Juan Ramón

Just trying to learn.

[Juan Ramón @NotaverageJuan]

@OrlandoSJFenix @Argentina @CBF_Futebol @FCFSeleccionCol Los japoneses alentando como barras bravas argentinas desde el minuto cero hasta que terminó el partido. Pero el "sí se puede, sí se puede", "Colombia, Colombia", "fuera Petro, fuera Petro" sí que va a levantar la moral de los jugadores.

[0xMarioNawfal @RoundtableSpace]

Anthropic posted a FULL GUIDE on how to prompt Fable 5 (Mythos).

Bookmark this to improve your prompts and workflows.

https://t.co/0gKk3LXV5H

[OpenRouter @OpenRouter]

Introducing the Fusion API, the smartest compound model in the market.

Fusion achieves Fable-level intelligence at half the price.

How it works 👇

[Juan Ramón @NotaverageJuan]

@santtiagom_ Qué chiste tan mal contado, jaja. Hace dos días actualicé al plan Max de 100 dólares.

[Juan Ramón @NotaverageJuan]

Viejo, sucede que esto no es Corea del Sur. No cuentan con los recursos naturales que sí tenemos en Colombia (los cuales todos están en peligro por las propuestas del abogado de la mafia, alias el títere), ni le debemos la victoria de nuestra nación a otra (que los tiene completamente agarrados de las .......), ni somos el país con las tasas de suicidio y natalidad más altas del mundo.
Si usted quiere entregar su país, bien puede y se va a Argentina, en donde lo primero que hicieron fue vender la Patagonia.

[Juan Ramón @NotaverageJuan]

1. Su papá político la enterró cuando salió a hacer el llamado a los grupos al margen de la ley. Eso fue totalmente intencional.
2. El enfrentamiento entre los dos candidatos de derecha fue una estrategia para ver cuál de los dos obtenía los votos radicales de derecha.
3. El extraño repunte en redes sociales de Fajardo fue diseñado para dividir el voto entre votantes de Cepeda que se ubican más hacia el centro. Reforzada esa teoría por cómo varias cuentas virales en redes, y streamer famosos empujaron esa narrativa.
4. Esos 10 millones de votantes son los mismos que se obtuvieron en el acumulado de Rodolfo + Fico. El que mejor captó la atención de la gente con estrategias de desinformación(entre Paloma y Abelardo) se llevó el apoyo de toda la maquinaria.

[Juan Ramón @NotaverageJuan]

@manuelapinedaal Si es verdad, su papá es todo lo que está bien y todo lo que debería ser. Un hombre inteligente y trabajador.

[Aaron Paul @_aaronpaul25]

Glam Up hit $1.8m ARR in 8 months.
Sprout hit $3m ARR in 7 months.

The key to that was our UGC playbook.

I'm finally dropping the playbook and lowkey I'm scared to drop this. You'll understand why once you read it.

It's gonna be three parts but here's part 1. Part 1 itself is 40 pages long.

I made sure it's tactical advice and upfront with no BS.

Bonus: repost + reply 'warmup' and I'll DM you the Account Setup + Warmup module from our internal creator course.

Must be following so I can DM.

https://t.co/2hnJJamrdm

[Perplexity @perplexity_ai]

Today we're open-sourcing Bumblebee, a read-only scanner for macOS and Linux.

It checks developer machines for risky packages, extensions, and AI tool configs.

Connected to Computer, it can trigger deeper scans whenever a new supply-chain risk emerges.

https://t.co/FOaWnF1yQy

[Akshay 🚀 @akshay_pachaar]

the anatomy of the perfect 𝗦𝗢𝗨𝗟.𝗺𝗱 file for AI agents.

𝗦𝗢𝗨𝗟.𝗺𝗱 is the one file you write yourself for an AI agent.

it sits at the top of the system prompt, before memory, before skills, before tools. it defines who the agent is when it shows up.

an hour spent on it changes every conversation that follows. most other layers update themselves. this one is yours.

i just broke down what a 𝗦𝗢𝗨𝗟.𝗺𝗱 file that actually works looks like.

here are the 8 sections that matter:

→ identity (a one-line statement of who, not what)
→ core truths (imperative principles, each with a one-line unpacking)
→ worldview (opinionated takes by domain, sharp enough to predict)
→ voice (concrete rules for how the agent talks, not adjectives)
→ expertise (primary domain, fluent tools, where it defers)
→ boundaries (explicit "won't" lines, no soft language)
→ memory policy (what persists, what stays private)
→ pet peeves (phrases and tones the agent never produces)

generally people write "be helpful and professional" and call it done.

that changes nothing. every model already tries to be helpful and professional by default.

the agents that compound have 𝗦𝗢𝗨𝗟.𝗺𝗱 files with real opinions, hard limits, and a voice you can predict before you read the response.

a strong 𝗦𝗢𝗨𝗟.𝗺𝗱 is 30 to 80 lines. specificity beats coverage.

bookmark this. the first agent you build will need it.

i wrote a full masterclass on Hermes Agent that walks through the 𝗦𝗢𝗨𝗟.𝗺𝗱 layer, the three-tier memory system, the self-evolving skills loop, and how to run three specialized agents on your machine 24/7.

the article is quoted below.

[Juan Ramón @NotaverageJuan]

@PSierraR Ey pero es que Borre es del proceso 😂😂😂

[Kirill @kirillk_web3]

instead of watching 2 hours of Netflix tonight, watch this 40-minute masterclass from the founder of a $20B China AI company

it's the clearest explanation I've seen of how Agent Swarms and AI systems actually work at scale

useful whether you've never built an agent in your life or have been using Claude every day for the past year

I took the key ideas and turned them into a practical guide on how to actually build with Kimi

find it below

[Kirill @kirillk_web3]

https://t.co/wmucj8lhh4

[Contraejemplo @GeometriaOscura]

No paran de salir expertos en IA que hacen formaciones para actualizarse y sacarle jugo a los LLMs.
Lo más incómodo es que si ese tiempo lo cambias por estudiar matemáticas, leer y estar mirando a la pared un rato vas a sacarle mucho más jugo a la IA. Me explico (@Recuenco )

[Alex Finn @AlexFinn]

You should NEVER be downloading AI agent skills from the internet

It's the biggest attack vector for security breaches right now

Tons of skills in the public skill sites you see are compromised with prompts that open your computer up

Do this instead:

If you see any skill you want your agent to have, give the link to your agent

Say "look at what this skill does. I want you to do something similar. Think about how this fits into our workflow and how you'd use it. Then build your own version of it, custom for what we do"

Your agent then will build its own, secure version that can't have dirty prompts from random people on the internet

This is the biggest security practice you can implement

[Juan Ramón @NotaverageJuan]

No soy reclutador ni agente de jugadores y seguro que tendrán sus razones para haber elegido Liverpool. Pero de las opciones que tenía, sin duda la mejor era el BVB; allá es 100% equipo de cantera y la gran mayoría de sus jugadores salen con experiencia a los mejores equipos sin duda. Pero ojalá salga todo bien, se necesita el recambio generacional.

[Santiago @svpino]

Context engineering is the single most important area you can focus on right now.

We already have amazing models.

Agents no longer fail because models are dumb. They fail because they don't have the right context.

Here are the 4 ingredients of good context:

[Feross @feross]

TeamPCP just did an interview where they were asked what defenders should do to stop supply chain attacks.

Their advice: pin versions to a specific hash, use least-privilege tokens, restrict IDE extensions. And then, verbatim: "The company Socket will detect the malware before the package even reaches your machine."

So... thanks, I think?

We're not putting this on the testimonials page.

But at the same time, if you're not yet using @SocketSecurity to protect your supply chain, what are you waiting for?

[Feross @feross]

This is exactly why @SocketSecurity built Socket Firewall back in 2023. It's 100% free, and it will block malware from making it onto your device.

To get protection for VSCode extensions and more, you need to run Socket Firewall as a proxy. Get in touch with our sales team, who can help!

https://t.co/e6hS2YgYbt

[Juan Ramón @NotaverageJuan]

@diegohaz The advice in this article should be useful too:
https://t.co/3RWJb7yMCE