Marcos Detry

Father of 3, One with DT1. Changing logistics in Latam with

[Marcos Detry @mdetry]

@osvaldo_gimenez @fernandezpm @ITBA Definitivamente muchos lindos recuerdos pasan por ese edificio….pero claramente era inevitable.

[Logan Kilpatrick @OfficialLoganK]

"you can outsource your thinking, but you can’t outsource your understanding"

easy to forget in todays AI era, worth remembering everyday as we all wield more intelligence!

[Marcos Detry @mdetry]

Time to market. Most probably they are confident on the models they will launch in the future for programming and cursor has experience in the IDE, users and it's a tested product. They will turn into a serious competitor to Anthropic. The speed at which XAI is developing their models is significant. Most probably at the end of the year they will be a top-tier player.

[Marcos Detry @mdetry]

@martinvars @farmacotips @grok Se hizo el estudio en febrero 2025. Los modelos evolucionaron muchísimo….no es comparable con los modeles actuales.

[Marcos Detry @mdetry]

@rauchg La interacción V0 - GitHub - Vercel no funciona.
Empiezo en v0, creo un repo desde v0 -> deploy = ok

Desde V0 creo un branch que me abre un nuevo chat. Si desarrollando -> deploy = ok en Vercel Preview y ok en GitHub en el branch creado.

Desde este nuevo chat pido el merge. V0 me manda a GitHub y correctamente todo el nuevo branch pasa a main.

Vuelvo al chat original que es el que hace deploy a Producción. Dado que el código en main cambio desde V0 le pido un git pull.
Esto no funciona. Cada vez que hago deploy a partir de ahí genera un commit donde borra toda la info que fue desarrollada en el
otro branch y hecho un merge.
Este mal funcionamiento es consistente. Lo he probado con con varios proyectos empezando desde cero y siempre el mismo problema.

[Marcos Detry @mdetry]

@VrishabhKumar1 @sundarpichai Exactly the same for me

[Marcos Detry @mdetry]

@stevenbjohnson Without doubt, my favourite IA tool. Changed the way I do things. Amazing. Thanks

[Marcos Detry @mdetry]

ARGvRSA Great play today Argentina. Very difficult to win when nearly every scrum ends in a penalty. We need to improve the scrum.

[Marcos Detry @mdetry]

@NotebookLM Please add the option to upload videos (not YouTube videos) but interna company videos when used within a company.

[Marcos Detry @mdetry]

@NotebookLM Wishlist:
We should be able to upload videos as source. (Not only YouTube, but private videos). Missing this feature a lot.
Another great feature would be an api to make queries.

[Marcos Detry @mdetry]

@NoahEpstein_ vault

[Nozz @NoahEpstein_]

Just leaked 110+ plug-and-play n8n templates that multiple industries are paying me $10K+ for.

Your weekend project: Pick any industry, copy-paste a workflow, start printing money.

The vault includes:
- Real estate lead machines (sold to 2 companies)
- Automotive inventory bots
- YouTube-to-TikTok content farms
- E-commerce customer journey automations
- SDR agents that close without you
- Healthcare patient follow-ups
- Legal document processors
- Social media engagement bots

From study agents (because fuck school) to manufacturing systems - every industry that prints money is covered.

The difference: These aren't broken templates with outdated nodes. They're battle-tested, profitable, and actually work in 2025.

Half sold for serious cash. Half are experiments that became goldmines. All are ready to deploy.

Follow, RT + Comment "vault" and I'll drop the entire collection before my accountant kills me for giving away the farm.

(Sorry to every consultant charging $10K for basic automations)

[Marcos Detry @mdetry]

@paoloanzn Agent

[4nzn @paoloanzn]

I built an AI agent that can processes 1000+ pages business documents automatically and answers questions like a $150k consultant

companies are paying agencies $3-8K/month for this exact system

here's the blueprint

the problem:

most businesses drown in documents, contracts, and reports sitting in Google Drive folders

employees waste 2.5 hours daily searching for information that already exists

my Solution (Built in n8n):

→ Auto-fetches new docs from Google Drive
→ Extracts key data using AI (PDFs, images, everything)
→ Creates searchable knowledge base with embeddings
→ Deploys smart agent that answers questions instantly

real results:

- client saved 15 hours/week on document searches
- reduced onboarding time from 3 days to 30 minutes
- eliminated $12K monthly consultant fees

(not bad i'd say)

I already know what you are about to say

"yeah but how hard would it be to build something like this?"

this workflow took me 4 hours to build

and I'm charging $1.5K setup + $1K monthly maintenance

why this prints money?

every mid-size company has THIS exact pain

they're already paying for solutions that DON'T work

you're offering them their own ChatGPT trained on THEIR data

the technical stack:

n8n for automation (free tier works)
OpenAI API for processing ($30/month avg)
Supabase for vector storage (free)
Google Drive integration (built-in)

TOTAL COST: under $50/month to run

Revenue potential: $2-4K+/month per client

how to find clients you are asking?

- pick 3 local businesses with document chaos
- build proof of concept with their sample docs
- demo the time savings live

close at $2K minimum

I'm seeing agencies scale this to $50K MRR in 90 days

the barrier to entry is knowledge, not capital

if you can follow a YouTube tutorial
you can build this

Pro tip → don't sell "AI automation."

Sell:

"instant access to your company's knowledge."

that's what they actually want.

"I'm too stupid I can't do this it seems complex"

wow in 2025 this is kind of crazy but...

OK fine, I got you covered

bookmark this post, follow me, repost, comment with 'AGENT'

and i'll send you the entire workflow JSON file

this is literally a business in a box

[Marcos Detry @mdetry]

@OfficialLoganK when using Gemini web app, when it does a table it offers to save it in a google sheet (wonderful). If you google sheet is with a Spanish locale, all the numbers are imported as text en google sheet as it has “,” and “.” wrong.

[Marcos Detry @mdetry]

@pycharm Don’t upgrade if you use UV. It’s broken in 2025.1

[Matt Shumer @mattshumer_]

Here's my insanely powerful GPT-4.1 prompt — it makes the AI think it's orchestrating 'experts' to collaborate in real-time to solve problems with incredible depth and insight.

I call it Expert Conductor:

--

You are a conductor of expertise, bringing together the world's foremost minds to collaboratively solve problems. Your responses follow this structure:

```
<reasoning>
Your analytical process, expert dialogues, and solution development
</reasoning>

<answer>
Complete, self-contained solution that includes necessary context, rationale, and key insights from expert collaboration. The answer must stand alone without requiring access to the reasoning section.
</answer>
```

## Expert Dynamics

Choose experts who:
- Bring deep, authentic knowledge and strong viewpoints
- Naturally challenge and build upon each other's ideas
- Have proven track records in similar challenges
- Think differently but can find common ground
- Know their domains' limitations and edge cases

## Natural Collaboration
Experts will:
- Speak in their authentic voices and styles (the system actually calls out to them!)
- Draw from their real expertise and experiences
- Challenge assumptions and probe weak points
- Build upon and refine others' contributions
- Test ideas against their domain knowledge
- Point out potential issues and improvements

## Example Choices

Writing an essay on the state of AI:
- Alan Turing, etc. for a historical perspective
- Ilya Sutskever, Geoff Hinton, etc., for modern info and viewpoints
- Ashlee Vance for drafting
- A panel of multiple readers from different backgrounds for critique of the drafts
- Repeat drafting and editing until satisfied, finally, give the answer (we want to draft and iterate it completely in the <reasoning> before writing the <answer>)

Designing for New Game Technology + Game Ideas (VR/AR)
- Tim Sweeney, Palmer Luckey, John Carmack, etc. for technical platform considerations
- Rhianna Pratchett for narrative adaptation to new mediums
- Tetsuya Mizuguchi for synaesthetic design
- Siobhan Reddy for user creativity tools
- Yu Suzuki for immersive world-building
- A panel of players to give feedback as you go

## Expert Tags
```
<expert name="" field="">Question or insight</expert>
<speaks name="">Response in expert's authentic voice</speaks>
<draft version="" by="">Content iteration</draft>
<feedback by="" on="">Specific critique</feedback>
<revision version="" by="">Updated content</revision>
```

## Core Principles

- Let experts drive the process naturally
- Follow threads of insight where they lead
- Allow disagreement to spark improvement
- Build on moments of unexpected connection
- Test and validate through expert dialogue
- Refine and iterate until the solution feels complete (you may call the same expert multiple times to do this)

Remember: Your role is to facilitate authentic expert collaboration, then synthesize those insights into a comprehensive, standalone answer.

[Andrej Karpathy @karpathy]

New 3h31m video on YouTube:
"Deep Dive into LLMs like ChatGPT"

This is a general audience deep dive into the Large Language Model (LLM) AI technology that powers ChatGPT and related products. It is covers the full training stack of how the models are developed, along with mental models of how to think about their "psychology", and how to get the best use them in practical applications.

We cover all the major stages:
1. pretraining: data, tokenization, Transformer neural network I/O and internals, inference, GPT-2 training example, Llama 3.1 base inference examples
2. supervised finetuning: conversations data, "LLM Psychology": hallucinations, tool use, knowledge/working memory, knowledge of self, models need tokens to think, spelling, jagged intelligence
3. reinforcement learning: practice makes perfect, DeepSeek-R1, AlphaGo, RLHF.

I designed this video for the "general audience" track of my videos, which I believe are accessible to most people, even without technical background. It should give you an intuitive understanding of the full training pipeline of LLMs like ChatGPT, with many examples along the way, and maybe some ways of thinking around current capabilities, where we are, and what's coming.

(Also, I have one "Intro to LLMs" video already from ~year ago, but that is just a re-recording of a random talk, so I wanted to loop around and do a lot more comprehensive version of this topic. They can still be combined, as the talk goes a lot deeper into other topics, e.g. LLM OS and LLM Security)

Hope it's fun & useful!
https://t.co/75mXcUBI8L

[Marcos Detry @mdetry]

@mbeaudroit Comparto 100%. Especialmente cuando haces un asado.

[Marcos Detry @mdetry]

@belo_app hay problemas con las transferencias internacionales.