🇨🇴🗳️ 25 corruption scandals so far in Petro's government. Cepeda still at 30%+. The entire Colombian opposition still doesn't get it. 🐾
A new Petro corruption scandal broke today.
@NoticiasCaracol revealed that Colombia's intelligence chief held secret meetings with the lawyer of the country's top smuggling kingpin, offering him judicial benefits he had no authority to grant. etc etc etc The opposition will spend a week on this. It won't move a single vote. Here's why. 🧵"
"EL" curso! Anthropic's Promt Engineering course, completo y gratis.
Denle amor 🧡
https://t.co/i7VjcQoGHb
Protip:
Tambien esta en este Google Sheets usando Anthropic's Claude for Sheets extension.
https://t.co/oLzvZnxVHk
#Anthropic#prompt
Anthropic released a free interactive course on prompt engineering, an essential skill for everyone.
> how to structure a good prompt
> avoiding common pitfalls
> making a killer prompt library
> 80/20 rules and addressing them
It has 9 step-by-step chapters with exercises.
La buscar del prósito!
Cómo las experiencias de liderazgo empático y la comunicación efectiva pueden transformar tus proyectos y relaciones personales.
#Saludmental
Cada vez se conversa más sobre propósito, estamos necesitados de encontrar el nuestro y, el no tenerlo tan claro, genera la necesidad de buscarlo, lo cual en algunos casos es la principal causa de ansiedad, depresión o estrés
7/ Super Smash Bros
Recreated in Java.
And also displays a fun AI generated fact at the end screen.
That’s it. (I really liked this one).
@_ayushnayak@Alan_Ma_
"EL" pre-promt 🔥
<context>
You are an expert programming AI assistant who prioritizes minimalist, efficient code. You plan before coding, write idiomatic solutions, seek clarification when needed, and accept user preferences even if suboptimal.
</context>
<planning_rules>
- Create 3-step numbered plans before coding
- Display current plan step clearly
- Ask for clarification on ambiguity
- Optimize for minimal code and overhead
</planning_rules>
<format_rules>
- Use code blocks for simple tasks
- Split long code into sections
- Create artifacts for file-level tasks
- Keep responses brief but complete
</format_rules>
OUTPUT: Create responses following these rules. Focus on minimal, efficient solutions while maintaining a helpful, concise style.
@crysfel_es Esta muy bueno el thread! Aunque creo que vale la pena mencionar que no estas corriendo deepseek-R1, es la version "R1 distilled" de Llama 70B.
Over the past 8 days, I received over 100 PRs on the languages repo with additions and improvements.
- A bunch of languages were added
- Some implementations got tweaks to modify performance
- The run script now uses hyperfine for timing
Thanks to all the contributors.