Z U K A (@Zukaaaexe) header
Z U K A (@Zukaaaexe) profile picture

🕯️ Whispering through charts & chains. Crypto · Web3 · Forex enthusiast.

Joined February 2024
Photo by Z U K A (@Zukaaaexe)Photo by Z U K A (@Zukaaaexe)Photo by Z U K A (@Zukaaaexe)Photo by Z U K A (@Zukaaaexe)Photo by Z U K A (@Zukaaaexe)Photo by Z U K A (@Zukaaaexe)Photo by Z U K A (@Zukaaaexe)Photo by Z U K A (@Zukaaaexe)Photo by Z U K A (@Zukaaaexe)Photo by Z U K A (@Zukaaaexe)
di web3, aku liat orang tuh upgrade terus tiap hari. lah aku perasaan masih di sini2 aja
78
My current AI stack 1. @OpenBot_ I replaced GrokBot with OpenBot 2 weeks ago - best decision I've made in months. After the whole usage issue a few weeks ago, I knew I couldn't rely on Grok anymore. I didn't want to end up in a situation where I have shit to do, and Grok rugpulls me with the usage or replaces it with an idiotic model to save on costs. I tried out a few and Openbot's my fav. It runs on my Claude subscription, so I'm always on a frontier model instead of whatever GrokBot picks under the hood. And my usage issues are gone. OpenBot runs locally on my Mac mini. Even though people view OpenBot as a GrokBot replacement - it's starting to add new features which makes it even better imo. threaded conversation, agent docks, library, etc. 2. Claude: $200/mo Ultra plan My main model. I use Opus 5.5 day to day and switch to Fable 5.2 for the hardest problems. No explanation needed, Claude's simply the best. 3. ChatGPT: $20/mo I mainly use it for image generation and whenever I want a second opinion. 4. GrokBot: $30/mo The one thing I can't replace is Grok's native X integration for research. So I run GrokBot as a bot inside OpenBot: • My OpenBot agent sends my message to GrokBot over a webhook. • Grok does the work and drops its answer into a shared folder on my Mac mini. • My agent reads it back to me. So, it feels like chatting with any other bot. 5. OpenRouter: pay as you go One account and one API key give me pay-as-you-go access to the models I don't subscribe to, like Gemini, Qwen, Kimi and Grok. They mostly power my Mixture of Agents skill, and my agent switches each one to its newest version every week. Say you're making a huge decision. Ask Claude and you get one answer. But what if you could get several perspectives from different AI models and end up with the best version? a. Fast mode: Claude writes one version and ChatGPT writes another, without seeing each other's. Gemini grades both and picks the winner. Then my agent writes the final version from the winner, adding the best points from the runner-up. b. Full mode: Claude, ChatGPT, Gemini, Qwen, Kimi and Grok each write their own answer, and so does my agent. They grade each other's work blind, never their own. A model that didn't write the top answer turns it into the final version. Then Grok, whose job is to disagree, tears it apart before I see it. Fast takes a few minutes and costs cents. Full takes about half an hour and a few dollars, so I save it for the big calls. Everything's moving so fast so it'll probably end up looking different next year. Anyways I spent a lot of time testing diff things out and reached a setup I'm very happy with.
37
13
3
260
34,370
9
1,087
47
3,948
65,246
Z U K A retweeted
Bisa tidur nyenyak saat malam dan pas bangun seger banget itu sebuah anugerah yg harus disyukuri.
242
5,159
222
24,295
347,625
Sore hari ini gua nemu satu hal yang menurut gua cukup berharga Pake @lpagent_io gua bisa belajar dari smartwallet LP secara onchain, yang mana di layar sini winratenya cukup besar. Langkah pertamanya gimana bang ?. Langkah pertama masuk ke sini : app.lpagent.io/smart-lp
7
5
1
57
2,712
Z U K A retweeted
mau nanya dong buat yang sering pecut agent kalian kalau memory agent penuh di reset atau di simpan dalam bentuk repo, soalnya device gw udah banyak memorynya dan salah satu cara bikin repo buat otak agent gw ada yang kayak gini kah?
10
5
50
4,030
right on time.
2
274
2
2,292
30,191
fakkkk
Everyone is talking about GTA 6, while I’m thinking about my portfolio.
8
A man's mind, 24/7.
2
64
2
253
6,938
Z U K A retweeted
January. November
61
5,051
174
25,485
361,365
rame movement hermes to openbot di timeline, asli relate bgt anjir. hermes gw sndiri ampe berdebu gr-gr openbot wkwk. laptop jd daily driver, tau-tau streak 12 hari nembus 124M token. gokil bat eksekusi lokalnya. ada yg server hermes-nya jd pajangan jg? akwkaowk @OpenBot_
1
49
Z U K A retweeted
maybe i died of covid in 2020 & this is hell
230
9,118
356
48,409
1,032,932
Z U K A retweeted
Right now, I need Your miracle, Lord. It has been a long time since I had a spark.
59
2,654
149
12,785
275,512
life of a nigga trying to win
291
9,297
334
60,427
1,736,051
Z U K A retweeted
Mihao.
98
3,599
55
21,736
241,183
wkwk anjengg, akun tele, ig, sma X ini kena untung balik semua X yg paling susah karena nunggu 2hari balesan sma CS X BTW GOOD JOB DAH, 2 HARI ITU URUSAN GW GAMPANG GA KAYA CS LAIN CACICU @X
hal yang tidak pernah dirasakan user os minoritas
34
nitip ah, barang x wkwkw
emang bisa kayak gini yah
254
Top 15 Skills for Hermes Agent, ranked by GitHub stars. ⭐ Coding, memory, research, design + more: 1. Superpowers github.com/obra/superpowers 2. Anthropic Skills github.com/anthropics/skills 3. UI UX Pro Max github.com/nextlevelbuilder/… 4. Graphify github.com/Graphify-Labs/gra… 5. Claude-Mem github.com/thedotmack/claude… 6. Archify github.com/tt-a1i/archify 7. Last30Days github.com/mvanhorn/last30da… 8. OpenMontage github.com/calesthio/OpenMon… 9. Humanizer github.com/blader/humanizer 10. i-have-adhd github.com/ayghri/i-have-adh… 11. Marketing Skills github.com/coreyhaines31/mar… 12. Planning With Files github.com/OthmanAdi/plannin… 13. SkillSpector github.com/NVIDIA/SkillSpect… 14. Skill Seekers github.com/yusufkaraaslan/Sk… 15. BrowserAct Skills github.com/browser-act/skill…
57
329
14
2,488
175,168
Z U K A retweeted
i will win. i deserve to win.
33
291
18
1,422
15,129
Z U K A retweeted
Never fucking quit. Your entire life can change before the end of the year.
84
937
27
13,209
184,063