Eka Put

“Produce One Chapter Like It”: The Miraculous Inimitability of the Qur’ān’s sapienceinstitute.org/produce-one-ch…

Lots of people compare LLMs to assembly, and say "You didn't look at the assembly output of your program, why would you look at the output of the LLM?". Well, first, in the Linux Kernel we did look at the generated assembly often. But leaving that aside: Except for the rare compile bugs, I can trust that if I write correct code, I will end up with correct assembly. I also know that the compiler will not start adding security holes on its own volition. No such guarantees with llm.

Yang kehilangan personel? Indonesia. Yang mendesak rapat darurat? Prancis. Benar-benar presiden kita tak punya wibawa sama sekali.

Appears that a big chunk of Claude Code's source code has been exposed on npm via a .map file accidentally uploaded to the public registry. ~512K lines of code ~1,900 files HugOps to the Anthropic team, this is brutal github.com/instructkr/cla…

@ArdyaDipta @ariaghora Waktu skripsi bikin ini juga pakai algoritma fp-growth, gak tau bener gak ya pak? Tapi berhasil si bikin sistem rekomendasi 😅

@__r17x @bepituLaz @satya_fariz Makasih pak

@EkaPutCom @bepituLaz @satya_fariz invited

Tulisannya bagus banget (membuat lu semakin berfikir untuk mengurungkan niat untuk FOMO dengan agentic tools dan mulai mengembangkan "workflow" sendiri) praetorian.com/blog/determini…

@giosakti @idswdev @idswdev 2026 di sekitar bulan november juga pak?

Bulan November 2025 kemarin ngadain @idswdev tema utamanya tentang "AI". Tapi kayaknya "AI" sekarang udah beda banget sama yang dibahas waktu itu. Cepet banget perubahan landscapenya 😅 Bakal makin seru kayaknya @idswdev 2026 nanti, soalnya komunitas lokal udah makin intens 😉

@__r17x @bepituLaz @satya_fariz boleh ikutan juga pak?

@bepituLaz Kalau mau lihat, ada di project @satya_fariz (bisa di invite sama dia) 🤣

@atmorojo @azamuddin91 Pake KDE aja pak dan jangan di oprek2

@azamuddin91 Buat saya Linux itu distracting karena suka ricing. Lebih seneng moles desktop ketimbang nge-game 😅 Udah lama sembuh. Weekend ini coba hijrah ke wayland. Ternyata ada bug di compositor pilihan. Sekarang masih kejebak di lubang kelinci, tersesat jauh dari produktivitas.

Alasan gw milih linux karena less distracting, buat kerja pake ini. Workflownya lebih masuk, bisa dicustomize biar makin smooth, dan focus on work.

Sekarang lebih value simplicity daripada complexity keren2an. Misal.... seputar Kubernetes, Microservice, Distributed System Entah karena umur (*uhuk), entah experience, entah trend, entah efek AI, entah karena jadi pragmatis, atau apa ya... Sekarang berpikir 10x sebelum nyentuh hal2 complex itu - Repot gak tuh maintainnya? Kalau perlu dedicated person, atau bakal ada overhead 10% ops, gak usah deh - AI friendly gak? Kalau malah bikin susah vibe coding, gak usah deh - Memperlambat dev gak? Kalau quite significantly, dan gak worth the impact, gak deh - Dibutuhkan buat scale kita di 1-2 tahun ini gak? Kalau belum, nanti dulu deh. Sistem yang ini gpp kok kalau cuma kuat 500 rps - Bisa "nyampah" dulu dan *gampang direfactor* nanti gak? Kalau bisa, ya sudah nyampah dulu, yang penting cepet jadi dan solve current problem - Ngimpact ke bisnis gak? Atau cuma keren2an technical, tapi dikit biz valuenya? - Ini bakal potensi direuse/diextend gak? If not, udah gak usah bikin interface atau layer tambahan, keep it simple dulu. Refactor later, toh gampang pake AI - Future usecase yang kita pikirin sekarang ini akan terjadi gak di 1-2 tahun ini? Apakah kita ada plan ke arah sana? If not, gak worth complexitynya - Ini library/framework masih exist gak di 2 tahun ini? Gede gak communitynya? - Ini nambah moving parts gak? Nampah potential bugs gak? dll

@imrenagi belum mulai pak?

Lets go! Segera kita mulai!

@tibudiyanto Nixos di vm?

current dev setup: - nixos - home-manager with all my dev settings - opencode via distrobox-export

you know whats underrated? distrobox-export

Halo semua! Gw memutuskan utk ngeyoutube lagi dan kita akan mulai dengan live stream buat ngebongkar AI setup & workflow dari developer-developer di sekitar kita. Di episode perdana ini kita akan bongkar development setup @bepituLaz ! Selasa 7-8 PM WIB! youtube.com/live/Fde7DdRAr…

@mgppap Bagus pak?

pakai GLM 5 Turbo, sampai lupa kalau masih subs claude 😅

@arisetyo_v2 Wen.ru, Xtgem 😂

OGs remember WAP and WML

The greatest privilege my past success has gotten me is that I can wake my daughter up at 730, eat breakfast with my family in LA, be in SF by 915, have a full day of work until 5, and be back home in LA in time to read and put my daughter to bed. Extremely thankful.

🧵 Satu tahun terakhir saya mengembangkan startup (galenic.systems) sebagai side hustle di sela-sela waktu luang. Saat ini sudah ada dua produk SAAS yang market ready. Semuanya saya kerjakan sendiri + AI; mulai dari product research, production, sampai marketing. (1/9)

Claude Code wiped our production database with a Terraform command. It took down the DataTalksClub course platform and 2.5 years of submissions: homework, projects, and leaderboards. Automated snapshots were gone too. In the newsletter, I wrote the full timeline + what I changed so this doesn't happen again. If you use Terraform (or let agents touch infra), this is a good story for you to read. alexeyondata.substack.com/p/how-i-droppe…

Since last year, I've arguably been wrongfully accused in a state corruption case. To defend my innocence, I spent past 6 weeks building an agentic AI swarm that: Analyzed 4700+ pages court docs Mapped 8900+ testimonies Found dozens of contradictions This is how I fight 👇🏼 First off, some context may be necessary. Even though I'm accused in a state corruption case, I'm not a government official. I'm a software engineer. I spent over 15 years building large-scale tech systems across Europe and Indonesia. I've led engineering teams of up to 600 people and helped grow a small tech startup into a unicorn. In 2016, I moved back from Europe to Indonesia, because I believe technology at scale could make a real difference to the millions of people in the nation. Six years ago, working as a tech consultant under a nonprofit foundation, I started advising Indonesia's Ministry of Education on building large-scale technology platforms. Public sector work pays significantly less than private sector, and I took close to a 50% pay cut to make the switch. I was fine with that. Using what I knew to help underserved communities in Indonesia felt like the right trade. Our mission was to build a user-centric superapp for public education, specifically for teachers and public schools, the kind of work the private sector ignores because there's no money in it. At some point, officials at the ministry asked for my input on one of their procurement plans. I helped them work through the technical details, shared what I knew, laid out the pros and cons, and recommended a set of tests they should run to determine which options were the most suitable. By the time they made their final decision and executed the procurement, I had already resigned from the consulting work, so I didn't think much of it. Fast forward to May 2025. My house was raided as part of a newly opened corruption investigation tied to that procurement. Two months later, I was named a suspect and placed under city detention due to my health. The trial started in January 2026. We've been through more than a dozen sessions so far, and not a single piece of evidence or testimony has been presented showing I received a single cent from the procurement. What came to light was the opposite: evidence and testimony that my recommendations were neutral and likely were ultimately ignored by the ministry's own team, who went ahead and made the call on their own. So why am I the one on trial? Because the ministry officials who did take money from the procurement vendors needed someone to blame for the decisions they made. Blaming an outside consultant is the easy way out. Witness testimonies in court has shown that the officials actively directed the procurement while claiming it was done on my instructions and even misled their own team within the ministry by saying I held a position of authority. We needed evidence to dispute those accusations, questions to cross-examine the witnesses, and we needed them fast. This is where my AI comes in. A few days before the trial began, we received a 4400-page printed document containing all the witness statements collected during the investigation, plus several hundred pages of other related documents. The information asymmetry is staggering. Those with deep enough pockets to hire large law firms can throw dozens of paralegals and associates at a document like that and mount a proper defense on short notice. I didn't have that kind of money. By then, I had been out of work for more than six months. The AI startup I founded had to shut down. Our investors asked us to return their funding. I had to lay off the entire team. Most of my lawyers are friends of my wife from her college days, who stepped up and waived most of their fees because they could see I was being railroaded. The whole situation felt hopeless. But somewhere in the middle of the despair, a spark lit up. Combing through and analyzing thousands of pages of documents is exactly the kind of problem AI was built for. I've built AI systems before, so I know the key to applying AI to a real-world problem is understanding the strengths and limitations of the available models, and figuring out how to make things not just work, but work efficiently enough to put into production. I was placed under city detention due to health issues with my heart, compounded by a tumor that has been growing rapidly over the past few months. But it also means I still have access to my dev PC. So I started with small experiments. My lawyers found a printing service that could scan the thousands of pages in a couple of days. At first, I tried simply uploading the scanned PDF into existing chatbots like ChatGPT, but the file was far too large for anything they could handle. Even when I managed to get it working through external cloud storage, the results were atrocious. Half of the strategies and "facts" the models surfaced were hallucinations. That wouldn't just be useless in court, it's actively dangerous and can jeopardize my defense. My experience building complex AI systems told me that the key to reducing those hallucinations is better data preprocessing. So I spent the first couple of weeks focusing on parsing the uploaded PDFs, running various kinds of text extraction, and eventually settled on building an agentic AI swarm that performs multiple layers of preprocessing and analysis. This multi-step analysis by several AI agents that swarm the PDF and extract different aspects of the case produces a dense knowledge graph where we can even trace the flow of money involved. My lawyers can now easily browse, filter, and search through nearly 9000 witness statements. We even discovered several witnesses with duplicate testimony, raising suspicion of coordinated efforts or tampering among them. But I didn't stop there. The processing chain includes several higher-level intelligence layers that draw from all the signals in the extracted knowledge graph. These layers add semantic understanding that powers a Chat AI feature, where we can ask specific questions about the case and get grounded answers. I even built a self-reflective sub-agent that automatically challenges and inspects the results to make sure there are zero hallucinations. Overall, the AI has helped me and my legal team uncover the big picture of what actually happened, and build questions that span hundreds of separate testimony sessions, giving us an unprecedented ability to cross-examine witnesses in court and significantly improved our defenses. But I have grander vision than just helping my own legal team. Indonesia's legal system is severely overburdened, with a huge number of cases flowing through the courts every year. This kind of AI could be a useful tool not just for lawyers, but also for judges and prosecutors trying to make sense of their caseloads. With the cross-examinations we've conducted and the weight of evidence that has come to light, we are aiming for an acquittal. Should that be the case, my pledge is to keep building this AI platform into something that can meaningfully improve the quality of justice in our legal system: by helping investigators analyze cases more thoroughly and shine a light on any potential crimes, by raising the standard of what prosecutors bring before a judge, and by giving lawyers the ability to uncover the truth in their clients' cases faster than ever before. Because in the end, I want what I've built to help more than just myself. I believe it can ease the burden on our judges and raise the quality of justice across the system in Indonesia.

@mul14 @zeddotdev GPU rendering mungkin, coba ghostty pak

Why does the terminal in @zeddotdev feel faster than a standalone terminal app? 🤔