Charli R

[Juan Carlos Rodriguez Romero @JCRodr1]

COT Update | Managed Money (Jun 2)

🌽 #Corn: -91k in 4 weeks. Longs flushed
🌾 #Wheat: flipped to -55k. Shorts back
🌱 #Soybeans: losing conviction.
But soy complex diverges 👇
🍽️ #Meal quietly adding. 🟡 Oil still leads

Not a broad ag rally. Funds rotating within the complex.

[YokerAI @IATheYoker]

Tu profesor tardó 20 años en aprender lo que estos 10 prompts de ChatGPT te enseñan esta tarde.

Copia y pega.

[FarmPolicy @FarmPolicy]

1/ #Soybeans planted in the United States is at 87%, as of May 31, up from 79% last week.

From the @usda_nass: https://t.co/8gt35ZSFoe

[Juan @_almironjuan]

#soybeans crush margin. South America remains strong

[Virginio Gallardo @virginiog]

NotebookLM es una de las herramientas de IA más potentes (y subestimadas) para lo que buscan aprender, para docentes e investigadores.

Transforma PDFs, apuntes, artículos o transcripciones en conocimiento accionable en cuestión de minutos

Infografía
@franpradasAI

[CHS Hedging @hedgeit]

#USDA #Corn #Soybeans #Wheat

[Juan Carlos Rodriguez Romero @JCRodr1]

#COT Update May 12

🌽 #Corn longs pulled back from highs
🌱 #Soybeans eased but funds stay heavily long
🟡 #Soyoil positioning cooled
🍽️ #Soymeal stabilised again
🌾 #Wheat shorts deepened

Funds remain exposed, but less aggressive. 🔄🌦️

[𝐌𝐮𝐬𝐢𝐜 - 𝐌𝐨𝐯𝐢𝐞 - 𝐀𝐧𝐝 𝐌𝐨𝐫𝐞⭐️❤️ @NgocThach74]

Truly a feast for the eyes.🏀

[Juan Pablo Galeano R. @juangaleanorey]

Soluciones simples de IA en la oficina

[Juan Pablo Galeano R. @juangaleanorey]

Guía Completa de Claude
de 0 a 100
👇
https://t.co/x6Lqn8aDge

[Ruben Hassid @rubenhassid]

Most people want AI to sound like them.

But no one does this first (and it takes 47 mins):

Step 1. Download Claude (claude. com/ download)
Open 'Cowork'. Create a folder for your voice.

Step 2. Select Opus 4.7 + Extended Thinking
Set as default model. Turn ON Extended Thinking.

Step 3. Copy-paste the interview prompt
From this guide: https://t.co/LyV7fegv4c
It asks you 100 questions about how you think.

Step 4. Answer every question out loud
Use the Wispr. ai. Talk to yourself. Don't type.
Typing makes you edit. Talking makes you honest.

Step 5. Don't tell what you like. Tell what you reject.
Be extremely precise and specific in your answers.
80% of your file should be what you'd never say.

Step 6. Paste Prompt 2 - The Voice Compiler
20K-word raw file → 2-4K compressed tokens.
Cuts generic. Keeps signal. Most people stop at the raw dump. That's the mistake.

Step 7. Save + test [yourname] .md
Open a blank Claude session.
Paste the file. Ask it to write something.
If it sounds like you → ship it. If not → re-interview.

Step 8. Deploy with Obsidian
Drop the .md in your Cowork folder. It auto-read on every prompt. Edit it like a Google Doc. It syncs automatically, without downloading uploading loop.

The Don'ts:
✦ Skip the 100-question interview
✦ Answer vaguely ("I like clarity" → clarity HOW?)
✦ Stop at the 20K-word raw dump
✦ Use blank chats instead of Cowork folders
✦ Treat the file as static (you change daily)
✦ Think your voice is too "magical" to capture
✦ Forget to document what you'd NEVER write
✦ Blame AI for sounding generic

The Do's:
✦ Always use Cowork - not blank chats
✦ Always turn on Extended Thinking
✦ Always compress with Prompt 2
✦ Always test in a blank session first
✦ Always document refusals, not just preferences
✦ Always edit your .md as your taste shifts
✦ Always push through the full 100 questions
✦ Always start prompts pointing to your folder

You think you're complex to fit in a file. You're not.

47 mins & one .md file to duplicate your brain.

Most people won't sit for 2 hours.
You're not most people.

Full process + prompts: https://t.co/LyV7fegv4c

[Ben Pierron @Ben_escrito]

Si tuviera un fin de semana para dominar Claude, empezaría aquí: https://t.co/nepfUQW21c

Deja de guardar 50 guías que nunca vas a leer. Estas son las únicas que importan:

(algunas guías son del jefe Ruben Hassid)

→ Nivel 1 - 17 min: Lo básico.

Claude For Dummies: https://t.co/jlB6IzTaHs
Claude Setup: https://t.co/f1oUvNtNAP

→ Nivel 2 - 1 hora: Flujos de trabajo reales.

Claude Cowork: https://t.co/7jjWe01ZWl
Claude para equipos: https://t.co/z7LEpf9xjr
Claude Design: https://t.co/GCAe64H6AG
Cowork + Projects: https://t.co/O218wA4Sb7
Claude para presentaciones: https://t.co/4M4gX7XCZY
Claude Skills: https://t.co/JsPA2rybvA

→ Nivel 3 - 3,5 horas: Nivel pro.

Evitar la adulación: https://t.co/iRp6XiQtdR
Claude Code: https://t.co/8KRFXLfJ2f
Claude 101: https://t.co/nMFE3CkP55
Deja de alcanzar los límites de Claude: https://t.co/EUtqndF4Y7
Deja de hacer prompting: https://t.co/hXgc6s1sFi

→ Nivel 6 - 8 horas: Modo experto.

Claude Computer: https://t.co/NrFSyiRC3d
Construir con la API de Claude: https://t.co/S4D13vdRJG

[Bhavesh Arora @bhavesharora02]

✦ EVERY CLAUDE COMMAND ✦
The Complete Reference Guide 🚀

Your go-to cheat sheet for using Anthropic Claude more efficiently.
Save time and get better outputs with the right commands.

1. START & CREATE

• /new → Start a new chat
• /project → Create a project
• /upload → Upload files
• /paste → Paste from clipboard
• /template → Use a template
• /import → Import from file
• /scan → Scan documents
• /voice → Use voice input

2. FOCUS & CONTEXT

• /focus → Set main objective
• /context → Add background
• /details → Provide more details
• /examples → Give examples
• /clarify → Ask follow-up questions
• /define → Define terms
• /assumptions → List assumptions
• /priorities → Set priorities
• /constraints → Set constraints

3. THINK & SOLVE

• /analyze → Break it down
• /compare → Compare options
• /pros-cons → List pros & cons
• /evaluate → Evaluate ideas
• /recommend → Get recommendations
• /brainstorm → Brainstorm ideas
• /solve → Solve the problem
• /challenge → Challenge assumptions

4. WRITE & EDIT

• /write → Generate content
• /edit → Edit for clarity
• /rewrite → Rewrite better
• /shorten → Make it concise
• /expand → Add more detail
• /improve → Improve writing
• /summarize → Summarize text
• /paraphrase → Paraphrase text
• /proofread → Proofread text

5. ORGANIZE & STRUCTURE

• /outline → Create an outline
• /structure → Organize content
• /bullet → Make bullet points
• /numbered → Make numbered list
• /table → Create a table
• /summary → Summarize content
• /key-points → Extract key points
• /mindmap → Create mind map
• /flowchart → Create flowchart

6. CODE & TECH

• /code → Write code
• /debug → Fix issues
• /explain → Explain code
• /optimize → Improve performance
• /refactor → Refactor code
• /test → Write tests
• /convert → Convert formats
• /documentation → Write docs
• /review → Review code

7. DATA & ANALYSIS

• /analyze-data → Analyze data
• /visualize → Create charts
• /insights → Extract insights
• /forecast → Make predictions
• /report → Generate report
• /stats → Calculate statistics
• /clean → Clean data

8. AUTOMATE & INTEGRATE

• /workflow → Create workflow
• /automate → Automate tasks
• /api → Use API
• /integrate → Connect tools
• /schedule → Set reminders
• /trigger → Set triggers
• /tasklist → Create task list
• /checklist → Create checklist

9. PERSONALIZE & CONTROL

• /preferences → Set preferences
• /memory → Manage memory
• /tone → Adjust tone
• /style → Change writing style
• /length → Change length
• /format → Change format
• /reset → Reset conversation
• /clear → Clear context

10. LEARN & RESEARCH

• /search → Search the web
• /research → Deep research
• /learn → Explain a topic
• /tldr → TL;DR summary
• /sources → Find sources
• /fact-check → Fact check
• /explore → Explore topics

11. COLLABORATE & SHARE

• /share → Share conversation
• /export → Export content
• /download → Download file
• /copy → Copy to clipboard
• /email → Email content
• /publish → Publish content
• /feedback → Send feedback

BONUS: POWER SHORTCUTS

• Combine commands for better results
• Add context early for stronger outputs
• Be specific and clear
• Iterate and refine prompts
• Save workflows that work

Most people use AI casually.
Power users build systems around it.

❤️ Like
🔁 Repost
🔖 Bookmark

Follow @bhavesharora02 for more AI content.

[Dhaval Makwana @heyDhavall]

List of 9 websites where you can download unlimited books for free:

1. gutenberg .org
2. standardebooks .org
3. manybooks .net
4. openlibrary .org
5. bookboon .com
6. freecomputerbooks .com
7. internetarchive .org
8. digilibraries .com
9. librivox .org

[Ai With Piyas @piyascode9]

🧵 ChatGPT vs Grok vs Gemini vs Claude vs Perplexity — 5 leading AI tools explained.

Best use cases, strengths & pro tips.
No hype, just practical insights to choose the right tool.

📌 Save this post & read the full thread 👇

[Don Quijote de la IA @IA_Quijote]

Este prompt es mi arma secreta para aprender cualquier tema en minutos.

Hoy lo comparto gratis

[Ruben Hassid @rubenhassid]

Prompting is dead.

Here's what to actually do instead (in one image):

1. Download the Claude desktop app (free).
2. Create a folder names "Claude Cowork".
3. Create 3 subfolders: about-me, output, templates
4. In about-me, create 3 .md files: about-me, anti-ai-writing-style, my-company.
5. Fill them with your tone, rules & non-negotiables.
6. Download my files (for free) here https://t.co/psB7XxAv8w
7. Don't pay anything. Reply to the welcome email.
8. Open Notion link → .md files folder → download.
9. Go to Claude app → Cowork. Select your folder.
10. Go to Settings → Cowork → Global Instructions.
11. Type: "Always read about-me first."
12. Now write 1-line prompt. It already knows you.

By the way, here's the red flags to know you're still prompting like it's 2025:

1. Your prompts are 500 words. Cowork needs 5.
2. You re-upload the files. They auto-load now.
3. "Act as a copywriter…" Stop. Claude needs files.
4. You created Projects. Cowork is one folder
5. No anti-AI file. So Claude sounds like Claude.
6. You re-explain your tone. Put it in a .md once.
7. Your outputs sound generic. Lack of context.
8. You blame Claude. The problem is missing files.
9. You copy prompts. They don't know your voice.
10. You think "prompting" is a skill. It's already over.
11. You never tried Cowork. The biggest feature.
12. You're still in chat. The top 1% are operating.
13. You never read this: https://t.co/LyV7fegv4c

People still type 500-word prompts in 2026.

You want to help your network upgrade?
♻️ Repost this so they finally try Cowork.

[Rahul Bais @rahulbais136]

CLAUDE + YouTube = $$$$.

No degree. No camera. No editing skills.

Even a 15-year-old can do this.

I'm going to show you exactly how.

12 prompts that print money on YouTube 👇

[Elora khatun @elora_khatun]

Stop scrolling.
Your AI learning curve is about to 10x. 🚀

These are the 10 YouTube channels dominating AI in 2026 - from fundamentals → cutting-edge research → real-world builds.

If you’re serious about AI, bookmark this 👇

🎯 Must-follow AI creators:

AI Explained
👉 https://t.co/6TheJp2Mz2…
Breaks down complex AI into simple, visual explanations.

Andrej Karpathy
👉 https://t.co/lrlILFAyDQ…
Ex-Tesla, ex-OpenAI. Deep insights on LLMs, neural nets & the future.

Cole Medin
👉 https://t.co/4oWOCd0gBA
Practical AI trends, tools & breakdowns you can actually use.

DeepLearningAI
👉 https://t.co/xvgELlbLjq…
Structured learning from the best in AI education.

Futurepedia
👉 https://t.co/nNHjXEGHKe…
Stay ahead with the latest AI tools & updates.

Matthew Berman
👉 https://t.co/hq1DD84n25…
AI tutorials, breakdowns & practical use cases.

Skill Leap AI
👉 https://t.co/3oLi3PVdMC…
Hands-on tutorials to level up fast.

Tim Ruscica (Tech With Tim)
👉 https://t.co/D2HWEsGETN…
Coding + AI = real-world skills.

Tina Huang
👉 https://t.co/j1E8JZaLfQ…
From beginner → advanced AI workflows & career advice.

Two Minute Papers
👉 https://t.co/S3V0sKi0SW…
Cutting-edge AI research explained in minutes.

💡 Pro tip:
Don’t just watch - build.

• Pick 1 tutorial
• Ship 1 project/week
• Share your learnings publicly

That’s how you stand out in AI.

AI isn’t slowing down.

The question is: Are you keeping up?

Follow @elora_khatun for more no-fluff AI breakdowns. 🔥

[Nav Toor @heynavtoor]

Researchers at EPFL proved your AI is lying to you.

Not sometimes. Most of the time.

They built one of the hardest hallucination tests ever made with Max Planck Institute. 950 questions. Four domains where being wrong actually hurts. Legal. Medical. Research. Coding.

Then they ran every top model on it.

The results.

GPT-5. Wrong 71.8% of the time.

Claude Opus 4.5. Wrong 60% of the time.

Gemini 3 Pro. Wrong 61.9% of the time.

DeepSeek Reasoner. Wrong 76.8% of the time.

These are the smartest AI models on Earth. The ones you trust with your career. Your health. Your money.

You think turning on web search fixes it.

It doesn't.

Claude Opus 4.5 with web search. Still wrong 30.2% of the time.

GPT-5.2 thinking with web search. Still wrong 38.2% of the time.

The internet attached. Still lying to you in 1 out of every 3 answers.

Now the part that should scare you.

Medical questions. The one place being wrong can kill you.

GPT-5 hallucinated 92.8% of the time on medical guidelines.

Claude Haiku 4.5 hallucinated 95.7% of the time.

Gemini 3 Flash hallucinated 89% of the time.

Nine out of ten medical answers from popular AI models. Wrong.

It gets worse.

The longer you talk to it, the more it lies.

Early mistakes cascade. The model starts citing its own earlier hallucinations as facts. Your third message is more wrong than your first.

The paper, in its own words: "hallucinations remain substantial even with web search."

This is what hundreds of millions of people are doing right now. Asking software that lies in the majority of its answers. About their health. About their job. About their legal case. About their code.

Most are not checking.

Most never will.

But please. Keep using ChatGPT for medical advice.

The doctors need a break.

https://t.co/dHBP5CDpTM