Я родился мальчиком в сельской местности ДР Конго, в одной из самых бедных семей.
Мне довелось увидеть 9 внуков и 15 правнуков.
После выхода на пенсию меня не стало в 78 лет от болезни Альцгеймера или другой деменции.
#1из8миллиардов https://t.co/sq3HOTA3BH
ESTO ES UNA MINA DE ORO
Anthropic ha publicado +400 agentes y skills listos para usar en casi cualquier tarea:
→ https://t.co/wS5zUp2UCP (158k estrellas)
Unos 170 agentes organizados como una empresa: ingeniería, diseño, marketing, ventas, producto, testing, seguridad y soporte.
Con packs adicionales para finanzas, salud y desarrollo de videojuegos.
Compatible con más de 15 herramientas.
→ https://t.co/Sq06TTjnjT (40k estrellas)
202 agentes, 184 skills y 105 comandos repartidos en 94 plugins para Claude Code.
Especialistas en lenguajes de programación, revisión de código, depuración, infraestructura, seguridad y testing.
Instala solo los plugins que necesites.
→ https://t.co/bxPVYAgagZ (26k estrellas)
Los plugins del propio Anthropic, organizados por áreas de trabajo: ventas, atención al cliente, gestión de producto, marketing, legal, finanzas y datos.
→ https://t.co/W6Z5VPlR2p (18k estrellas)
Agentes oficiales que puedes poner en marcha: un resumen diario de Slack y GitHub, clasificación programada de incidencias de Sentry, bots para Slack y Linear, un agente de atención al cliente y un analista de datos financieros.
→ https://t.co/IOtiSh372n (103k estrellas)
De ingenieros de Anthropic.
25 skills que cubren todo el ciclo de desarrollo: interview-me, redacción de especificaciones, desarrollo guiado por tests, pruebas en navegador, revisión de seguridad e integración y despliegue continuos
Yo empezaría por claude-quickstarts.
Cada agente es un ejemplo completo y funcional que puedes ejecutar y desmontar para entender cómo funciona.
Aprovecha estos recursos oficiales gratuitos para tus próximos proyectos👇
SpaceXAI just released a free 55-minute workshop on Grok Bot
In this session, Grok Bot engineer walks through the whole trust curve:
01:35 - the real question isn't speed, it's how do you trust it
04:01 - her agents auto-merge PRs now, 20 landed overnight and she read them on main
18:58 - a coordinator agent writes the rubric and spawns its own sub agents
43:16 - GrokBot's onboarding lets each bot choose its own working directory
54:48 - designers and PMs on the team now ship features directly
Nobody shows the boring middle
Five months ago she couldn't trust a single agent near the codebase
The leash was never the model
It's how much of the loop you're willing to give up
More Grok Bots won't help if you still approve every merge yourself
Save this before you spin up your next Grok Bot
@elonmusk@bot По братски, увеличьте лимиты, а то прошло всего 4 дня и у меня работа колом встала, потому что грокбот лег отдыхать до конца рабочей недели
I made an Open Source version of the Grok Bot complete with all the features
It does not need any subscriptions at all and uses the existing subscriptions you already have
It can spin up virtual machines from @asciidotdev
It uses @trycua for computer use
It also has plugin support supporting all the integrations by @composio
Routines coming soon :D
Link to the repo in the comments
i'm f**king done with Grok Bots waking up 8,640 times a month just to find nothing changed...
one routine running every 5 minutes costs roughly $397/month at Grok 4.6 API rates. run it hourly and that drops to $33. same bot, same job, 12x the estimated cost.
so here's how i'd structure a 6-bot crew that actually makes sense overnight.
[the setup looks like this]
1. chief routes events, not noise
2. scout checks what actually changed
3. quant compares the last saved state
4. risk returns PASS / CUT / KILL
5. exec handles safe, approved actions
6. scribe logs every run and queues drafts
the trick isn't making 6 bots work harder. it's stopping them from waking up for nothing.
add a cheap change check before every full run and my cost model drops from $397 to $45 (-89%).
anything risky at 3 a.m. stays a draft until you're awake.
that's the Grok Bot setup i'd actually trust overnight.
full breakdown in the article below ↓
SpaceXAI hired this engineer at $750K-$1.2M a year because she knows how to build a company that runs on bots, not people
She shipped 2,500 PRs last month. 83 a day. Zero written by hand
In this 54-minute livestream, her team builds one from scratch: empty GitHub, zero bots, 72 hours
Prompt → Bot → Skills → Team of Bots → Company
step 1 → one bot per job, not one chat per task - each bot owns an outcome, you stop babysitting prompts
step 2 → move it to the cloud - every bot gets its own computer, the 2 a.m. run fires with your laptop closed
step 3 → teach it once - show the task on its screen, it's saved as a skill forever, 90% less re-explaining
step 4 → put the bots in one group chat - they message each other, wait on dependencies and unblock themselves
step 5 → set approval rules, then let go - 2,500 PRs a month merge while she sleeps, you review after it lands
SpaceXAI calls this "a persona, not a task"
Most people still open a new chat for every task
You don't have to
Bookmark and watch it
Then read how to build your first Grok Bot team in the article below ↓
SpaceXAI engineer Lauren Tan:
"99% of people use only a fraction of GrokBot's potential
They run one agent without loops or graphs
I run an autonomous team of 20+ GrokBot agents - a Chief of Staff, a PM, and specialized workers
That’s the new engineering stack"
GrokBot → Chief of Staff → PM → Specialized Workers → Autonomous Agent Team
In a 50-minute workshop, Lauren shows how to build a powerful agent team from scratch
Single Agent → Loops → Graphs → Autonomous Fleet
Worth more than most $1,500 agentic engineering courses
Bookmark and watch it today
Then learn how to build your own GrokBot fleet
PUMP OR DUMP, MY GROK BOT DOESN’T CARE. $54 → $5,874 IN 22 HOURS
The biggest take of the run was a short. The second biggest was a long.
Most people decide in the morning whether they’re bullish or bearish, then spend the day defending it. My bot doesn’t have a side to defend. Market sliding, it shorts. Market bouncing, it longs.
I asked Grok to build a perps bot for BTC, ETH, SOL, AVAX and SUI, one that trades both ways and never holds a position on feelings. This is the logic it came back with:
- Every entry has its take-profit calculated before it opens, no “let’s see where it goes”
- Picks the side off the move: dump means short, bounce means long
- Sizes off the current balance, not the starting deposit
- Matches leverage to the coin and to the distance to target
- Cuts a loser fast and never averages down
That second rule is the whole personality of the thing. A red hour and a green hour are both just setups.
The five big takes split three shorts, two longs. The SOL short paid the most, $1,617, and the BTC long came next with $677. Every one of them cleared 100% on margin.
What keeps it alive is the ratio. The average win was about 4% of the balance, the average loss about 0.8%. Five to one. 181 trades, 36 of them red, and on the equity curve you can barely find the dips.
The small trades actually out-earned the big takes, $3,143 to $2,677.
The leverage here is my own desk’s sizing, not a signal. Don’t copy it.
Hour 22. $5,874 on the account, and the bot still has no opinion on where the market goes next. It just needs it to go somewhere.
SpaceXAI just showed how to build 24/7 GrokBot agent team:
"if you use GrokBot, it`s already their computer, not yours"
Grok Bot is built around persistent agents:
• its own computer
• its own memory
• its own tools
GrokBot doesn't need you to start the work
GrokBot can work, use its computer and keep going while you're away
→ you shouldn't operate the agent
→ you should delegate to it
worth more than 100 videos on building agents
save now, then read how to build a 24/7 GrokBot agent team in the article below
SpaceXAI engineer Josh Kim:
"I don't want to talk to any other bots. I only want to talk to you."
He put one PM GrokBot in charge of 5 specialized agents and delegated the entire marketing campaign to it.
Research → positioning → landing page → Google Ads → analysis → launch
Then the PM bot studied the whole workflow and started 3 new campaigns on its own.
In 44 min, he goes from one prompt to an AI marketing team that researches, builds, ships and coordinates itself.
By the end, the landing page is live in production.
This makes most $500 "AI marketing automation" courses look obsolete.
Watch how 6 GrokBot agents become a marketing team - then copy the full agent stack below ↓
UN CHINO FILTRÓ LA FORMA MÁS FÁCIL DE HACER DINERO
y acaba de publicar gratis lo que otros estan cobrando $300
se llama AutoClip. le pegas el link de un vídeo y te devuelve los cortes ya montados, con título viral incluido, sin tocar el ratón.
esto es lo que hace solo:
→ descarga el vídeo y los subtítulos
→ lee la transcripción entera y saca el guion
→ detecta dónde empieza y acaba cada tema
→ puntúa cada trozo del 1 al 10
→ corta solo los que valen la pena
→ le pone título a cada uno
→ agrupa los que van juntos en un pack
siete pasos. tú solo pegas el link.
un podcast de 2 horas se convierte en 15 cortes verticales listos para subir. tiktok, shorts, reels y x, los cuatro pagan por views.
interfaz web con progreso en tiempo real. funciona con youtube, bilibili o archivo local: docker-compose up -d y listo.
6.300 estrellas, 1.200 forks, licencia MIT.
resultado: lo que antes costaba 300 dólares por vídeo ahora es gratis y corre en tu propia máquina.
esto cambia el juego para cualquiera que viva de cortar contenido largo.
repo y más info en comentarios 👇🏻
Asked Grok Bot to watch the Grok Bot Galaxy livestream with me and take notes for me 😂
It’s literally following the livestream in real time, pulling out the interesting parts, grabbing screenshots and keeping track of what I actually care about
Basically I have a Grok Bot watching Grok Bot....so I don’t miss anything
Grok Bot just replaced entire team of engineers
This free 1-hour workshop shows how you can build a codebase agents can be trusted in:
04:53 - you are the bottleneck, you sit watching every single agent output
07:44 - the most important skill is verification
12:14 - feature map teaches agents how to navigate your entire UI
20:01 - evals are unit tests for your agents
37:19 - 600 PRs of refactor later, she no longer looks at the code
46:50 - the shortest path is the best path, built for the dumbest agent
Most people feed their agents one task at a time
You can build a pipeline that merges its own PRs overnight
Skills → evals → guardrails → zero review
This free workshop teaches more than most $500 agent courses
Save it before your codebase becomes unreadable