Bekti

8.1K posts

Bekti banner
Bekti

Bekti

@bnasima

Esports faithful. Building Ranked, gaming career platform for all gamers. Prev : Garena, Mineski, EVOS. 🇮🇩

Jakarta Capital Region شامل ہوئے Mayıs 2010
910 فالونگ443 فالوورز
Bekti
Bekti@bnasima·
@KaiXCreator Distribution damn hard, but we are on it
English
0
0
0
250
Kaito
Kaito@KaiXCreator·
Has anyone here actually shipped a product you created via vibe coding? How is it going?
English
313
6
284
104.4K
Bekti ری ٹویٹ کیا
@levelsio
@levelsio@levelsio·
I think the challenge is that everyone can now build apps But 1) almost nobody has distribution (like an audience), or 2) the money to pay for distribution (ads or UGC), or 3) the creative genius to get distribution for free (classically called guerilla marketing)
English
141
297
4.3K
763.4K
Mayank
Mayank@Mayank_Msd·
Developers right now: which team are you on? Claude, Codex, or Cursor?
English
68
1
24
4.2K
Bekti
Bekti@bnasima·
@blakebha Kind of losing its edge now with people vibe coding their internal tool
English
0
0
0
11
Blake Ha
Blake Ha@blakebha·
Hey founders! I’d love to connect with more people building in: AI SaaS Future of Work Meeting tools Productivity Communication Drop what you’re working on below! I’ll sign up, try it, and share feedback.
English
151
2
111
5K
Bekti
Bekti@bnasima·
@yukatheoglen gw bang, warnet HQ sama XYZ semarang, empo sm nightmare jkt
Indonesia
0
0
0
72
yukatheo
yukatheo@yukatheoglen·
coba absen di sini siapa yang gedenya di era warung warnet ?
Indonesia
509
42
874
61.2K
Bekti
Bekti@bnasima·
Seru bgt ngulik hermes, kyk bocil nemu mainan baru
Indonesia
0
0
0
14
Bekti
Bekti@bnasima·
@iamlukethedev Yeah automating data entry always improve QoL a lot
English
0
0
1
10
Luke The Dev
Luke The Dev@iamlukethedev·
@bnasima Niceee. That’s a good problem to solve and save some time
English
1
0
0
18
Bekti
Bekti@bnasima·
Hermes really improves my workflow as well, mindblown over how productive i am with Hermes
Luke The Dev@iamlukethedev

After 6 months of OpenClaw, I finally tried Hermes. Three hours later, my Jira agent had already saved me nearly 2 months of engineering time. Teknium, you were right. For the last 6+ months, I’ve been one of the biggest OpenClaw supporters. I built @Claw3DCity on top of it. I shipped countless workflows with it. I genuinely love the project. But over the last few weeks, I kept getting messages: “Have you tried Hermes?” “OpenClaw broke my workflow.” “The latest OpenClaw update broke Codex.” Then Teknium replied to one of my posts. So I finally stopped being stubborn and gave Hermes a real shot. I rebuilt my Jira → Agent → GitHub workflow in Hermes. And honestly… It blew my mind. Not because it could do something OpenClaw couldn’t. But because of how smooth the experience was. While building the workflow, Hermes suggested improvements. It pointed out edge cases. It recommended additional protections. And most importantly: It worked on the first pass. The OpenClaw version took me around 7 hours to get where I wanted it. The Hermes version took about 1 hour. Today alone, the workflow closed 12 Jira tickets in under 3 hours. Work that would’ve likely consumed well over two months of engineering time. That got my attention. A lot. So I’ve made my decision. I’m moving my personal workflows to Hermes. I’ll likely move client workflows as well. That’s not a knock on OpenClaw. OpenClaw inspired a lot of what I’m building today, and I’ll keep following the project closely. But right now, for my use case, Hermes feels like the better fit. Teknium, thank you for pushing me to try it. And thank you for all the support you’ve given Claw3D along the way. Now comes the fun part. Getting Claw3D running even deeper on Hermes. 👀 If you want me to share the full Jira → Hermes → GitHub workflow, comment: HERMES FLOW

English
1
0
4
542
Bekti
Bekti@bnasima·
@iamlukethedev I move data from app to sheets regularly, with hermes it can pull api and write to my sheets, then do daily digest and update on concerning trends, thats just one use case
English
1
0
1
32
Luke The Dev
Luke The Dev@iamlukethedev·
@bnasima That’s awesome to hear. Tell me a little bit of your Workflow
English
1
0
2
303
Yash
Yash@YashHustle_22·
Are you paying for Claude or Codex or both?
English
43
0
19
2.2K
Bekti
Bekti@bnasima·
Kena rate limit di hermes berarti cronjobs gak jalan yah?
Indonesia
0
0
0
13
Wise
Wise@trikcode·
You basically need to be unemployed to keep up with all this AI stuff.
English
624
1K
12.9K
447.3K
Kr$na
Kr$na@krishdotdev·
Which coding model do you think offers the best value for money right now? - GPT-5 Codex - Claude Sonnet 4.6 - Claude Opus 4.8 - Gemini 3.5 Flash - Composer 2.5
English
45
0
34
4K
Bekti
Bekti@bnasima·
@ezash Mantap bang
Indonesia
1
0
1
214
Eza Hazami - ハザミ。エザ
For years I’ve been watching Summer Game Fest as a viewer, and this year I’ll be joining as an Official Co-Streamer 😭 So if you’re planning to stay up late (or wake up early) to watch all the new game announcements, come hang out with me! 📆 June 6, 2026 ⏰ 5 AM (GMT+7) 📺 @ezahazami" target="_blank" rel="nofollow noopener">youtube.com/@ezahazami Besides Persona and other Sega games, what game announcement are you hoping to see this year? 😎☝🏻 @summergamefest #summergamefest
Eza Hazami - ハザミ。エザ tweet media
English
28
16
168
10.5K
Floro S.
Floro S.@sflorimm·
Founders, what do u do when Claude hits limits?
English
103
0
44
8.5K
Bekti
Bekti@bnasima·
Debugging ampe subuh
English
0
0
0
4
Bekti
Bekti@bnasima·
@4thinfected Setuju bang, kaya nuntun bayi, beda bgt sama ngobrol ama orang dewasa kalo sama chat app hahaha
Indonesia
0
0
0
20
Hylexa.
Hylexa.@4thinfected·
@bnasima Yes karena agent itu seperti bayi harus di bimbinng tapi semakin sering di gunain di suapin agent akan tumbuh pinter jadi akan lebih cocok di workflow pribadi
Indonesia
1
0
0
43
Hylexa.
Hylexa.@4thinfected·
Beberapa tips biar agent berkurang halucinate, lebih patuh, dan menetralisir kesalahan. Jujur pasti kalian pernah maki agent 😭 BUKAN GTU ANJ!! atau GB*K BANGETT SIH NGEN*!! Bentak pake capslock + tanda !! Itu cuma bikin agent defensif dan gak bikin agent semakin patuh / kooperaktif. Beberapa yang gw lakuin agar agent lebih decisive dan thoughtful. • Kasih real data atau source. Perintah kosong tanpa data = agent cuma nebak-nebak = rawan halu. • Pakai bahasa Inggris. Karena mayoritas training data m berbahasa Inggris, performanya biasanya naik signifikan. • Jangan langsung kasih perintah tanpa konteks. Karena tanpa konteks = agent bakal bikin asumsi sendiri. • Paksa agent tidak auto setuju ( agent akan lebih mikir kritis dulu ) Agent yang kurang optimal itu bisa jadi kurang data/docs atau koreksi promotnya buat lebih spesifik.
Hylexa. tweet media
Indonesia
3
1
22
960