puertorossi

1.2K posts

puertorossi banner
puertorossi

puertorossi

@puertossaint

شامل ہوئے Ağustos 2025
23 فالونگ5 فالوورز
puertorossi ری ٹویٹ کیا
Maran
Maran@TheMaran·
how you can run minimax m3 model for $0 😳 minimax m3 is 10-20x cheaper than claude opus 4.8 & somewhat performs like opus there's an ongoing event, you can use minimax for free until june 18 what you get for $0: - a model with 1,000,000 context window - a model which beats gpt 5.5 & claude opus 4.7 in benchmarks - a model with strong coding ability how to access the model: - go to the link in the comments - create account with gmail or any available options - create an api key & set a name - copy the api & base url how to use this api & base url: - use on Hermes agent to make your agent a pro coder - use on cursor to vibe code cool stuffs what to build with it: - build something cool for arc - build some tools for you, if you are actually paying for any tools & subscription - you can build anything that makes money for you and others bookmark this post, before you run minimax m3 site link in the comments
Maran tweet media
English
17
12
140
8.3K
puertorossi ری ٹویٹ کیا
How To Prompt
How To Prompt@HowToPrompt__·
Someone open-sourced a tool that takes any username or email and finds every account linked to it across 600+ social networks in seconds. Just one command and it scans every platform, runs free AI profiling to build a full behavioral profile of the target, and exports the whole thing as a clean PDF report. → 600+ sites scanned → free AI profiling included → username OR email lookup → low false positive rate → PDF + CSV exports → runs from one CLI 100% Open Source.
How To Prompt tweet media
English
13
64
406
18K
puertorossi ری ٹویٹ کیا
➳uchiha
➳uchiha@uciuchiha·
Gpt plus Akhirnya bisa juga, cuma Rp 1 Bayar pake GoPay
➳uchiha tweet media
Indonesia
918
100
1.8K
873.5K
puertorossi ری ٹویٹ کیا
KJ || Otw 1 M pertama 💰
KJ || Otw 1 M pertama 💰@1M_pertama·
🚨 HACKS CHATGPT PLUS RP 0 SEBULAN ❌ Ga pake link aneh ❌ Ga pake kode referral ❌ Ga pake akun hasil crack ✅ Fitur resmi dari OpenAI Cuma 10 menit. Pantengin👇⬇️
KJ || Otw 1 M pertama 💰 tweet mediaKJ || Otw 1 M pertama 💰 tweet media
Indonesia
2
10
28
2.4K
puertorossi
puertorossi@puertossaint·
@idextratime bangkenya korsel makin kecium tuh, nyatanya kelakuan sampah mereka ini ke orang terkenal aja gila ya, kalo ke warga indo lebih" gila lagi diskriminasinya. saksi bisu bokap sendiri kerja sama perusahaan korea 20 tahun+, denger ceritanya bikin sakit hati. tunggu gua injek balik🖕
Indonesia
0
0
0
2.6K
Extra Time Indonesia
Extra Time Indonesia@idextratime·
🚨 BREAKING : Hubungan antara timnas Korea Selatan dengan media asal negara mereka tengah memanas setelah adanya insiden audio bocor di sesi latihan, dimana dua jurnalis Korea mengkritik Son Heung-min. Mereka mengejek cara lari Son dan mempertanyakan keringanan pembebasan wajib militer yang ia dapatkan. Son mendapatkan pembebasan khusus setelah memenangkan medali emas di Asian Games 2018 di Indonesia. Ia hanya menjalani pelatihan dasar 3 minggu pada 2020 (seharusnya 18-21 bulan). Respons skuad Korea Selatan langsung terlihat, menolak wawancara. Setelah kemenangan atas Ceko, Son Heung-min mengabaikan seluruh pertanyaan di mixed zone, dan federasi membatalkan wawancara individu yang sebelumnya sudah dijadwalkan. Tim membatasi konferensi pers hanya pada yang wajib dari FIFA. 📝 ESPN | Infobae
Extra Time Indonesia tweet media
Indonesia
525
1.1K
12.5K
988.4K
puertorossi ری ٹویٹ کیا
Techjunkie Aman
Techjunkie Aman@Techjunkie_Aman·
Spotify just got another huge community update. EeveeSpotify Reincarnated v6.6.5 is now available. New in this release: • Spotify 9.1.56 compatibility • Improved LRCLIB lyrics support • Multiple new app icons • Better stability • Ongoing Spotify update support Already included from recent updates: • SponsorBlock • True Shuffle • Custom lyrics • Enhanced ad blocking • CarPlay support • iPad fixes Unlike abandoned projects, this one is actively maintained and updated whenever Spotify changes. The team has already pushed multiple updates in just the last few weeks. Watch the full video for a complete walkthrough and setup guide. What's the first feature you'd enable after installing it?
Techjunkie Aman tweet media
English
9
22
239
16.6K
puertorossi ری ٹویٹ کیا
Vineer
Vineer@vineerpasam·
If AI is so good, then why isn't there a successful startup built entirely on an idea generated by ChatGPT?
English
351
17
513
87.1K
puertorossi ری ٹویٹ کیا
The Boring Marketer
The Boring Marketer@boringmarketer·
if you want Fable level performance NOW, the answer is to build your own coding harness here's how I'm doing it (in a lightweight Pi-native way rather than a heavy Superpowers/Compound clone) first, I think we're going to see PERSONAL HARNESSES that derisk single model reliance, help users save money, and squeeze top frontier performance out of homegrown systems The best engineers I know already do this... 1) Use Pi, the open source coding harness that you can make your own and access any model from 2) Set 5.5 codex as your default model 3) Deeply analyze publicly available system prompts (guess which model I looked at?) 4) Feed Codex context on Loop Engineering and other engineering skill repos 5) As it to improve efficiency as a lot of engineering repos are super heavy and bloated/slow 6) Ask it to use FUSION via Openrouter for planning, logic, and review tasks 7) Ask it to use Kimi k2.7 code for subagents/execution 8) Have it dog food the harness until it's dialed in then unleash it on a repo for a deep analysis
The Boring Marketer tweet media
English
69
91
1.4K
91.3K
Piterlexx
Piterlexx@Lexiiesz·
@ofootball__ anyway, they know they won't go far. cos they definitely can't continue cleaning the stadium up until the finals
Piterlexx tweet media
English
89
1
199
47.9K
World Cup 2026
World Cup 2026@ofootball__·
After the game ended, Japanese fans stayed in the stadium to collect paper and waste. Respect, Japan. 🇯🇵
World Cup 2026 tweet media
English
3.1K
18.5K
140.9K
10.4M
puertorossi ری ٹویٹ کیا
Hugging Models
Hugging Models@HuggingModels·
Gemma 4 12B Coder is here and it's a game changer for local code generation. This GGUF model packs Google's latest gemma-4 architecture into a compact 12B size, perfect for running on consumer hardware. It's optimized for reasoning and thinking, making it ideal for developers who want fast, private coding assistance without the cloud.
Hugging Models tweet media
English
92
465
4.4K
1.5M
puertorossi ری ٹویٹ کیا
Setya Mickala
Setya Mickala@setyamickala·
Indonesia memang negara dengan kedai kopi terbanyak di dunia Ironisnya, meski UMR rata-rata masih di kisaran 3 juta sampai 5,7 juta/bulan (tergantung daerah), kedai kopi hampir selalu penuh setiap hari, di Solo pun yang UMR kecil pun kedai kopi selalu penuh 😹 Salah satu penyebab utamanya adalah Gen Z yang menjadikan ngopi sebagai gaya hidup se hari², dan banyak yang rela menghabiskan Rp. 25.000 sampai Rp. 50.000 per hari hanya untuk kopi. Akibatnya, prioritas menabung kalah, padahal untuk punya rumah sendiri butuh dana yang jauh lebih besar. fenomena ini bikin industri kopi booming, tapi juga bikin banyak anak muda kesulitan secara finansial jangka panjang.
Doritra Aprian@Doritraa

Indonesia jadi negara dengan kedai kopi terbanyak (include warkop sih). Satu poin plus buat industri dan satu poin minus soal persaingannya. Apakah franchise brand kopi masih worth it?

Indonesia
56
14
158
14.4K
puertorossi ری ٹویٹ کیا
azka ✦
azka ✦@agngw_·
"Google AI Pro 1 Tahun" Di timeline kalian sering muncul akun2 jualan ini gak? Biasanya mereka jual di harga 20rb-30rb. Akun saya jg sering posting ini. Bedanya, saya gak mewajibkan utk bayar. Karena apa? Karena aktivasinya pakai bot telegram punya orang. Dan dalam prosesnya harus share password email, ya meskipun bisa kita ubah lagi setelah berhasil aktivasi. Ini yg seller biasanya gak sebutin, padahal penting bgt diinfokan sebelum pembeli bayar. Mereka biasanya cuma nampilin benefitnya.
azka ✦ tweet media
Indonesia
1
3
45
2.9K
puertorossi ری ٹویٹ کیا
Brad Mills 🔑⚡️
Brad Mills 🔑⚡️@bradmillscan·
1 buy a computer with lots of RAM 2 download hermes and set it up with local models 3 create a gateway to talk to it privately from any device 4 use llm-wiki.net to build a wiki (or multiple wikis) with a local reasoning model 5 use gbrain on top of llm-wiki for the memory retrieval layer using local re-ranker way better UX than using ChatGPT or Claude apps.
Mr.Hodldamus@MrHodl

Local LLMs are cool as hell, but they still have one big flaw. When you close the chat, it forgets everything. No memory of your life, your health, your cars, your Bitcoin setup.. nothing. That's why the hosted ones feel smarter. They save all your chats on their servers so they remember you. The missing piece is building real long-term personal memory for local models. Im honestly surprised this hasnt been solved yet. It feels so obvious now.

English
34
157
1.9K
163.2K