Jorge Davison @jdavisonc

Problem solver by nature, Cutting-Edge Technology Lover. All opinions are my own. Montevideo, UY Joined April 2010

Tweets

6K
Followers

273
Following

1K
Likes

5K

VraserX e/acc @VraserX

3 weeks ago

AI is weird. One moment it’s hallucinating pizza recipes, the next it’s generating an entire operating system from scratch. We’ve built the most powerful tool in history and it still acts like a toddler with superpowers.

17 5 82 2K 4

Tomas @tomasholtz_

3 weeks ago

Si usan claude code o cursor para codear, agréguenle el mcp de @Context7AI. Busca la documentación del repo que necesite usando rag y se lo devuelve al llm en markdown, mucho mejor que pedirle al modelo que haga web search. Desde que lo uso dejo de alucinar, usar métodos que…

10 54 675 37K 941

Download Image

@levelsio @levelsio

4 weeks ago

Embrace being a crud monkey

@levelsio @levelsio

4 weeks ago

Embrace being a crud monkey https://t.co/YjMfjONuAE

175 160 4K 1.5M 3K

Download Image

131 399 4K 501K 2K

Download Video

Brendan Jowett @jowettbrendan

2 months ago

BREAKING: AWS just solved the biggest AI agent bottleneck. No more custom glue code. No more M×N tool chaos. No more protocol headaches. Introducing: Amazon Bedrock AgentCore Gateway Here's how it works:

60 186 1K 313K 2K

Download Image

ℏεsam @Hesamation

2 months ago

“A fresh college grad on top of AI can outperform a full-stack engineer with 10 yrs of experience that is still doing things as they were back in 2022.” @AndrewYNg explains perfectly why we need more programmers, not less.

27 285 2K 132K 1K

Download Video

DHH @dhh

2 months ago

You have all the time you need, you're just spending it poorly. Don't tell me you don't have time for Linux or kids OR BOTH. You have time for all of it once you stop filling your day with junk activities.

120 227 3K 156K 943

Download Video

Jorge Davison @jdavisonc

2 months ago

Six Principles for Production AI Agents app.build/blog/six-princ…

0 0 0 6 0

Akshay 🚀 @akshay_pachaar

3 months ago

Finally! A Text-to-SQL tool that actually works! Vanna is an open-source RAG framework for complex Text-to-SQL generation. It manages dynamic data and allows custom RAG model training for greater accuracy. 100% open-source.

22 191 1K 98K 2K

Download Video

Eduardo Mangarelli @emangare

3 months ago

Sobre el reciente research de METR sobre productividad de devs con herramientas de IA/LLMs/Dev Agents. El estudio analiza el impacto en la productividad de devs experimentados en proyectos OSS, y generó múltiples reacciones, reflexiones y cuestionamientos👇

1 2 3 736 3

Download Image

Alejo @ecommartinez

4 months ago

OpenAI, Google y Anthropic acaban de publicar las guías sobre: - Ingeniería de prompts - Creación de agentes efectivos - IA en los negocios - 601 casos de uso de IA y mucho más... Las 9 mejores guías que no te puedes perder:

15 312 2K 122K 3K

Download Image

Programmer Humor @PR0GRAMMERHUM0R

4 months ago

jumpingONmemeTrend redd.it/1kvzs4o

1 25 321 17K 20

Download Image

JetBrains @jetbrains

5 months ago

🤗 Mellum is now open source on @huggingface! It’s a focal model that is small, efficient, and made for one thing: code completion. ⚙️ Trained from scratch by JetBrains. 🌱 First in a growing family of dev-focused LLMs. 🔗 jb.gg/Mellum_XOS

14 167 1K 388K 419

Download Video

AshutoshShrivastava @ai_for_success

5 months ago

LMAO 😂 Vibe-coding is fun until you have to debug it without a clue.

96 103 1K 545K 130

Download Image

Lior Alexander @LiorOnAI

5 months ago

Must watch. Anthropic's released an hour long deep dive on prompt engineering. Covers: ▸ What makes a good prompt ▸ Handling ambiguity, reasoning paths, and edge cases ▸ Enterprise vs research prompting strategies ▸ Using personas, metaphors, and structured logic ▸…

13 96 933 67K 2K

Download Video

Santiago @svpino

5 months ago

MCP is mind-blowing. Here is a genius setup that will earn you a promotion with your manager. I have multiple data sources: data in S3, MySQL, and local files. Using Spice (an open-source project), I can co-locate all of that data behind a single SQL endpoint and augment it…

40 205 2K 142K 4K

Download Video

Akshay 🚀 @akshay_pachaar

5 months ago

INCREDIBLE!!! Gemini did 6 hours of manual data analysis work in just 2 mins. Gemini in a Colab notebook now lets you plan, analyze, and visualize your data. I used a dataset of 100k rows and didn't write or execute a single line of code. Completely hands-off!

40 295 2K 258K 3K

Download Video

Sundar Pichai @sundarpichai

5 months ago

Just announced new versions of Gemma 3 – the most capable model to run just one H100 GPU – can now run on just one *desktop* GPU! Our Quantization-Aware Training (QAT) method drastically brings down memory use while maintaining high quality. Excited to make Gemma 3 even more…

168 497 5K 545K 1K

Download Image

ℏεsam @Hesamation

5 months ago

MCP vs function calling visually explained:

47 435 4K 481K 5K

Download Image

Jo Kristian Bergum @jobergum

5 months ago

Billions worth of system prompts are exposed in a single repo. The scale of IP leaks is remarkable in the LLM era.

241 1K 18K 2.3M 25K

Download Image

Pierre Bongrand @bongrandp

6 months ago

For the very first time OpenAI released a model right after Google and they are way behind No one needs a not-so-smart model (GPT-4.1 mini), nor an overpriced dumb one (GPT-4.1) You either want a super smart model, or the best cheap model. Gemini 2.5 Pro or Gemini 2.0 Flash