Instead of another YouTube rabbit hole tonight.
Take these 11 courses to master Claude (for free):
→ Level 1 - 20 mins: The basics.
Claude certificates: https://t.co/Vn60ElPrcK
Claude For Dummies: https://t.co/HNa5MrCe6m
AI is (stupidly) simple: https://t.co/SVGd966GXi
Claude Roadmap: https://t.co/NG73kDCvth
→ Level 2 - 55 mins: Real workflows.
Claude Cowork: https://t.co/uWTpOI3oyE
Claude for teams: https://t.co/qxlcqheAme
Claude for slides: https://t.co/L0bPMgWEsy
Claude Skills: https://t.co/6cHYYfjpP2
→ Level 3 - 45 mins: The pro moves.
Claude Connectors: https://t.co/TSAQqOp5pn
Stop hitting Claude's limits: https://t.co/j5fEzSGxlT
Upload yourself in Claude: https://t.co/kDGBpSEA6J
Stop using Claude at work: https://t.co/c6X55Th0gV
Pro tip: Don't binge it. Do one level per sitting.
Actually apply each guide before moving to the next
gila sih ini, beneran ngerusak pasar open-source AI lagi
buat klen semua yang lagi belajar AI, atau suka ngotak-ngatik AI tapi mentok di device or cost, wajib banget tau ini.
qwen baru aja rilis qwen 3.5 small series. intinya mereka ngeluarin model-model kecil dari ukuran 0.8B sampe 9B yang enteng banget tapi kemampuannya oke banget. slogannya aja "more intelligence, less compute".
beberapa poin yg mnarik:
- model 9B punya performa ngeri, bahkan bisa ngalahin model 120B+
- udah native multimodal, jadi emang didesain buat paham teks, gambar, sama video.
- ramah banget buat device lokal. yang 9B bisa running di mac ram 6gb doang. yang ukuran 0.8B malah bisa jalan di smartphone.
semuanya full open-source pake lisensi apache 2.0, jadi bebas buat eksperimen.
ini bener-bener ngebuka peluang buat kita bikin ai agent sendiri tanpa perlu pusing mikirin cost server gede.
ada yang udah nyobain ini?
iPhone lo dicopet?
Lo bisa tau MUKA pencurinya + LOKASI dia sekarang.
Tanpa app tambahan dan bukan dari Find My. Langsung ke HP lo.
Gue setup ini di iPhone gue. Cuma 5 menit.
Sekarang gue ga takut kalo iPhone gue bakal kemalingan.
Gini caranya:
Microsoft killed the GPU mafia 🤯
They finally open-sourced their 1-bit LLM inference framework called bitnet.cpp. It lets you run 100B parameter models on your local CPU without GPUs.
- 6.17x faster inference
- 82.2% less energy on CPUs
100% Open Source.
Beta Release Buku AI SMP SMA di
https://t.co/LgkpuxQ3UA
folder BUKU-AI-SMP-SMA-beta-release
https://t.co/kHMaoEzZzk
Isinya baru buku SMP Kelas 7 Semester 1 & 2 ... yang lain masih dalam proses penyelesaian ...