Hadikusuma Wahab

@AAidityas Nice use case dan video. Salam kenal!

GILAKKKK NYAMBUNGIN CLAUDE KE NANO BANANA 2 UNTUK BIKIN IKLAN JADINYA KEREN BGT COY! CUMA 6 MENIT VERSI SINGKATNYA! DAN PAKAI SKILL GRATISAN! iseng nyambungin Claude Code ke API Viostudio.id libur lebaran kemarin hasilnya: 40 ad creative ke-generate sekaligus dari template, tanpa buka Canva, tanpa klik satu-satu yang menarik buat gua bukan cuma hasilnya, tapi apa yang ke-unlock kalau pola ini dipakai lebih jauh: bisnis yang biasanya nunggu 3 hari buat revisi desainer sekarang bisa iterasi puluhan variasi iklan dalam hitungan menit A/B testing jadi beda level. bukan lagi 2-3 variasi tapi 20, 30, 40 sekaligus, tinggal lihat mana yang perform UMKM yang nggak punya budget desainer bisa produce creative sebanyak brand besar kalau disambungin ke scheduler bisa full auto: generate, approve, publish satu orang bisa output sebanyak tim desain kecil dengan setup kayak gini video prosesnya ada di bawah 👇

@CryptoEights bener banget. mental model gw skrg, cukup pahami konsepnya, lalu implementasi sesuai kebutuhan. supaya cepet paham konsepnya, share ke agent, otomatis summary, ngobrol2 bentar. udah deh rasa penasarannya ilang :)) kalau berguna, lanjut pake

Siapa yang disini ngerasain hal yang sama Lagi coba hal baru udah ada yang lebih baru Baru coba install openclaw udah ada ini Baru buat AI Agents udah ada yang duluan Perkembangan AI emang ga ngotak Kita dituntut shipping lebih cepat Tapi yang harus dijaga adalah KEMAUAN kita untuk berkembang

Jadi penasaran gimana cara Claude Team bisa produktif ini. Gimana mereka plan, rollout, evaluate semua fitur2 ini. Things to explore over the weekend.

Claude makin serius di agentic sejak OpenClaw. Pace development-nya cepet bgt bahkan lebih cepet dari pace kita buat ngikut atau nyobain 😅 Gw notice banyak fitur baru yang dirilis yg berhubungan dengan Agents/Agentic, 1. Auto Mode. Kalau biasa pake Claude code, relevan bgt sering ditanya permission. Bisa pake "dangerously skip permissions" tapi ada resiko. Dengan auto mode jadi smarter permissions, bukan skip permissions. 2. Remote Control. Session Claude Code bisa lanjut dari HP via app Claude. Uda coba di Android masih buggy. 3. Claude Channels. Chat sama Claude Code via Telegram atau Discord. 4. Computer Use. Claude bisa kontrol komputer langsung. 5. Dispatch. Kirim task ke Claude Cowork dari HP, desktop yang ngerjain. 6. Scheduled Tasks. Claude Cowork bisa punya cron / schedule. Bisa buat Morning briefing, weekly report. 7. 1 juta context window. Codebase besar, dokumen panjang, semua masuk. 8. Command /loop. Ketik /loop 5m check deployment di terminal, Claude Code jadi background worker. Belum lagi, Openclaw juga updatenya ngebut banget 🤣 Mental model sekarang, cukup tau aja semua update, ga harus semua dicobain. Dan bbrp fitur di atas juga masih research preview, belum stabil. Jadi fokus ke use case utama kita aja dan cobain fitur2 baru yg relevan.

@mvanhorn awesome!

@dhiku Just submitted a feature pr and it got merged! Woohoo! Thanks for the intro.

@amirk 🫡 Barusan post ini, x.com/i/status/20363…

@dhiku siap menyimak

Mau coba mulai rutin post lagi, setelah lama gak aktif. Topiknya akan fokus di AI. Kebetulan emg suka ngulik dan kantor Vidio/Emtek jg cukup masif implementasi AI selama 2 tahun terakhir. Di X, post lbh lengkap mulai dari project2 AI yg menarik, real use case yang bisa langsung kepake sampai ke bahasan teknis. Sedangkan di thread post akan lebih ke real use case. Tulisan murni dari gw based on experience, bukan agent. Silahkan follow dan kenalan 👋

Ini jadi alasan kenapa AI agent yg gw bikin fokus di use case sbg chief of staff utk productivity (ada di post sebelumnya atau di highlights). Kalau udah jalan smooth buat pribadi berikutnya tinggal implementasi di kerjaan. Tentunya dgn extra security dan scalability.

@FinnWestX Overall chatgpt 5.4 is still the best experience for agent. Sonnet for finance related. Most reliable but expensive Kimi k2.5 for the rest. Best value for money.

Use Case OpenClaw agent dan Review setelah 2 bulan 🦞 Dari awal tujuannya adalah bikin "sistem" yang memudahkan manage personal life dan project. Prinsip Atomic Habit, build system to make new habit. Jadi setup Openclaw-nya cukup challenging: multiple agent, model, users. Gw pake tema My Hero Academia buat naming karena setiap agent punya karakter, domain, dan "kekuatan" masing-masing. Total ada 6 agent. All Might: Chief of Staff & Orchestrator Agent Ini karakter utama, chief of staff. Setiap pagi dia kirim briefing ke WhatsApp gw, semua Todo yg perlu perhatian (connect dengan Workflowy, Calendar). Semua reminder dan notifikasi dari agent lain juga lewat dia. Intinya dia sbg orchestrator, bahkan bisa modify behavior agent lain. Multiple channel, aturan simpelnya: kalau butuh perhatian gw → WhatsApp (dan di pin atas). Kalau mau diskusi detail → Telegram. Aizawa: Parenting Agent Bisa buat journaling anak, diskusi soal parenting, pola perilaku anak, reminder jadwal sekolah. Anak-anak juga bisa tanya langsung via WhatsApp mereka sendiri yang lebih secure karena ada guardrails. Yang menarik, knowledge dan wisdom dari berbagai framework parenting yg cocok udah diajarin sebagai skill. Deku: Product & Coding Agent Semua urusan product development side project gw masuk sini. Mulai dari yg non profit darisini.com, ruangkajian, dan jg wellness di activebarn, sgym. Deku tau knowledge-nya, konteksnya, stack-nya, ga perlu gw jelasin ulang tiap sesi. Urusan coding pakai Claude Code, agentic dan iteratif. Deku paham semua knowledge dari Lenny Ratchitsky database dan wisdom dari Shreyas Doshi dan bbrp thought leaders product & tech. Hawk: Business Agent Semua urusan business lewat Hawk. Yang bikin menarik: agent ini di-share ke pasangan dan saudara gw via WhatsApp, masing-masing dari nomor mereka sendiri. Jadi mereka mau tanya atau minta apapun bisa lebih mudah, karena Hawk uda ngerti semua informasi2 penting. Momo: Finance Agent Buat urusan personal finance, budget, tax, dan investment. Sengaja dipisah karena datanya penting dan perlu set model yang lebih canggih/mahal Claude Sonnet karena analisis keuangan butuh reasoning yang lebih kuat. Todoroki: Research Agent Ini yang paling beda. Todoroki jalan di framework terpisah, NanoClaw, berbasis Claude Code SDK. Dia ga cuma jawab sekali. Dia search, evaluate, re-search, baca pdf, web, dan terus iterasi sampai dapat jawaban yang beneran. Yg gw suka dari Claude code adalah Agentic browsing-nya beda kelas dengan yg lain. Dan hasil summary jawabannya verbose bgt. Output-nya langsung tersimpan ke Obsidian vault gw (sync Google Drive). Satu tempat, searchable selamanya. Kesimpulan Setelah jalan dua bulan, gw merasakan sendiri banyak bgt manfaat yang didapat, waktu yang dihemat, dan bisa lebih fokus. Next level productivity tool. ✅ Multiple agent yang punya spesialisasi dan bisa bekerja sama ✅ Multiple channel bisa di telegram dan whatsApp sekaligus ✅ Multiple user, pasangan dan keluarga gw bisa akses agent yang relevan ✅ Multiple model via OpenAI Oauth dan OpenRouter ✅ Terintegrasi Google Workspace, Workflowy, Obsidian, etc Overall experience sudah ok. Setup awal agak ribet tapi ternyata yang paling challenging setelah digunakan cukup lama adalah "maintenance" supaya hasilnya ttp konsisten. Kita harus tau cara kerjanya Openclaw untuk menutupi kekurangannya, file yg digenerate bisa cukup messy, jadi perlu tweak terus supaya hasilnya rapi dan konsisten. Tapi kalau udah ngerti caranya, you'll never go back to the "old" system. Berikutnya gw akan post lebih detail teknis setup Openclaw dan skill masing-masing agent. Stay tune!

The working style of OpenClaw founder @steipete is insane. bro runs 4–10 AI coding agents in parallel to generate, review, and commit code at superhuman speed. hitting 500+ commits pretty much every day and did 6,600+ in jan month alone. NVIDIA CEO must be happy seeing him spend $250k worth of tokens every month lmao

the most underrated hire right now is a great product person. when i say product person i'm def not talking about a product manager. perhaps i think there has to be somewhat of a new role. i don't have a good name for it yet but maybe something like "product thinker".. someone with an intuitive grasp of the product as it exists, where it's soft, where it sings, & how to iterate it toward something even sharper. in some sense, this person has to cohesively hold in their head where this product should be 2 years from now & work backwards from that. i say this cuz when building was hard, engineering was the bottleneck & the status hierarchy often reflected that. building is no longer hard. which means the variance in outcomes has shifted almost entirely to judgment on what to build, how to sequence it, & how to talk about it. & the story matters as much as the thing. internally, it organizes the team around a shared model of why. externally, it shapes the interpretive frame users bring to their first experience. you can't retrofit narrative onto a product & expect it to land, it has to be load bearing from the start. the rarest version of this person sits at the intersection of culture & deep technology. someone genuinely bilingual. they know what's technically possible & they know which cultural currents are real vs. ephemeral. that combo is what separates products that feel inevitable from products that feel assembled. before ppl clap back with this person has always been valuable, i know.. i am just saying now they might be the most *important* person in the room. their value compounds like never before.

we just wrote the ultimate beginner's guide to OpenClaw almost everyone @every has one now, and they have completely changed the way we work and live. we're using our claws to: - build product - answer customer service queries - book hard-to-get restaurant reservations - track our reading notes and much more this is the guide we wish we'd had at the start: every.to/guides/claw-sc…

A few random notes from claude coding quite a bit last few weeks. Coding workflow. Given the latest lift in LLM coding capability, like many others I rapidly went from about 80% manual+autocomplete coding and 20% agents in November to 80% agent coding and 20% edits+touchups in December. i.e. I really am mostly programming in English now, a bit sheepishly telling the LLM what code to write... in words. It hurts the ego a bit but the power to operate over software in large "code actions" is just too net useful, especially once you adapt to it, configure it, learn to use it, and wrap your head around what it can and cannot do. This is easily the biggest change to my basic coding workflow in ~2 decades of programming and it happened over the course of a few weeks. I'd expect something similar to be happening to well into double digit percent of engineers out there, while the awareness of it in the general population feels well into low single digit percent. IDEs/agent swarms/fallability. Both the "no need for IDE anymore" hype and the "agent swarm" hype is imo too much for right now. The models definitely still make mistakes and if you have any code you actually care about I would watch them like a hawk, in a nice large IDE on the side. The mistakes have changed a lot - they are not simple syntax errors anymore, they are subtle conceptual errors that a slightly sloppy, hasty junior dev might do. The most common category is that the models make wrong assumptions on your behalf and just run along with them without checking. They also don't manage their confusion, they don't seek clarifications, they don't surface inconsistencies, they don't present tradeoffs, they don't push back when they should, and they are still a little too sycophantic. Things get better in plan mode, but there is some need for a lightweight inline plan mode. They also really like to overcomplicate code and APIs, they bloat abstractions, they don't clean up dead code after themselves, etc. They will implement an inefficient, bloated, brittle construction over 1000 lines of code and it's up to you to be like "umm couldn't you just do this instead?" and they will be like "of course!" and immediately cut it down to 100 lines. They still sometimes change/remove comments and code they don't like or don't sufficiently understand as side effects, even if it is orthogonal to the task at hand. All of this happens despite a few simple attempts to fix it via instructions in CLAUDE . md. Despite all these issues, it is still a net huge improvement and it's very difficult to imagine going back to manual coding. TLDR everyone has their developing flow, my current is a small few CC sessions on the left in ghostty windows/tabs and an IDE on the right for viewing the code + manual edits. Tenacity. It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day. It's a "feel the AGI" moment to watch it struggle with something for a long time just to come out victorious 30 minutes later. You realize that stamina is a core bottleneck to work and that with LLMs in hand it has been dramatically increased. Speedups. It's not clear how to measure the "speedup" of LLM assistance. Certainly I feel net way faster at what I was going to do, but the main effect is that I do a lot more than I was going to do because 1) I can code up all kinds of things that just wouldn't have been worth coding before and 2) I can approach code that I couldn't work on before because of knowledge/skill issue. So certainly it's speedup, but it's possibly a lot more an expansion. Leverage. LLMs are exceptionally good at looping until they meet specific goals and this is where most of the "feel the AGI" magic is to be found. Don't tell it what to do, give it success criteria and watch it go. Get it to write tests first and then pass them. Put it in the loop with a browser MCP. Write the naive algorithm that is very likely correct first, then ask it to optimize it while preserving correctness. Change your approach from imperative to declarative to get the agents looping longer and gain leverage. Fun. I didn't anticipate that with agents programming feels *more* fun because a lot of the fill in the blanks drudgery is removed and what remains is the creative part. I also feel less blocked/stuck (which is not fun) and I experience a lot more courage because there's almost always a way to work hand in hand with it to make some positive progress. I have seen the opposite sentiment from other people too; LLM coding will split up engineers based on those who primarily liked coding and those who primarily liked building. Atrophy. I've already noticed that I am slowly starting to atrophy my ability to write code manually. Generation (writing code) and discrimination (reading code) are different capabilities in the brain. Largely due to all the little mostly syntactic details involved in programming, you can review code just fine even if you struggle to write it. Slopacolypse. I am bracing for 2026 as the year of the slopacolypse across all of github, substack, arxiv, X/instagram, and generally all digital media. We're also going to see a lot more AI hype productivity theater (is that even possible?), on the side of actual, real improvements. Questions. A few of the questions on my mind: - What happens to the "10X engineer" - the ratio of productivity between the mean and the max engineer? It's quite possible that this grows *a lot*. - Armed with LLMs, do generalists increasingly outperform specialists? LLMs are a lot better at fill in the blanks (the micro) than grand strategy (the macro). - What does LLM coding feel like in the future? Is it like playing StarCraft? Playing Factorio? Playing music? - How much of society is bottlenecked by digital knowledge work? TLDR Where does this leave us? LLM agent capabilities (Claude & Codex especially) have crossed some kind of threshold of coherence around December 2025 and caused a phase shift in software engineering and closely related. The intelligence part suddenly feels quite a bit ahead of all the rest of it - integrations (tools, knowledge), the necessity for new organizational workflows, processes, diffusion more generally. 2026 is going to be a high energy year as the industry metabolizes the new capability.