Neo🐸

Previously dealing with WACCs, now I only care about WAPs

[zerohedge @zerohedge]

Confessions Of A Newsletter Writing Market "Permabear" https://t.co/W5Kos7f8JH

[kiosa @thegreatest_sv]

THIS IS ACTUAL F*CKING GOLD

Anthropic employee leaked a Claude Code kit to stop it wasting expensive AI on easy jobs.

It's called jev-kit.

You know when Claude sends a powerful model to find a file or look something up?

This kit checks whether a cheaper agent could handle it.

Claude writes the code. JEV checks which jobs need the expensive help.

here's how it works:

> one tier too expensive? suggest a cheaper agent
> two or more tiers too expensive? block it in enforce mode and suggest the cheaper option
> agent says "done" without checking its work? send it back to verify
> tool call looks questionable? check it before it runs

The point is simple.

> Keep the powerful models for difficult work. Stop spending their time on basic searches and small decisions.

There's also an optional browser agent:

> JEV chooses what to click
> Claude writes the text that goes into fields
> a Sonnet planner can help when the steps aren't obvious

So instead of asking a big model to think through every click, you give it the parts that need actual writing and planning.

How much does it save?

There's no proven percentage for the whole kit. That depends on your tasks and which agents you're using.

But it gives you a way to spot expensive dispatches and test cheaper alternatives in your own workflow.

Start in shadow mode. It logs what it would flag without blocking anything.

Look at the results. Then decide what to enforce.

You'll need a TypeSafe API key for JEV.

paste this into Claude Code:

"Inspect https://t.co/K9iwgn5Qsa and read docs/install.md.

Run install/install.sh --check-only and show me the plan.

Explain how it could reduce expensive subagent use in my workflow and check whether it supports my current setup.

Show every settings change first. Keep shadow mode enabled.

Tell me where to enter my TYPESAFE_API_KEY locally, outside this chat.

No installation or changes until I approve."

https://t.co/1mnVQdzqlW

Your best model shouldn't spend its day looking for files.

[Sweex @sweexx9]

🚨¡BOMBAZO! El ingeniero que creó Claude Code desde cero acaba de soltar un video de 28 minutos que es puro oro:

cómo escribir prompts que realmente entregan resultados brutales.

He visto cursos de 300 dólares que no llegan ni a la suela de lo que él explica en los primeros 10 minutos.

Archivos CLAUDE.md, atajos de memoria, sesiones paralelas y patrones de prompting que casi nadie usa…

Todo en un solo video. Completamente gratis. Sin relleno.

Da igual si eres desarrollador, estás empezando o ya llevas meses con Claude: esto te cambia el juego desde hoy.

Guárdalo. Míralo. Compártelo.

[Khairallah AL-Awady @eng_khairallah1]

Don't waste 2 years learning to build LLMs like Claude & ChatGPT.

Thariq Shihipar shows you exactly how to build AI agents from scratch.

• 00:00 - AI agent harness
• 23:44 - building AI agent loops
• 56:39 - AI agent context engineering
• 1:33:34 - AI agent deterministic hooks
• 1:50:31 - Anthropic SWE interview process

I watched it last night.

Halfway through, I realized I could break into an AI lab in months, not years.

Bookmark this & give 2 hours today, no matter what. Then read the article below.

[Alex Moore @heyalexmoore]

🚨 Claude just changed the game.

All you need is:

💻 A laptop
🌐 Internet connection
⏰ 60 minutes a day

That’s enough to build a $7,200/month online income stream using AI.

No coding.
No expensive setup.
No years of experience.

Most people still use AI for fun…

But smart creators are quietly using Claude to:

• Create digital products
• Offer AI services
• Write viral content
• Automate work
• Build online income streams

Usually, I sell this detailed guide for $97…

But today you can get it FREE. 🎁

Inside you'll discover:

✅ The exact asset
✅ My full workflow
✅ The Claude prompts I personally use
✅ How to scale to $10K/month
✅ How beginners can start fast

Want it?

❤️ Like this post
💬 Comment “AI”
➕ Follow me to receive it in DM

⏳ Available FREE for 48 hours only.

[Rahul @sairahul1]

Google just dropped a 1-hour course on agentic engineering from scratch:

00:00 – How to build your first AI agent
08:24 – Build agent memory (short, persistent, long)
28:34 – Agentic loops, long-running AI agents
40:04 – How to build MCP (MCP vs API)
1:00:22 – Multi-agentic systems

This 1-hour watch will replace 10 paid agentic courses on the internet.

Bookmark this. Watch this weekend.

[Lorden @lorden_eth]

You can make $10k per month

All you need is Higgs field + $20 Claude subscription

If you’re a 17y/old smart kid, you can call every local business in your area

Tell them you can build a new website for just $500

You can build it in fvcking minutes with AI

All you need is one prompt:

“Act as a world-class web agency and build a production-ready website with Claude and Higgsfield”

[Anatoli Kopadze @AnatoliKopadze]

Anthropic engineer:

"Fable 5 is already smarter than we know how to use. The bottleneck was never the AI, it's you."

In 19 minutes he shows exactly how to get everything out of Claude with no extra tools, no extra costs.

You're already paying for all of this, just not using it.

Watch the session, then read the guide below on the Claude features 99% of users never find.

[Khusboo Tayal @KhusbooT14835]

Claude FULL COURSE 1 HOUR (Build & Automate Anything)

[Rohit @heyrohitai]

🚨Anthropic just showed a 24-minute workshop on how to actually do prompts for Claude.

Taught by the people who built it.

Free. No registration. No paywall.

I've seen $300 courses that don't cover what they teach in the first 8 minutes.

Watch it and bookmark it now!

[Anatoli Kopadze @AnatoliKopadze]

Godfather of AI: "If you sleep well tonight, you may not have understood this lecture."

This 47-minute lecture is the best thing I've seen about AI in the last few months.

Hinton built the neural networks behind every AI alive, then quit Google to warn us it's already ahead of us on most cognitive tasks.

Despite that, most people open Claude, type one thing, close the tab and think they're using AI, but they're using maybe 10%.

I turned his talk into 17 Claude features 99% of users never find.

Watch the lecture, then read the article below.

[Khairallah AL-Awady @eng_khairallah1]

this is f*cking gold

How to build your first AI agent (Full guide)

if I had this a year ago, I would've shipped my first agent in a day instead of 2 weeks

in the right hands, this changes everything:

[Neo🐸 @Neobadu29]

@SoulzBTC yes

[Polymath Investor @polymathinvest1]

A few months back, I published this guide on how to remember everything you read.
Re-sharing it here for anyone who finds these protocols useful.

(1/11)

[Entrepreneurs on X @entreprneursonx]

During this period, he read "Autobiography of a Yogi," a book he would reread every year for the rest of his life.

It introduced him to prajna, or transcendent wisdom, proving that a sharp gut instinct is far more powerful than pure logic.

[power of books @Powerofbooks3]

5 books that will increase your Intelligence in 2026📖📚

1. Mastery

[self.dll @seelffff]

> be me
> get into one of the best universities in russia. for free.
> study machine learning and applied mathematics
> somehow also work as an ML engineer at the same time
> spend the leftover hours building AI agents that run your life
> go to the gym. because apparently that's also on the schedule.
> start a twitter page. just to see what happens.
> 6,000 people show up.

still a student.
already building.

[Philanthrop @0xPhilanthrop]

An Anthropic team lead emailed me. From a corporate address. I thought it was a scam.

"Your Polymarket wallet is on page 14 of our internal research deck"

A screenshot. My wallet. Inside a slide labeled "external validation - top 0.1% exit structure"

Their model flagged me. Not a human. Claude 4.7 picked my wallet out of 12,000 during training.

"You exit before the volume spike. Every single time. We couldn't replicate that in our sandbox until 4.7"

He asked me to switch to Opus 4.7 and post my results publicly.

"I need proof this works in the wild. Not in our evals. No one trusts benchmarks anymore"

I switched in 20 minutes. Didn't touch a single prompt.

First 48 hours. 11 trades. 10 green. The one red lost $40. The greens made $3,200.

"Your old model captured 68% of the move. 4.7 captures 89%. That's not tuning. That's a different brain"

https://t.co/50cCWaENhi

https://t.co/o9vQvDKtwe

Same repos his team benchmarks against. Open source. Full stack.

I asked why Anthropic cares about one random trader.

"Because your live wallet is better proof than any paper we could publish"

187 trades since the switch. 80% hit. Sharpe sitting at 3.04.

Breakdown by category:

Crypto: +$7,400
Politics: +$5,100
Weather derivatives: +$3,500
Macro: +$2,300

Total: +$18,300 from $200 seed. 31 days.

Copytrade https://t.co/UlvSrUzZGN

He asked me not to share the slides.

I didn't. But I'm sharing everything else.