Jack 10 Stocks

Long-term investor. Just do it. KISS fan

[Jah Mills @itsjahmills]

this app marketing is GENIUS 😭
it’s so smooth no one realizes it’s an ad

it’s an extremely simple story time
that shows the results after using the app

not the features or UI
but instead just the end result

no wonder it makes $50k/month

they’re spamming the same format
if they keep it up

they’ll be at $100k/month in no time

[Chase @0xChaseTM]

https://t.co/ZWVF63tPPn

[Simone Canc @simonecanciello]

https://t.co/Qb66mjGpnM

[Codez @0xCodez]

Anthropic Managed Agents team:

"Fable 5 is our best model for running self-improving agent systems.

Add /loops, dynamic workflows, dreaming and you are unstoppable"

in 13-minutes, Anthropic team shows how to build self-improving agent systems with Fable 5 from scratch.

Worth more than a $500 agent building course.

Live from the last Anthropic stage in Japan. Unpublished.

[Sidney Brant @Byysid]

This is how I get results like this for apps

[rody @0x_rody]

At Anthropic's event, Metaview engineer:

"We stopped fixing our prompts. The system reviews its own output and rewrites its own instructions now."

In 16 minutes, he shows the Claude Code loop running in production on thousands of reviews, not in a demo.

Watch the talk, then grab the full loop setup below👇

[Shann³ @shannholmberg]

how to build agent profiles in Hermes Agent

what is a profile? its essentially a dedicated agent with its own configuration, skills, memory and model

if you have multiple agent profiles they can start to work together. thats how you create an agent company

you can manage these agents one to one, via an orchestrator agent or directly via a Kanban board

I do a mix of all of the above in my day to day. I work with the orchestrator to access my company brain, delegate work to other agents, and prototype new workflows

I talk directly to specialist agent profiles to create agents that are dedicated towards one vertical of work. they have unique skills and tools to accomplish the goals I throw at them

you have two choices in creating a new agent profile. you can either chat to your default agent and go back and forth creating the profile, or now Nous released a way in the Hermes dashboard where you can set up profiles and everything that goes with it

a bonus 3rd way is to use my agent control room (find it in the link below)

[Shann³ @shannholmberg]

agent loops in coding vs marketing

an agent loop is simple. the agent does something, checks the result, keeps what works, reverts what doesn't, and repeats until the work is good enough

the whole thing depends on one question: what can the loop use to check its own work? coding and marketing answer that very differently, and it changes how you build

some loops optimize against a score, others improve through judgment. thats the whole difference.

a coding loop usually has a hard signal to push against:

> tests pass
> build passes
> typecheck passes
> benchmark improves
> the bug is gone

the environment tells the agent when it is wrong. it tries something, measures, keeps the win, reverts the loss, and runs again. green means done.

marketing loops dont get that. most marketing work has no clean score at the moment its made.

a weak landing page still loads, a generic email still sends, a bland post still publishes, a misleading comparison page can still rank, a bad ad still spends money. nothing in the environment stops it.

so a marketing loop needs judgment before it needs more autonomy. not just draft, revise, post.

it needs gates that act like tests, but for the things a compiler can never check:

> truth: are the claims true and checked against sources
> proof: is the evidence strong enough to back the claim
> specificity: is this concrete, or vague filler
> voice: does it actually sound like us
> positioning: is it on message, not off in the weeds
> offer fit: does it match what we actually sell
> audience fit: will the buyer care about this
> differentiation: does it stand out, or is it generic
> taste: is it genuinely good, not just finished
> timing: is now the right moment to ship it
> do nothing: is the original already better, leave it alone

a coding loop can end at "tests passed". a marketing loop should end at "this is worth a human decision".

thats the part most AI marketing agents miss. they copy the motion of coding loops without the verification layer, so they produce more work, faster, with less taste.

[Avi Chawla @_avichawla]

I cut Fable 5 token usage 2.5x with just one change!

- Before: 5.5 M tokens · 7 errors · $8.94
- After: 2.3 M tokens · 0 errors · $4.17

The final build was the same for both, but the path the agent took wildly differed.

In both runs, the agent started with the same thing, i.e., it understood the backend before building anything, like:

- Permission policies
- Available storage buckets
- Auth providers configured
- How edge functions are deployed

The first run used Firebase, which was built for a human dev using a dashboard.

While the dev can read the above state by clicking through tabs, an agent has no dashboard. So it gathered the same info through API calls.

And there's no single Firebase call that returned this info. The agent required to query multiple times, and each query over-returned.

For instance, when the agent asked how sign-in is configured, Firebase also returned the entire auth surface and every method it supported.

This was far more context than what it needed. And it repeated across every part of the backend it inspected.

Some states (like which auth providers are active) weren't queryable at all. I provided it myself. Otherwise, the agent would have guessed.

Errors further compounded the token usage.

When a dev sees "permission denied," they can look at the console and figure out whether it's a rule, a path, or an unauthenticated request.

Firebase returned the same string to the agent as well, and it had none of that surrounding context to debug.

So it guessed again, picked the most likely cause, and rewrote code, utilizing more tokens.

This Firebase setup cost me 5.5M tokens and 7 manual interventions during errors on a full-stack RAG app.

But I brought that down to 2.3M tokens and 0 manual interventions by using InsForge as the backend context engineering layer (open-source and self-hostable via Docker).

It provides the same primitives as Supabase/Firebase, but structures the entire information layer for agents, instead of dashboards.

In one CLI call that consumed ~500 tokens, the agent saw the full backend topology before writing a single line of code.

This included auth, database, storage, edge functions, model gateway, micro VMs, and deployment.

Also, instead of loading the entire product surface into context on every task, four narrowly scoped skills activated only when relevant to keep cognitive load minimal.

And to ensure efficient retries if needed, every CLI operation returned structured JSON with meaningful exit codes, so the agent never guessed what to do next.

Here's the InsForge GitHub Repo: https://t.co/MFjGiErHMP

(don't forget to star it ⭐)

The video below depicts the final build, comparing Firebase and InsForge.

To dive deeper, I recently published a full walkthrough building the same RAG app on both backends and inspected them end-to-end.

Read it below.

[CyrilXBT @cyrilXBT]

https://t.co/SUO2CVOkCf

[wandermist @wandermist]

267 TOKENS PER SECOND ON A SINGLE RTX 5080

this is ollama running llama 3.2 1b and it’s not even a large model but the speed is the whole point

two years ago getting 30 tokens per second on consumer hardware felt like a win and now a single gpu is doing nearly 10x that

the gap between local and cloud is closing faster than anyone expected and the article below breaks down exactly which tools and hardware get you there in 2026 ↓

[Adrian Solarz @adriansolarzz]

https://t.co/vn7MS4Iqxh

[Adrià Martinez @adriamatz]

Stop overthinking your marketing

Try this instead 👇

Slide 1: a hook
Slide 2: a photo of your app

That's the format pulling 40M view slideshows

One indie hacker hit 700K users solo doing only this

You can replicate it at scale

Full playbook in the article

[Spike 1% @SpikeCalls]

One person rebuilt an entire company’s brain in 7 days inside Claude Code.

Not a doc. Not Obsidian. A living galaxy of nodes.

Every employee. Every AI agent. Every SOP. Every tool. All wired together on one screen.

Click a department. The human agent team opens up. The SOPs attached to it open up. What each person is allowed to touch opens up.

That last part is the whole game.

Permissions baked into the brain. An employee opens the chat, the AI already knows what they can access. Agents, data, SOPs surface inside the conversation like you tagged them by hand.

Obsidian can’t do this. Notion can’t do this.

No dev team. No funding round. No 6-month roadmap. 7 days, 1 person, 1 terminal.

This is the part nobody has priced in.

The tools to build $200K enterprise software now sit on your laptop for free.

The only thing missing is the guy who opens the terminal.

[Chrome @0xchromium]

Andrej Karpathy spent 2h showing how he actually uses AI day to day

he's a co-founder of OpenAI and led AI at Tesla, so when he shows how he works, it’s worth watching

and the whole session is just him telling the machine what he wants in simple terms, like he's briefing a coworker

watch what's actually happening the entire time:

> he describes the task in normal words
> it goes off and does the work
> he glances at the result and nudges it with one more sentence

that's the whole skill, and you've had it since you learned to talk

the only gap between that and a worker that runs on its own is handing that sentence a schedule and the tools to act

check his work, then build the version that keeps working when you stop

[Khairallah AL-Awady @eng_khairallah1]

Anthropic engineer:

"You're not supposed to prompt Claude. You're supposed to build a system that prompts itself."

this is one of the best workflows I've seen in a long time

in this video he breaks down exactly how most people are using Claude:

- the 14% you lose to CLAUDE.md before typing a word
- the plugins that 95% of users have never installed
- the caching setup that keeps it at 95% hit rate and almost free
- why starting every chat from zero is the slowest way to use Claude

if you've been using Claude for more than a month and never left the chat window, you've been using one project when you could be running a team of them

instead of another show tonight, watch this

make sure to bookmark it before it gets lost in your feed

full guide in the article below

[Jah Mills @itsjahmills]

this app founder is a genius 😭
the app is at $153K/mo, launched 4 mo ago

that video alone at 13.9 M views
made a couple thousand minimum

they’re scaling super fast with UGC
and got over 100+ organic creators currently

the apps demo is STUPID clear
3k+ ppl asking for the app name

[Jah Mills @itsjahmills]

it took us 3 weeks to get 500k+ views
with a fully AI UGC on instagram

and it taught me something huge

if you create good content for long enough
the algorithm is very simple

it works to keep finding the type of user that engaged with your post

similar to paid ads

but this only works if you stay within niche
and post consistently great content

so stop seeing 1,000-4000 views as bad
it’s simply taking the time to learn

we’re being extremely aggressive with our marketing

and created 40+ content variations each
A/B testing a different part of the video

- hook, music, transitions, wallpapers, workout, location, CTA, captions

every single component is being tested

we had a huge set back with Meta randomly
banning 8 of our accounts last week

we got the content ready and aim to post
20x per day minimum by 6/10

each day breaking down the data
and creating more of what works

then running it on paid ads both
tiktok spark ads and meta ads

marketing is definitely takes more time
but at least shipping took just 2 weeks

using Rork Max + Opus 4.7

at the time i launched, there was no other possible way to natively code in SwiftUI

[Adrian Solarz @adriansolarzz]

https://t.co/CRcbFUggPv

[TadasG 💻 @tadasgedgaudas]

Easy money if you’re not trying to be the Steve Jobs

- go to https://t.co/PznJQ6yE05
- view Rising apps tab
- copy an app which is growing fast and $100k mrr+
- spam 100 tiktoks/month
- write personal thank you letters to Jacob

thank you