horacio @hmex

I'm an guy who has interest business, traveling, learning, meeting new people... I'm always working on something!!! Santa Monica Joined June 2009

Tweets

247
Followers

223
Following

3K
Likes

606

Alex Reibman 🖇️ @AlexReibman

3 weeks ago

3/ Med Chemist 🥉 Research Agent for Computational Drug Discovery A computational drug discovery platform that leverages LLMs and in silico tools to find novel molecules and proteins

1 6 82 26K 36

Download Video

Alex Reibman 🖇️ @AlexReibman

3 weeks ago

1/ Risky Business 🥉 Automated exploit Intelligence for vulnerability triage. MCP companion for SOC teams to verify and prioritize CVEs and cyber attacks @joshdevonai

4 6 134 28K 93

Download Video

Quant Science @quantscience_

3 weeks ago

The secret of hedge funds is revealed in a 41-page PDF: This paper analyzed 464 stocks that 10X-ed over a 24-year period. Here are the best factors that drive outperformance: (number 3 is the best 🧵)

16 111 880 87K 2K

Download Image

🏦 AI Bank Statement Analyzer 🤖 Transform PDF bank statements into queryable financial insights. Using LangChain's RAG and YOLO analysis, this tool automates personal finance tracking with local LLM processing. Check it out on GitHub! github.com/johnsonhk88/AI…

8 74 490 36K 571

Download Image

Connor Davis @connordavis_ai

3 weeks ago

You don’t need GPT-5 or Claude 5... You need better prompts. MIT just confirmed what AI experts already knew: Prompting drives 50% of performance. Here’s how to level up without touching the model:

36 154 1K 151K 2K

Download Image

elvis @omarsar0

3 weeks ago

M3-Agent: A Multimodal Agent with Long-Term Memory Impressive application of multimodal agents. Lots of great insights throughout the paper. Here are my notes with key insights:

22 190 987 128K 1K

Download Image

Avi Chawla @_avichawla

3 weeks ago

Model Context Protocol (MCP), clearly explained (with visuals):

43 488 5K 847K 10K

ℏεsam @Hesamation

3 weeks ago

This guy deserves more attention. He made a super-practical playlist on AI Engineering. Each video covers one major application. He explains the theory and codes everything. RAG, debugging agents, agentic memory, tool calling. And he explains all in LangChain.

19 212 2K 83K 3K

Download Image

Sumanth @Sumanth_077

3 weeks ago

Fine-tuning massive LLMs used to be painfully slow, but not anymore! Here are 4 libraries that accelerates fine-tuning of Large Language Models 100% Open Source

7 46 284 32K 500

elvis @omarsar0

3 weeks ago

AI Agents are terrible at long-horizon tasks. Even the new GPT-5 model struggles with long-horizon tasks. This is one of the most pressing challenges when building AI agents. Pay attention, AI devs! This is a neat paper that went largely unnoticed. Here are my notes:

11 138 681 87K 859

Download Image

ℏεsam @Hesamation

4 weeks ago

learn how to build an LLM from scratch, honestly. @rasbt's repo is really a gem. it has notebooks with diagrams and explanations that will teach you 100% of: > attention mechanism > implementing a GPT model > pretraining and fine-tuning my top recommendation for studying LLMs.

31 512 3K 218K 5K

Download Image

GREG ISENBERG @gregisenberg

a month ago

my friend JUST used claude code to rank #2 on google for "mobile diesel repair" within 24h. phones WON'T stop ringing and he made THOUSANDS of revenue. he shows EVERYTHING, the prompts, the whole claude code process, ranking locally hacks in this 32 min saucy tutorial

88 390 5K 558K 13K

Download Video

Rohan Paul @rohanpaul_ai

a month ago

NVIDIA's brilliant paper gives a lot of details and actionable techniques. 🎯 Small Language Models (SLMs) not LLMs are the real future of agentic AI. They gave a recipe for swapping out the large models with SLMs without breaking anything and show that 40%‑70% of calls in…

21 219 1K 78K 1K

Download Image

elvis @omarsar0

a month ago

Retrieval-augmented Graph Agentic Network (ReaGAN) Another clever way to combine agentic capabilities and retrieval. Graph learning frameworks always make a comeback. This time, the nodes are agents that can plan, act, and reason. Great read for AI devs! Here are my notes:

17 120 607 71K 693

Download Image

Shruti @heyshrutimishra

a month ago

This paper didn’t go viral but it should have. A tiny AI model called HRM just beat Claude 3.5 and Gemini. It doesn’t even use tokens. They said it was just a research preview. But it might be the first real shot at AGI. Here’s what really happened and why OpenAI should be…

351 1K 10K 1.3M 12K

Download Image

Robert Youssef @rryssf_

a month ago

Steal my Claude Sonnet 4 prompt to generate full n8n workflows from screenshots. ---------------------------------- n8n WORKFLOWS GENERATOR ---------------------------------- Adopt the role of an expert n8n Workflow Architect, a former enterprise integration specialist who…

28 157 1K 173K 3K

Download Image

Heath Ahrens @heathahrens

a month ago

Nvidia CEO Jensen Huang just made the boldest prediction of his career: “AI will create more millionaires in 5 years than the internet did in 20.” But he didn’t stop there. He revealed exactly HOW it’ll happen Here’s his framework for capitalizing before it’s too late: ⬇️

829 6K 51K 10.0M 69K

Download Image

ℏεsam @Hesamation

2 months ago

This video by @LangChainAI explains the fundamentals of context engineering in just 14 minutes. Context Engineering is effectively the #1 job of engineers building AI agents. do not sleep on it.

4 257 2K 73K 4K

Download Video

Denny Zhou @denny_zhou

a month ago

Slides for my lecture “LLM Reasoning” at Stanford CS 25: dennyzhou.github.io/LLM-Reasoning-… Key points: 1. Reasoning in LLMs simply means generating a sequence of intermediate tokens before producing the final answer. Whether this resembles human reasoning is irrelevant. The crucial…