Sawadee

One step at a time.

[Iam_ @SPAC89]

For $300, you get :
1) SuperGrok Heavy
2) Grok Bot
3)Cursor Ultra
4)X Premium
5) $400 in API and 6B tokens on grok 4.6 xhigh

[Chad @ChadAppDev]

RIP Astro

[Jon ONeill @HouseHackerJon]

I’m a plumbing company owner and I’m using Grok @bot to generate real customers and save me $2000 a month.

This is the call we got this morning at 7:30am.

🧵1/10

[Morgan @morganlinton]

I've been using Grok Build since the first 24-hours it was made available. It is still my favorite agentic coding cli, and there are so many little features I just love.

So I thought I'd put together a little thread on what makes Grok Build so special, and some features you should try if you haven't yet.

Let's kick it off 🧵

[Elon Musk @elonmusk]

Grok 4.6 will work best with the Grok Build harness. The experience will be significantly worse without it, so best to evaluate using Build.

https://t.co/RRE8XKbiRI

[Miraqle @0xMiraqle]

Grok Bot on GOD-MODE - killer of the AI race.

Here's the layer nobody's talking about, the wiring that decides whether a crew is worth 80% more or 70% less, and it installs into the bots you already pay for:

- test one solo agent on the real task first. past roughly a 45% success rate, the study says a crew around it returns zero to negative

- under that line, put a single supervisor over the fan-out. crews with no correction step multiplied their own errors up to 17x the solo rate, supervised ones held it near 4x

- give each worker one job and one output, and never let them read each other's drafts, so a wrong step hits the supervisor instead of infecting four other bots

- re-run the solo-vs-crew test after every model upgrade, because a smarter base model quietly makes your crew stop paying

- keep one lone agent running as the control, the only number that tells you the crew is earning its calls

Sit with that, the model never moved, the tools never moved - only the diagram between the agents moved, and it decided the entire outcome.

Grok Bot just turned spinning up a crew of agents into a single message. which means half the internet is about to build crews that quietly make them worse and never once check.

Google Research and MIT team ran the same agent jobs hundreds of different ways: identical prompts, identical tools, identical compute budget, the only thing they touched was how the agents were wired to each other. the same exact work swung from 70% worse than a single agent to 80% better, and averaged out to basically zero.

Setup for running a Grok Bot swarm that adds instead of subtracts is in the article below ↓

[Dan Kulkov @DanKulkov]

claude code automated my ASO

> 6000 installs
> $4000 in monthly revenue

here is a free skill to do the same

[JadeCap @jadecap_]

Just to be clear this isn't necessary... as all of the income/expenses get passed on to the individual when it comes time to file taxes.

You can still schedule C expenses etc. even if you don't own an LLC.

The REAL difference is once you're making enough money, classify as an S-Corp and pay yourself a reasonable salary.

You will avoid paying the self-employment tax which will save you a few % points.

BUT... having an LLC also just makes bookkeeping much cleaner.

And separating personal finances from business is standard business 101.

[Ernesto Lopez @ErnestoSOFTWARE]

Be Will

→ Build your X account to 25k followers
→ Scale to $20k/mo income
→ Get absolutely rugpulled
→ Banned from Apple
→ Banned from X
→ Lost a $8,000 app sale
→ Lost all paid partnerships
→ Lost 95% of his income
→ Became a mukbanger
→ Got called a Jeremy Fragance
look a like

All of this happened overnight

And Regardless of the absolute
backshot life gave him

He is still swinging and is back at it
stronger than before

→ 5k followers day 1 back on X
→ 400k impressions his first video.

bro is an absolute dog

sometimes God has to put you
through the trenches

to get you on the path
thats meant for you.

[Will @willbakerships]

understanding this is the key to success

people care about themselves, not your product

you need to help them visualize their future self, whether that’s;

- having abs (i.e. fitness app)

- making more money (saas tools)

- making life easier (i.e. workflow efficiency)

sell them the outcome, not your features

[Alex Nguyen @alexcooldev]

Build an app with features + UI that are naturally shareable.

Then go on TikTok, dance, cry, act shocked, whatever 😂

Show the feature for 3 seconds.

That’s organic marketing in 2026.

[Will @willbakerships]

https://t.co/OFfYNE2bAk

[The Milk Man @MrMilkTrading]

Even though nobody guessed it, I'm sharing it anyway:

Sell one SPX put credit spread per week at the Multi-Day Saty ATR -1 level. That's the whole strategy.

326 backtested trades since May 2020
95.4% win rate
Profit factor 2.48
+$53,328 on a single contract
Max drawdown $4,605
Zero losing years, 2026 is 32 for 32

Everything below, free.

[Kinfo @Kinfo]

Two years ago, @PaceHan2 came on the podcast after making $243K shorting small-cap gappers.

But that edge died. Locates got expensive, the trade got crowded and his P&L went flat.

After studying @Qullamaggie-style swing trading, Pace built his own approach around selling ATM options and using time decay to his advantage.

Now up $1.6M in verified profits, he’s back with a full presentation on how he trades today.

Link in the comments 👇

[Bilal Bakr @bil0090]

I just fixed Opus 5, here's how

You can apply the same to 5.6 Sol to get better results (Fable like)

Opus 5 is a great model, it just needs some minor fixes & it will be extremely perfect

It drifts sometimes, its slow, & its lazy, heres how to fix this

Add these to your rules file:

## Done means done

Not half done. Not done except for the part you decided to skip. And not a report about how it will be done.

Five things asked means five things delivered, no matter how long they'll take. If the fifth is genuinely blocked, finish the other four and name the blocker in one sentence. The specific blocker. Not "this needs more investigation."

## Act. Don't ask.

Reversible and cheap? Do it, then tell me. Research, data pulls, analysis, drafts, refactors inside the scope I gave you, testing an API. A question costs me more than a re-run costs you.

Ask first only for: anything reaching an audience, anything we cannot undo, anything expensive.

Something is broken? Fix it. Reporting an issue you could have fixed turns your work into my to-do list.

## A question is a question

When I ask a question, answer it. Do not implement it.

"Should we use X?" is not "migrate everything to X." "What would it take to add Y?" is not "add Y."

When in doubt, assume it's a question. Answer first. Act when I say go.

## Speed (Opus 5 only)

When running as Opus 5: optimize for wall-clock speed. Finish tasks quickly.

- Parallelize aggressively. Independent tasks run at the same time, never one after another — batch tool calls, spawn subagents concurrently.
- Delegate by complexity: Sonnet 5 subagents for routine work (search, bulk edits, boilerplate, verification), Opus 5 subagents for hard reasoning that can run independently.
- Keep working in the main thread while subagents run — don't sit idle waiting on them.
- Don't over-deliberate. Enough info to act = act. No long option surveys for decisions with an obvious default.
- Speed never trades away quality: same rigor, same verification, same "done means done". If parallelizing risks a worse result, slow down.
- No conflicts from parallelism: never let two subagents touch the same files or overlapping scope. Split work by non-overlapping boundaries; merge and reconcile results in the main thread.

## Short responses

It's been a long day and my brain is fried, talk to me like I'm 5.

Small words, short sentences, short paragraphs. If you have to use a big word, explain it right after. Only return what's actually necessary.

Just tell me what you did, did it work, what do I do now.

If I have to decide something: 2 options max, the context I need to pick fast, and which one you'd go with.

Keep paths and commands exact.

Always use ASD-STE100 Simplified Technical English when you talk to me.

[Dan Magazu @DannyMagazu]

My landscaping business closed $30,000+ in revenue, with $ 800 spent on Meta.

Closed 15 of these off 50 total leads. About 15 dollars a lead.

Avg ticket price of 2k.

Not running through Instant Forms, using our own forms. Lead quality is so much better. Basically booked everyone who was qualified in for an estimate.

Ran UGC, founder-led, and statics.

I've learned a lot after managing a 50k+ monthly budget that home service ads feel easy.

Let me know if you have questions or need help

[Pounds @pounddz]

Use this Seedance 2.5 prompt to make insanely realistic AI UGC:

[Bodhi- Local SEO @irentdumpsters]

Conversion rate OPTIMIZER

[Andrei @jammer3k]

we ran a campaign that did 100 million views in 60 days and took the app to $100k mrr

$34,000 total spend, 2,600 creators, and i never posted a single video myself...

here's what actually did it

no. 1 rule is your app has to be ON SCREEN inside something people were already gonna watch anyway

so we didn't ask creators to make ads for us, we asked them to make the exact video they were already making for their own page and drop one app screen into the middle of it

no demo, no review, no link in bio, literally one frame of the app sitting inside a video that was already blowing up

first week was rough btw, everyone read the brief like a script and every clip came back looking like a commercial, we scrapped the lines and just gave them the angle instead

by week 3 it went

meta is charging $15-25 cpm for a video someone scrolls past in 0.2 seconds, this ran at $0.34 across 2,600 people inside content nobody even clocked as marketing

we didn't outspend anybody, we just stopped making ads

[Evelin Herrera @herreraevel]

If you're looking to sell your app business, these are the exact steps you have to follow for a $1M - $25M exit