rodya

-------

[Future Stacked @FutureStacked]

Stanford has just leaked this free class that explains how claude work from the inside

The majority wastes 90% of its potential

Save this to favorites so you don’t lose it​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​.

[Dami-Defi @DamiDefi]

Anthropic engineers don't write longer prompts.

They write fewer, better instructions.

That changes everything.

Most people still treat AI like a search engine. Anthropic treats it like a capable teammate.

Instead of micromanaging every step, they provide intent, define boundaries, require proof, then get out of the way.

The biggest mistake isn't using weak prompts.

It's overprompting.

Every unnecessary instruction increases cost, adds ambiguity, and gives the model more chances to drift.

The best prompts do four things:

• Explain why the task matters.
• Define what success looks like.
• Explicitly state what NOT to do.
• Require evidence before claiming completion.

The future of prompting isn't writing 2,000-token prompts.

It's designing systems where 20 clear words consistently outperform 200 confusing ones.

Prompt engineering is evolving into instruction engineering.

That's where the real edge is.

Watch the video, then read the guide below.

Video cred: Nate Herk | AI Automation (Youtube)

[Khairallah AL-Awady @eng_khairallah1]

this is f*cking gold

Andrej Karpathy joined Anthropic five weeks ago.

A friend on his team just showed me the exact LLM-WIKI.md file he actually uses.

I dropped it into my setup. The very first response was different.

Not slightly different. Completely different.

Claude stopped giving generic answers and started working exactly the way I think.

You don't talk to the model anymore. You build the system that talks to the model for you.

Bookmark it before it gets lost in your feed.

Read it now, then check the article below.

[codila @0xCodila]

Anthropic Engineer Andrej Karpathy:

"AI won't replace you. But the people who use AI to learn - will replace the people who don't "

the Karpathy formula for using AI to learn:

step 1 → AI adapts to what you already know - explains through your analogies

step 2 → AI challenges you at your exact level - not too easy, not too hard

step 3 → AI scales one-on-one tutoring - the thing that makes you beat 98% of people

one tutor. your language. your level. your pace - proven since the 80s - now available to 8 billion

watch - bookmark, then read article below ↓

[Phil Chen @philhchen]

https://t.co/oMoEAYkqGl

[Spicy @spicyofc]

https://t.co/Vk7slNKPFM

[kaize @0x_kaize]

https://t.co/1ieFSwIZsb

[DAN KOE @thedankoe]

https://t.co/9DllJuH2ie

[JDK Analysis 🇪🇺 @The_JDK99]

Want to take better trades and avoid the bad ones?👀
(Don't miss this!)

Let’s talk about how to use OrderFlow as trade confirmation at key levels; 👇

When price reaches a key support or resistance level, most traders already have a bias. OrderFlow shifts your focus away from prediction or hope and toward real-time validation.
Instead of assuming your level will hold, you observe what participants are actually doing the moment price interacts with it. Are aggressive traders able to push price through? Or are they being absorbed?

1) At resistance:

✅ We take the short if…
Aggressive buyers step in (market buys), but price doesn’t push higher → clear absorption by passive sellers (effort ≠ result).
Wait for sellers to respond and trap those longs.
When they exit, their market sells fuel the move down.
→ OrderFlow shows: rising CVD + rising OI while price stalls = bearish absorption

❌ We avoid the short if…
Aggressive sellers pile in at resistance, but price keeps grinding higher or holds strong.
Those shorts are getting absorbed by passive buyers → building fuel for continuation to the upside.
→ OrderFlow shows: falling CVD + rising OI while while price holds below resistance = bullish absorption

2) At support:

✅ We take the long if…
Aggressive sellers step in (market sells), but price doesn’t push lower → clear absorption by passive buyers (effort ≠ result).
Wait for buyers to respond and trap those shorts.
When they exit, their market buys fuel the move up.
→ OrderFlow shows: falling CVD + rising OI while price holds the level = bullish absorption

❌ We avoid the long if…
Aggressive buyers step in at support, but price keeps moving lower or fails to bounce.
Those longs are getting absorbed by passive sellers → building fuel for continuation to the downside.
→ OrderFlow shows: rising CVD + rising OI while price holds weak at support = bearish absorption.

The key principle: effort vs. result.
We don’t need to predict new buyers or sellers entering the market. We focus on what’s already happened -> traders stuck in losing positions 👀
Their exits are predictable market orders we can anticipate, and those market orders often drive the next move.

Using OrderFlow helps you take higher-quality trades at your key levels, and avoid the bad ones.

But always remember; profitability comes from discipline and risk management! Not from better entries.

[Atrades @atrades06s]

Salah satu tools yang paling sering gue pakai:

VWAP (time-based).

Simple, tapi cukup efektif buat ngeliat buyer atau seller yang lagi dominan.

Contoh 👇

[Atrades @atrades06s]

VWAP (Volume Weighted Average Price)

Sebuah thread tentang cara memahami dan menggunakan VWAP dalam trading. 🧵👇

[BOSS @thebeautyofsaas]

the only documentary list you need

[Rahul @sairahul1]

https://t.co/dDQ3VmYZ2P

[Kurnia Bijaksana @mkbijaksana]

Khusus buat pemula

Ini framework dalam menganalisa pasar
Saya jelaskan konsep trending market dan ranging market

Lalu apa itu pullback dan kapan pasar bisa reversal.

Tapi karena rekaman di tradingview dibatasin 15 menit, saya cuma bisa kasih sedikit konsepnya.

Yang lebih lengkap ya saya ajarkan di Bootcamp Evolution Trading Masterclass

Detailnya di komen

[Khairallah AL-Awady @eng_khairallah1]

https://t.co/hnwk3geOZx

[Movez @0xMovez]

https://t.co/OMBzNQETKM

[Yarchi @undefinedKi]

https://t.co/KADozFhjGF

[Anatoli Kopadze @AnatoliKopadze]

https://t.co/eq0oL4fIaR

[Param @ParamSiddh]

Best YouTube Channels To Learn AI in 2026 (No BS). Save it.

1. Fundamentals – 3Blue1Brown
2. Deep Learning – Andrej Karpathy
3. AI Research – Yannic Kilcher
4. Practical AI – AssemblyAI
5. LLMs – AI Explained
6. ML Theory – StatQuest
7. Papers Simplified – Two Minute Papers
8. GenAI – Matthew Berman
9. AI Agents – Nicholas Renotte
10. Applied ML – Krish Naik
11. PyTorch – Aladdin Persson
12. Math for ML – Serrano Academy
13. Industry Insights – Lex Fridman
14. Real-world AI – DeepLearningAI