Valentino Harpa

"Hidup indah, bila mencari berkah."

Jarang aktif di sini, jika ada butuhnya, tolong kontak di sosmed lain saja. Terima kasih banyak!

[Isagi @otakuisagi]

Seneng banget sekarang makin banyak anime bisa ditonton gratis dan legal di YouTube. 🥹

Buat yang lagi cari tempat nonton, nih beberapa channel buat nonton anime:

📺 Muse Indonesia
📺 Ani-One Indonesia
📺 Tropics Anime Asia
📺 Muse Asia (ENG SUB)
📺 Ani-One Asia (ENG SUB)

Kalau ada yang kelewat, boleh banget tambahin di reply ya. Biar watchlist kita makin banyak. 👀

[Nico @nicos_ai]

Google lanzó la herramienta que todo desarrollador pedía desde hace años.

Se llama CodeWiki.

Pegas cualquier repositorio y la IA lo convierte automáticamente en una documentación interactiva.

No solo resume el código:

• Genera diagramas automáticamente
• Explica cómo funciona cada parte
• Crea tutoriales paso a paso
• Detecta arquitectura y dependencias
• Y hasta monta un chatbot que entiende tu código completo

Básicamente:
convierte proyectos imposibles de entender en algo que cualquier desarrollador puede navegar en minutos.

[ALUTHEDON @Mbakaza4L]

This flag will get more likes than the Israeli flag.

[hot cocoa @bismillahyuk_]

🚨 Daftar list pegawai yang kena MUTASI dari Menteri PU akibat tersebarnya surat tugas Papi Dody ke New York.

Langsung satset ya di mutasi sama beliau ini 🙂🤯

[h100envy @h100envy]

https://t.co/249JaHcEz7

[ToonHive @ToonHive]

‘Code Lyoko’ is officially returning with a brand-new sequel series currently in production, set to serve as Season 5.

The project is currently in the writing stage, with the original creators and voice cast expected to return nearly 19 years after the show’s last season aired.

[Dhaneswara Intan | Remote Work | Career @workwithdhanes]

Ini ya guys profile upwork aku yang udah tembus beberapa kali invitation di upwork, barangkali ada yang mau nyontek strukturnya aku jabarin satu satu formula yang aku pake.

WHO AM I → WHO I HELP → WHY TRUST ME → PROOF → HOW I WORK → RESULT → RISK REDUCTION → CTA

[rob. @robiartec]

HICIERON UN CAPCUT GRATIS Y SIN MARCAS DE AGUA, Y TIENE 55K STARS EN GITHUB

CapCut te mete marca de agua, te bloquea funciones y encima te cobra suscripción. Un grupo de devs se cansó y construyó la alternativa open source.

→ Editor de vídeo completo, sin marcas de agua ni paywalls

→ Compatible con web, escritorio y móvil → Open source con licencia MIT

→ Servidor MCP incluido para agentes de IA

→ Se está reescribiendo en Rust desde cero con API, plugins y scripting

Se llama OpenCut y es exactamente lo que CapCut debería haber sido desde el principio.

Te lo explico abajo (link de la repoo también) ⬇️

[Sanket Datta @sanketdattta]

@dharmesh Useful rule: query for facts, infer for ambiguity. The expensive mistake is using AI to compensate for weak data plumbing. Where do you draw that line in product decisions?

[Rash_TechAI @irashathadani]

10 RESEARCH WEBSITES THAT PHDS DO NOT WANT YOU TO FIND.

Bookmark this. Academia is gatekept by paywalls and you should not be paying.

1. https://t.co/w5aGmsEO8t
The largest open library on earth. Almost any textbook your professor assigned is here for free.

2. https://t.co/bgokJYdop3
The search engine for academic papers. Sort by citations to find the most influential research.

3. https://t.co/iF6YXpIhEj
AI powered paper search built by the Allen Institute. Highlights every citation in context.

4. https://t.co/5xwH9lD6tl
Plug in one paper, see every related study mapped as a graph. Reveals what experts actually read together.

5. https://t.co/1pMqKlnIWZ
An AI research assistant. Ask any question and get a structured table of papers with key findings.

6. https://t.co/loNjo3UikE
Aggregates the conclusions of thousands of papers into one answer. Stops cherry picking.

7. https://t.co/zoFxYq3kOi
The Spotify of papers. Recommends new research based on what you have already read.

8. https://t.co/SwdhbpHOQt
Visualizes citation chains. Shows how an idea spread across decades of research.

9. https://t.co/RmAmyVOCV7
Tells you which papers support, contradict, or mention any claim. Saves hours of fact checking.

10. https://t.co/D8H3COvPXj
200 million open access papers in one searchable index. The world's largest free academic archive.

Most students pay $40,000 to access what these sites already make free.

[MahaKersa @mahakersa]

Baru beres nonton video ini di yt.

Dan saya tersadarkan kalo menjamurnya org yg jualan seblak, cilok, gorengan dan pedagang olahan tepung lainnya di jalanan bukanlah tanda kebangkitan ekonomi rakyat, tpi sinyal keputusasaan (necessity entrepreneurship) untuk menutupi status pengangguran.

Setidaknya ada 6 poin yg saya dapati :
• Jebakan low barrier to entry: Bisnis olahan tepung dipilih cuma krn modalnya murah dan gk butuh keahlian khusus.

Dampaknya, terjadi ledakan keseragaman yg memicu kanibalisme ekonomi (sesama pedagang kecil saling mematikan di radius beberapa meter saja)

• Romantisasi penderitaan oleh negara: Narasi "UMKM Pahlawan Ekonomi" dikritik sebagai alat politik agar negara bisa lepas tangan dari kewajiban menyediakan lapangan kerja formal dan jaring pengaman sosial.

• Paradoks data pengangguran: Angka pengangguran resmi terlihat turun, tpi pekerja sektor informal melonjak smpe 60%. Ini adalah fenomena pengangguran terselubung, tercatat bekerja, tapi pendapatan minim dan gk menentu.

• Perang Harga vs Hancurnya Daya Beli: Di tengah inflasi dan turunnya kasta kelas menengah, merek bukan lagi faktor penting. Pedagang terpaksa memotong margin keuntungan demi mempertahankan konsumen yg sensitif harga.

• Ironi "Negara Tepung" yg 100% Impor: Indonesia menopang jutaan pedagang kecil dari komoditas yg gak bisa tumbuh di tanah sendiri. Ketergantungan impor gandum yg mutlak membuat nasib pedagang cilok di jalanan sangat rentan terhadap konflik geopolitik dunia dan kurs Dolar.

• Model bisnis ini udah di titik jenuh. Para pedagang seperti berjalan di tempat, bekerja keras 12 jam sehari menghirup asap jalanan, tetapi posisi finansialnya gk bergeser maju sama sekali.

Source : https://t.co/YnzpIZpO3L

[周览资源 @grgerwcwetwet]

终于找到一个能替代 Wireshark 的开源神器。

GitHub 3.7 万 Star 的 Sniffnet，把网络监控做成了普通人也能看懂的样子。

很多人打开 Wireshark 的第一反应都是：
看不懂，直接关闭。

而 Sniffnet 完全不同。

实时显示上传下载流量、连接主机、访问域名、IP 地理位置，甚至还能查看正在偷偷联网的软件。支持流量过滤、PCAP 导入导出、多网卡监控。

最关键的是界面非常舒服。

不用研究抓包规则，不用学习复杂命令，打开就能看到电脑到底在和谁通信。很多用户直接把它当成 GlassWire 的免费替代品。(Windows Central)

Windows、macOS、Linux 全平台支持，Rust 编写，占用资源极低。(GitHub)

对于经常折腾代理、NAS、Docker、服务器的人来说，这绝对属于装机必备工具。

https://t.co/pXQHkfXRzU

[Vincent @Vincent_AINotes]

一个程序员突发奇想：

DNS 解析器会把域名记几天——

那能不能拿来存文件？

↓

他找到了全网 390 万个开放 DNS 解析器

把文件切碎

撒遍整个互联网

没有硬盘 没有数据库 没有云

文件活在无数台服务器的缓存里 而那些服务器根本不知道自己在存东西

如果没人访问呢？

文件会慢慢"死去" 随着服务器们一个个把它遗忘

这是我见过最荒诞的开源项目之一

项目名叫 dnsfs

你会用 DNS 缓存存什么文件？

[Alok @analogalok]

Run Gemma 4 26B MoE on 8GB VRAM with 250k context at 20+ tokens/sec

If you own any 8GB VRAM graphics card, stop what you are doing. Local AI just had its absolute "Holy Shit" moment for budget hardware.

Yesterday, I benchmarked Unsloth Gemma 4 12B Q4_K_XL on an 8GB card.

The community went wild but immediately demanded more: "Can we run a 25B+ model on budget GPUs?"

Today, I’m delivering exactly that.

I am running a massive 26B parameter Mixture of Experts (MoE) model locally on a standard 8GB VRAM setup with 250k full native context!.

If you own an RTX 3060, 3070, 4060, or any budget GPU with 8GB of VRAM, the local AI paradigm has completely changed.

The performance metrics are astonishing:

- 20 tokens/sec flat decode throughput.
- Stable, flat decode speed even with massive prompts.
- I threw a 60k token prompt at it, and it still clocked in at 20 TPS without dropping a single frame.

# What about prefill?

Yes, Time To First Token (TTFT) is slightly high when swallowing massive contexts. But with a solid 200 tokens/sec prefill speed, the wait is barely noticeable and highly usable.

And this is running completely without Multi Token Prediction (MTP) active.

How is this possible? It’s the magic of Google's new QAT (Quantization Aware Training) quants for Gemma 4.

The model weight file (unsloth gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf) is only 13.2 GB, making it the ultimate local powerhouse.

# The Test Setup:

CPU: Intel Core i7

RAM: 16GB System RAM

GPU: NVIDIA GeForce RTX 4060 Laptop GPU (8GB VRAM)

# The Secret Sauce (The -cmoe Flag)

To make this work properly on any 8GB card, you must use the -cmoe (CPU MoE) flag in llama.cpp.

This flag isolates the heavy MoE expert weights directly to system memory (CPU/RAM) while letting your GPU focus strictly on the Attention layers and the KV Cache.

It prevents VRAM spillage and holds the throughput rock solid.

# The flags:

-m "gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf" -cmoe -c 248000 -v

Once running, just open the UI on localhost and toggle the new reasoning lightbulb icon in the text input box to watch the model perform multi step thinking.

Are you still running smaller models, or are you ready to scale up your budget local setups? Let's discuss in the replies

[Abhishek🌱 @Abhishekcur]

This article is literally wow.

i read it 2 years ago, and coming back to it today, it still feels new.

few tutorials teach computers in a way that permanently changes how you think. this is one of them.

If you've never built a VM before, you're missing one of the biggest "aha" moments in computer science.

[Blaze @browomo]

This Chinese guy created agents in Claude Code for landing pages and single-handedly serves 47 small businesses a month, taking $400 from each.

He built a system of 7 agents on Claude Sonnet 4.6 that analyzes Google Maps in small towns, finds small businesses without websites there, and over 1 weekend takes each one to a finished mockup with video and cold message.

No assistant, no sales team, no SDR. Just him, a MacBook, an iPhone, and 1 API key.

And traditional web design agencies keep teams of 8 people on salary for the same order flow, while his expenses are only tokens and subscriptions to Lovable, Higgsfield, and Calendly.

7 agents work through 1 orchestrator on Claude Code Router. Usage is about 3 million tokens a day, the average API bill is about $480 a month.

All 7 go through MCP servers and write shared state to the file system, without shared state in memory and without race conditions, and 1 of them lives right in the iPhone and picks up positive replies from the subway, a taxi, or on walks.

And here is the system prompt he put into the orchestrator before launch:

"You are the orchestrator of a solo agency that sells ready-made websites to local businesses. You delegate read-only tasks to 6 sub-agents and own all writes.

sub-agents:

// Scout (walks through Google Maps in selected cities, looks for narrow niches: 5+ years on the map, fewer than 50 reviews, no website or a website from 2014, but high ratings)
// Diagnoser (for each lead writes a 50-word diagnosis, hero angle, tone matched to the industry, and a cold message under 70 words)
// Builder (generates a landing page mockup in Lovable through MCP only for the top 5 leads per day, with the sharpest diagnoses and the biggest gap)
// Filmer (pulls 5 screenshots of the mockup and through Higgsfield renders a 10-second vertical video 1080x1920 with a soft zoom)
// Pitcher (sends a personalized cold message through the right channel for the niche: email to roofers, SMS to tradesmen, IG DM to salons, LinkedIn to realtors)
// Checker (runs every message through evals for personalization, absence of AI markers and buzzwords before sending)
// Mobile (lives in the iPhone, handles positive replies in real time, books Zoom calls in Calendly through MCP while the owner is on the go).

You never let 2 sub-agents touch 1 lead. You stop and request approval from the human only when a deal exceeds $3,000 or the reply rate in a niche for the day drops below 12%."

Meaning the system knows what it is and within what boundaries it is allowed to act.

It knows it is supposed to find leads on its own.

It knows it is supposed to take each one to a mockup, video, and cold message without intervention.

It knows the human only steps in when a deal goes above $3,000 or the reply rate stops converging.

→ The system runs 24 hours a day

→ Scout goes through about 220 local businesses on Google Maps per day and leaves 30 new leads in the queue

→ Diagnoser outputs 30 structured diagnoses + briefs + cold messages per day

→ Builder assembles 3 to 5 finished landing pages in Lovable for the sharpest leads

→ Filmer renders a 10-second vertical video in Higgsfield for each one

→ Pitcher sends 30 personalized messages per day across 4 channels with a reply rate of about 14%

→ Checker runs every message through evals before sending

And only when a deal breaks $3,000 or the reply rate for the day drops below 12% does the orchestrator wake the owner.

And when the owner at that moment is sitting in the subway or a taxi, the Mobile agent in his iPhone picks up 1 move on its own: replies to a fresh positive reply from a dentist, books a Zoom through Calendly synced to the local time of the client, and puts the lead back in the queue. The owner only has to tap "approve" and in just 10 minutes join the call.

Here is what the system writes in his log during 1 of the Saturdays:

"scout report: 218 businesses checked in Austin, Denver, and Miami, 34 without a website, 19 with a website from 2014, 6 with an active redesign request in reviews. passing top 30 to diagnoser."

"pitcher: 30 cold messages sent across 4 channels, 14 replies, 5 positive, 3 Zoom calls booked for Sunday. passing to closer."

"builder: landing page for Westside Cosmetic Dentistry built in Lovable, 5 sections, mobile, soft beige. URL placed at /Users/dev/maps-agency/clients/westside/v1. filmer launching Higgsfield."

"eval flag: deal with The Lotus Salon at $3,400 exceeds the approved limit of $3,000. sending for manual review."

He has no server of his own and no separate backend.

Just a local file sandbox at /Users/dev/maps-agency, an MCP router, 1 API key to Claude, and the same key forwarded to Claude Code on his iPhone.

Out of everything I have seen this year, this is the cleanest one-person agency for selling websites to small businesses: $480 a month on the API, about $18,800 into the account, and between them 7 prompts, 1 file system, and 1 phone in the pocket.

[Valentino Harpa @bukanvalen]

@HansdeJ38066083 @Londonlife44 @JamesMelville @sequi_simon Having Grok answer on replies is only for Premium users, so I asked Grok separately.

[Nav Toor @heynavtoor]

If I had to land a $200K AI engineer job in 90 days, I would not get a degree.

I would master these 10 GitHub repos.

1. awesome-llm-apps
The production AI playbook. RAG, agents, multimodal apps, all in working code. 106K+ stars.
Repo → https://t.co/oXrD5A8K6a

2. LangChain
The foundational framework. Used in production by Klarna, Replit, Elastic, and most AI startups in 2026.
Repo → https://t.co/alIh6rDDIu

3. LangGraph
The orchestration layer powering production agents. The skill on every senior AI engineer job description.
Repo → https://t.co/bzVBn9uecV

4. CrewAI
Multi-agent coordination. The framework most Fortune 500 teams reach for first.
Repo → https://t.co/0xohE065sD

5. Ollama
Run any open-source LLM on your own machine. The fastest way to learn how models actually work.
Repo → https://t.co/gyZhUdzsnZ

6. awesome-mcp-servers
MCP is the standard every major AI lab adopted in 2026. Knowing it puts you ahead of 99% of engineers.
Repo → https://t.co/ejVOgkRJDX

7. Qdrant
The vector database used for production RAG at scale. Embeddings and semantic search are non-negotiable for AI roles.
Repo → https://t.co/ziSSXW2dzZ

8. AI-Agents-for-Beginners
Microsoft's free 12-lesson course on building agents. Real code, real exercises, real prep.
Repo → https://t.co/7dNsDw6bTj

9. system-design-primer
Production AI is system design. The repo FAANG engineers use to prep for interviews.
Repo → https://t.co/AypwqcL1Xz

10. awesome-claude-code
The playbook for the tool now used inside FAANG, OpenAI, Anthropic, and most YC startups.
Repo → https://t.co/VhNjDoz7YM

Here's the wildest part:

A $200K AI engineer in 2026 isn't paid for a degree.

They are paid for what these 10 repos teach.

The market doesn't care where you learned it. It only cares if you can ship.

90 days. 10 repos. One portfolio that proves you can do the work.

That's it. That's the whole game.

Save this before you forget.

100% free. 100% open source.

[Erick @ErickSky]

[me pueden banear por este repo]
pero al dev de Hermes le gustó este repo, más na' te digo...

_____________________________________________

Headless Chrome está OFICIALMENTE JUBILADO.

Un dev PRO en Rust acaba de lanzó Obscura.

El navegador headless que destroza todo para AI Agents y crawlers.

Esto es lo que lo hace una bestia:

- 30 MB de RAM (Chrome se come varios GB)

- Se inicia en 85 ms

- Todo el binario pesa solo 70 MB

- Modo STEALTH brutal: randomiza fingerprints y bloquea trackers

- Soporta CDP → Puppeteer y Playwright funcionan sin tocar una sola línea de código

Si haces scraping SERIO o corres agentes de IA en escala… este repo es oro puro.

REPOOO👇