dulunya router, tapi sekarang saya fungsikan sebagai basic switch karena routernya sudah migrasi ke UniFi)
NAS: Lenovo M720q + TERRAMASTER D4-320. Pakai TrueNAS. Total storage 9 TB (3xHDD dalam konfigurasi RAIDZ1 + SSD L2 cache). Semua self-hosted apps saya (Immich, Nextcloud, Plex, Home Assistant, etc) jalan di sini. Berkat NAS inilah saya bisa merdeka dari subscription Google Drive.
K3s Cluster: Dell OptiPlex 3070 + Custom Desktop PC. Untuk hosting portofolio custom apps saya. Semuanya pakai Fedora Linux. Pod storagenya ngambil dari NAS via iSCSI.
PDU: Unknown brand beli di toko elektronik terdekat.

Sebetulnya ada satu yang gak kelihatan di sini, yaitu VPS di Biznet. Karena ISP plat merah IPv4 nya di belakang CGNAT, terpaksa sewa VPS di Biznet supaya dapat IPv4 publik untuk inbound traffic (yes ada beberapa apps yang perlu publicly exposed). Router UniFi connect ke VPS Biznet pakai Wireguard. VPS nya basically hanya berfungsi sebagai reverse proxy ke homelab saya.

[0xMarioNawfal @RoundtableSpace]

The Hugging bay, The Pirate bay for open LLM's, model weights downloadable with torrents.

This is a game changer.

https://t.co/nuZQ68aluH

[kaize @0x_kaize]

You can turn Opus 4.8 into Fable 5 for Free

And you have 2 days before the window closes.

July 7 is the last day Fable 5 is included in paid plans.

Fom july 8 it's usage credits: $10/$50 per m/tok, 2x Opus, the most expensive model on Anthropic's price list.

What to do?

Make Fable 5 write a skill for Opus 4.8: its reasoning patterns, verification habits, task decomposition, extracted into one SKILL.md your daily model inherits.

The prompt is one line:

"write a SKILL.md for Opus 4.8 capturing how you decompose hard tasks, verify your own work, and decide what to do next".

While the window's still open, 6 more ways to squeeze it:

1/ Give it your hardest problems. it's built for work that takes humans days - easy tasks waste the window.

2/ One big brief instead of 20 messages: full context, constraints, edge cases in message one - it decomposes the rest.

3/ Effort on high by default: xhigh only for genuinely brutal runs - high on Fable often beats xhigh on older models.

4/ One .md memory file that accumulates learnings across sessions.

5/ Make it verify its own work before reporting - kills the fake "done".

6/ delete your opus-era prompts - over-detailed instructions actively hurt Fable 5.

Access to Fable expires on the 7th, but the files it wrote don't.

Everyone else will figure this out on July 8, but you have until the 7th.

Once you've done that, be sure to read the article about Loop engineering, because you'll be working with it extensively after July 7:

[sedia tumbal proyek @masozee]

@ichikiwhere Citayem date kereta jakarta kota 7.03 wib mantep si

[Ikhwan Hsn @Ikhwanhsn]

Yang udah terlanjur masuk kuliah IT gimana bang?
Gapapa malah bagus, lanjutkan...

Pelajari ini:
> Openclaw/ Hermes
> x402 agentic payments
> Blockchain system

Combine itu semua, monetize, harusnya ga perlu kerja 9-5 lagi...

[Lambe Saham @LambeSahamjja]

ada santri nanya orang kristen bisa masuk surga gk ?

Santri: Cak, kebetulan teman profesi saya beragama Hindu. Beliau sering tanya, nanti setelah mati, selain agama Islam, apakah bisa masuk surganya Allah?

Cak Nun: Sangat bagus pertanyaanmu itu. Tapi ini soal antara qat'i dengan dhanni. Qat'i itu sesuatu yang pasti. Tapi pasti bagi siapa? Bagi kita, itu jadi tidak pasti. Yang kedua, dhanni itu berprasangka kira-kira masuk atau tidak masuk.

Santri lain: Mbah, apakah selain Islam bisa masuk surganya Allah?

Cak Nun: Itu jawabannya qat'i, Mas dan qat'i itu pasti. Tapi coba, aku tanya balik: kamu sendiri pasti masuk surga?

Santri: ...Ragu-ragu, Cak.

Cak Nun: Nah, kan. Dan tidak mungkin ada kepastian, karena kepastian hanya ada di tangan Allah. Kita hidup ini cuma mudah-mudahan "laallakum", bukan kepastian. Sama seperti puasa: kutiba 'alaikumus-shiyam... laallakum tattaqun supaya kamu bertakwa, bukan "supaya kamu pasti jadi takwa". Dinamis, kadang naik kadang turun.

Santri: Jadi bagaimana sikap kita, Cak?

Cak Nun: Kalau saya, posisinya sederhana: ayo didoakan saja. Mudah-mudahan semua orang yang baik diterima Allah, dimasukkan surga. Karena dia Hindu, Buddha, Kristen, atau Islam, itu urusan dia sama Allah bukan urusan saya. Kalau dia bersyahadat, itu kepada Allah, bukan kepada saya. Jadi saya tidak punya urusan menghakimi itu. Yang penting, doakan saja, dan pastikan dia jadi teman yang baik.

[Beta EP - 🍉 @BetaEpsilonPhi]

Hati-hati ya, di lingkungan Pemerintahan sudah ada yang kena tuntut dari Microsoft,

Besarnya lumayan 😅,

Masih ada opsi Open Source 🙏

Kiri : Fatwa MUI 1/2003 tentang Hak Cipta
Kanan : Tarjih Muhammadiyah

[独立开发者William @DLKFZWilliam2]

哈哈哈哈太妙了，看到一个神奇的项目，将context上下文转换为图像，然后通过OCR 处理，将 Fable 5的输入成本降低高达约 70%。😂

[𝗕𝗿𝗶𝗮𝗻 𝗥𝗲𝘆 @BrianMRey]

if you’re building an app

make sure to apply to Apple’s Small Business Program

doesn’t matter if you’ve launched yet or not

it’s completely free

and cuts Apple’s fee from 30% → 15%

[sedia tumbal proyek @masozee]

@mornbebey @SudutTakKasat @dorokdoker @haixensen Kayanya ini emang garis miring, terus diatasnya coret/kotor, karna atasnya itu lrbih tipis dibanding angka 7 yg di kiri