Peb (@CryptoEights) header
Peb (@CryptoEights) profile picture

Building @hyre_agent

Joined October 2010
Photo by Peb (@CryptoEights)Photo by Peb (@CryptoEights)Photo by Peb (@CryptoEights)Photo by Peb (@CryptoEights)Photo by Peb (@CryptoEights)Photo by Peb (@CryptoEights)Photo by Peb (@CryptoEights)Photo by Peb (@CryptoEights)Photo by Peb (@CryptoEights)Photo by Peb (@CryptoEights)
Peb retweeted
“perbaiki sholatmu, maka Allah juga akan perbaiki rejekimu” REAAAALLLL 1000000000000%
123
3,398
44
26,311
284,463
$325K+ of buyback firepower, loaded for $MONTRA. Montra's protocol buys back $MONTRA automatically with 70% of every fee it earns, $28K+ queued right now. $109K+ of treasury HYPE ready to fire. And $MONTRA's own creator fees, 655K kinetiq:native, committed to buy and burn.
82
45
18
342
64,950
Peb retweeted
wow elysium season lasted 1 hour ggwp
50
6
1
206
8,728
GILA SIH, INI GUA BIKIN CUMA DALAM TOTAL 4 JAM, termasuk revisian dari project sebelumnya. And the funny part? GUA LITERALLY 0 SKILL DESIGNER DAN BLENDER. 💀 Cuma modal prompt + AI. Buat kalian yang mau prompt-nya, tonton videonya sampai habis dan komen "DM", nanti gua kirim. PS. Rendering lebih cepat tetap membutuhkan GPU yang mumpuni.
GUA BLENDER AJA GAK BISA, APALAGI DESIGNING. Tapi bisa bikin beginian cuma modal Claude Opus 5.5, prompt, dan GPU sendiri. Total render time cuma 23 menit. Tanpa skill designing, tanpa pengalaman Blender sama sekali. Menurut kalian gimana hasilnya?
79
16
166
6,904
Peb retweeted
NEX+ACT × HYRE. We're an exclusive sponsor of NEX+ACT by WIT Where innovation meets possibility.
8
24
730
Cara bikin bot trading meme Solana pakai AI Agent Setelah gw sharing experimen trading bot yang bisa flip modal 1 jt jadi 8 juta atau 8x banyak yang nanya cara bikinnya. Jadi gw bahas alurnya supaya kalian bisa ngarahin AI agent kalian sendiri. Belum punya ai agent? Tutorial install cek di pin post gw. Trading meme sekarang didominasi bot. Banyak smart wallet beli lalu keluar hanya dalam hitungan menit. Kalo lu masih manual trading cari 10-20%, sering telat exit karna lawan kalian bukan manusia. Gw nggak ngejar 100% ROI atau 10x di setiap token. Profit 10–20% aja sudah cukup asal sistemnya bisa ngulang proses ini berkali-kali. Posisi per trade gw juga kecil tapi per hari bisa 50-80 trade. Modal besar dalam satu token rawan dibegal dev, kecuali tokennya memang punya komunitas kuat dan distribusinya sehat. Ini workflow yang gw pakai: Diskusikan topik2 ini sama agent kalian 1. Trigger Bot nggak perlu scan semua token. Bot cukup nunggu token dari sumber tertentu, lalu masuk ke proses filter. Sumber trigger yang bisa dipakai: - Dex event dari DexScreener - Trending atau hot search GMGN - Hot pool Meteora - Migrasi Pump.fun - Aktivitas kumpulan smart wallet - Call dari channel Telegram - Post dari akun X tertentu (API X berbayar) Diskusikan dengan AI agent kalian sumber mana yang paling cocok. Sebelum build, pantau dulu token-token dari trigger tersebut. Cek berapa banyak yang naik, seberapa cepat naiknya, dan kapan biasanya mulai dump. Buat dulu tools untuk monitoring lebih enak, sebelum nanti kita tau sifat pergerakan harga token dengan filter a b c gimana 2. Filter Setelah menemukan trigger yang sering menghasilkan peluang, bot harus milih token mana yang layak dibeli & mana yang di-skip. Minta agent kalian ngisi semua angka filter di file config supaya gampang diubah tanpa mengutak-atik kode. Data bisa diambil dari Solana Tracker, GMGN, Mobula, atau provider lain mungkin ada lg, pengalaman gw sndiri Mobula masih paling bagus tapi sekarang dia nggak gratis. Bisa pakai solana tracker cuma harus ada gate jika data null, atau 0 wajib di skip (masih kurang akurat sedikit) Contoh data yang masuk filter: - Market cap - Liquidity - Volume - Umur token - Dev holding - Bundler percentage - Sniper percentage - Top 10 holder percentage - Perubahan harga 1 menit dan 5 menit Tambah aja sesuai gaya trade kalian Ini bagian yang paling lama bisa berbulan bulan. Filter terlalu ketat bikin peluang yang masuk terlalu sedikit. Filter terlalu longgar bikin bot rajin entry ke token rugpull. 3. Security check Sebelum entry, bot wajib memeriksa: - Honeypot atau kemungkinan token tidak bisa dijual - Mint authority - Freeze authority - Risiko tambahan dari program token yang dipakai Gagal satu pemeriksaan, langsung skip. 4. Entry Token yang lolos trigger, filter, dan security check baru boleh dibeli lewat API Jupiter. Beberapa batas wajib disimpan di file config trade (jangan hardcoded): - Maksimal jumlah posisi terbuka - Nominal per transaksi - Maksimal slippage - Batas rugi & profit harian (kemaren gw pake nonstop profit sering balik ke market di jam jam tertentu) - Prioritas fee dan batas biaya transaksi Tujuannya supaya transaksi buruk nggak menghabiskan profit 5. Exit rule Setelah entry, sistem harus memantau setiap posisi secara rutin. Interval 2–5 detik masih cukup masuk akal untuk beberapa posisi tanpa terlalu membebani API Jupiter. Sistem exit yang gw pakai: Hard stop loss Kalau harga nyentuh batas rugi, langsung jual. Take profit Kalau target tercapai, ambil profit sesuai konfigurasi. Gw sendiri target 1000%, ga nutup kemungkinan ada yang langsung hard pump, tapi meski ga nyampe 1000% kita masi punya trailing stop Trailing stop Misalnya trailing aktif setelah profit 10% dengan jarak 5%. Kalau harga naik sampai 50%, batas exit ikut naik jadi sekitar 45%. Pas harga berbalik nyentuh batas itu, bot nutup posisi agar profit nggak ikut hilang kebawa turun lagi. Maximum hold time Kalau token sudah terlalu lama dipegang tetapi harganya nggak gerak, keluar dan pindahkan modal ke peluang lain. 6. Dry run wajib Latih bot di dry run selama mungkin. Jangan masuk live trading sebelum strateginya terbukti profit dalam ratusan posisi, bukan hanya profit lima atau sepuluh kali. Catat win rate, realized profit, kerugian terbesar, slippage, biaya transaksi, dan hasil berdasarkan masing-masing trigger. Kalau dry run aja nggak profit, jangan harap hasilnya profit setelah pakai uang asli. Disclaimer: hasil dan workflow yang gue pakai, bukan jaminan hasil untuk orang lain. Bukan financial advice. Crypto berisiko tinggi. Pakai uang yang siap hilang dan tetap DYOR.
Replying to @oezank_idc
cuman butuh how to build nya aja mas, nanti ngulik sendiri, masih bingung langkah nya, ini keman, screening nya gimana, masuk market nya gimana, keluar nya gimana, setidak nya ada clue yang bikin otak ga stuck.
40
122
2
654
27,807
Meta published a paper that might end the transformer era. For the last seven years, every major AI, ChatGPT, Claude, Gemini, has been built on the exact same architecture. Transformer. But Transformers have a massive, expensive flaw. To get smarter, they rely on an endless, brute-force supply of training data. And to remember long contexts, their compute cost explodes. We thought the only way forward was bigger GPUs and endless data centers. But, Meta proved us wrong. They published "Memory Mosaics at scale," and it completely rewrites how AI processes information. Instead of the standard attention mechanism, Meta built a network of associative memories. It works less like a calculator running endless sequence equations, and more like a device storing and selectively retrieving specific key-value pairs. The results are staggering. A Memory Mosaics model trained on just 1 trillion tokens completely outperformed a traditional Transformer trained on 8 trillion tokens. Let that sink in. It beat a model trained on 8x more data. It also demonstrated superior in-context learning and the ability to solve completely new tasks with a fraction of the examples. It naturally disentangles complex problems into smaller, independent sub-tasks automatically.
57
184
33
1,397
111,565
Peb retweeted
29,088 transactions through @PayAINetwork. This is what agentic payments look like in production. Small payments. High frequency. Real usage. From agents discovering tokens on pump.fun to paying for intelligence and inference x402 has been part of HYRE’s rails since day one. Thanks PayAI for powering the settlement layer. 🟩
Merchant Shoutout: @Hyre_agent 🟩 The most-used Hyre workflow is agents finding new tokens on pump.fun. Since April, on x402 through PayAI: 29,088 transactions and $727.07 in volume, per the team. Small payments at high frequency, which is the agent economy in miniature.
23
44
1
131
12,655
IN RANGE SPACE #4 : Trenching or LP-ing?! nitter.gq/i/spaces/1RKZzBeYPOQKB

53
15
6
35
4,894
Peb retweeted
Hyre turn into inference on @solana We are host our own model and everyone can use it through @UsePodAI Homura was downloaded 100K on Hugging Face we see a demand for Uncensored model
Most AI infrastructure is built for humans with credit cards, but @hyre_agent is built for the machine-to-machine economy. Think of it as rails for autonomous agents: inference and onchain data bought one call at a time. No accounts, no gatekeeping, and payment is the only credential you need.
4
6
32
3,071
Peb retweeted
King will be king 👑
Each one a king among kings
1
2
20
1,897
Sebenernya orang indo deploy token gada yg salah kok, asal beneran mau serius build project. Contoh kayak @CryptoEights , berani doxxed dan emang konsisten build. Yang salah itu kebanyakan Indon deploy token, buat x atau beli x yang lokasinya diboongin (non indo), dan gak berani doxxed. Lu buat x lokasi diboongin aja di awal dah niat boong kadal.
10
1
2
62
19,941
Peb retweeted
Everyone's renting models tuned to say no. We built our own and gave it away. 41,000+ downloads later: → HOMURA 30B, uncensored, agent-tuned → Calls tools instead of lecturing you → Open weights, Apache 2.0 → Runs on a Mac. No signup, no gate. Ronin without a master.
2
8
37
2,309
Biggest show I’ve ever hosted. Big thanks Gs ❤️ @notorious_d_e_v @0xSalads @STATIKHEADZ @CryptoEights @Solkingchad @SebastianWols17
Agentic Talks #2: The Stack Behind Agentic Commerce Agentic commerce is more than payments. It takes a full stack to make agents actually transact. This episode, we’re bringing builders from different layers of the @x402 ecosystem into one room: • @PayAINetwork - facilitator • @WURKDOTFUN + @Hyre_agent - merchants • @saidinfra - agent identity and reputation • @OOBEonSol - infrastructure • Xona - discovery Co-hosted: @SebastianWols17 Different layers. One emerging economy. Friday, August 28, 2 PM UTC
6
7
1
33
1,385
Peb retweeted
Stay tuned for today talks with @xona_agent Going to drop alpha if you missed the last one with @PayAINetwork
Agentic Talks #2: The Stack Behind Agentic Commerce Agentic commerce is more than payments. It takes a full stack to make agents actually transact. This episode, we’re bringing builders from different layers of the @x402 ecosystem into one room: • @PayAINetwork - facilitator • @WURKDOTFUN + @Hyre_agent - merchants • @saidinfra - agent identity and reputation • @OOBEonSol - infrastructure • Xona - discovery Co-hosted: @SebastianWols17 Different layers. One emerging economy. Friday, August 28, 2 PM UTC
10
42
2,168
thanks sharing sessionnya bang peb @CryptoEights dapet arahan buat hackaton, dan dapet ilmu baru.. padahal bang peb yang ngajarin, tapi gue yang dikasih fee
5
1
22
1,136
Last month I was paying for four AI tools at the same time. ChatGPT Plus, Claude Pro, some design tool, a writing tool. Somewhere around 100 bucks total, maybe a bit more with tax. This week I canceled three of them. Work didn't really change. Honestly most beginners pay for this stuff because they're scared of missing out, not because the free version actually stopped working for them. If you're still learning, free covers way more than people give it credit for. Take ChatGPT and Claude. Free is fine for brainstorming, drafting, looking stuff up. You don't need Plus or Pro until you're actually hitting the daily cap, and not just once in a while either. Design tools are where people burn the most cash for no real reason. You're learning composition, layout, how to use color properly, none of that needs the paid tier. Pay once you've got real clients asking for higher res files, not before. Writing tools and coding assistants are basically the same story. Free gets you through learning and small projects just fine. It only starts paying for itself once it's actually tied to income somehow. Before I pay for anything now I ask myself three things. Am I hitting the limit every day. Does this thing touch my income in any real way. Have I even used the free version properly for two weeks straight. Two out of three yes and I'll think about it. Out of those four tools, one's still around. The rest went back to free and I honestly didn't notice a difference
2
2
16
1,464
Peb retweeted
Darkbloom is back in action; Yesterday, we went from free tier to paid tier on OpenRouter. We have fulfilled on track close at 4.5B tokens served and $102K ARR. We are open network of Mac machines (250 online right now). On average, people are earning $120-200 per month per machine. If you have a Mac and it's idle most times: put it on Darkbloom(.)dev; Tip: run the Gemma 4 26B model.
169
124
68
2,013
2,684,047
ppl calling deerflow a free 24/7 employee but tbh its more like a runtime that gives an agent its own computer, not just answering back at u from what ive read on the repo, it actually writes files, runs code, works inside an isolated sandbox. not just hooked up to outside tools like usual tho setup looks kinda heavy tbh (docker, env config n stuff), not exactly plug n play if ur curious where "agents that actually work" are headed rn, worth reading into repo dropped in the comments
3
1
5
1,004