Adrian Valera

Fractional CTO

[Adrian Valera @adrianvalrom]

@c_sanve Melohaspegao

[Adrian Valera @adrianvalrom]

@ImVictorGuardia Me he enfrentado a ese problema en 3 ocasiones, no me sorprende.

Pero si... hay bastante fricción hasta que le pillas en truco

[Adrian Valera @adrianvalrom]

Why this guy has A-D and 1-8 indexes and I don't even thought about having that...

[Andrej Karpathy @karpathy]

We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks:

Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better:

Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better:

Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better:

Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work!

In summary:
- As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding.
- Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.

[Adrian Valera @adrianvalrom]

@davidlloayza Isma is around, if you want to ping him ;)

[Adrian Valera @adrianvalrom]

@XMihura Top!

[Adrian Valera @adrianvalrom]

If we see this like this... ♟️

[Jake Mor @jakemor]

be zuck:

- realize you can't compete with frontier labs
- open source your own, trick china into training for you
- buys china's top agent (manus), learns harness design
- china wakes up, blocks the acquisition
- spends $20b to KO scaleai as a data supplier
- builds muse, modeled off openclaw

3d chess. i dont see a world were they dont win. distribution always does. your grandma and 15 year old cousin will sign up for muse in the same week.

and you know for a fact they are optimizing every nook and cranny for engagement out the ass.

very well played team

[davidlloayza @davidlloayza]

Barcelona, here we go!

We are orginising a new event in barcelona during the AI Summit week, this time in partnership with @AticcoLab!

The idea is simple: put together the top talent! 100 spots for operators and builders!

Dm if you want to join! @adrianvalrom

[Adrian Valera @adrianvalrom]

Here we go again!

[davidlloayza @davidlloayza]

Saturday office with the G (@adrianvalrom)

Saturday the perfect day of the week to work, no meetings, no distractions, just focus

[Adrian Valera @adrianvalrom]

@marcosrincon_ Si quiero meter un kilo de azucar en un pais donde los dulces no son muy bien vistos, ¿cómo harías?

[Adrian Valera @adrianvalrom]

Mmm... I think I will save this for later.

[Daniel Belfort ⊙ @danielbelfort]

Introducing Offprint™

The physical magazine made from everything you "save for later" but never actually go back to read.

Find online, read offline.

Print media is back!

[Adrian Valera @adrianvalrom]

@_MarcosValera @soti_fam Bengalururuu

[Adrian Valera @adrianvalrom]

@_MarcosValera @goratetas1 Así habla @nntaleb en El cisne negro

El que no arriesga nada, no gana nada.
pero pierde poco.
El que arriesga todo, algún día lo pierde todo...
hasta que un día no.

No se trata de quién trabaja más.
Quién apostó, y a que costo

[Adrian Valera @adrianvalrom]

@daanimarttin Yeah!

Esta semana le metí api de sueño y deporte, pasándole una fotillo rápida puedes contar calorías.

Lo increíble sería meterle ahí la API de mercadona, yo como ando fuera de spain

El tema es tener una necesidad, y luego que se te ocurra ahí resolverla

[Adrian Valera @adrianvalrom]

Here we gooo

[marcos valera @_MarcosValera]

@unifygtm x @LetsGiveAGo x oai

using @ElevenLabs x @zernio x Gurusup Brain x probably a few more things (we're on it)

blurred pic

[Adrian Valera @adrianvalrom]

Granola spoon 😎

Starting to steal my brother's future content
Starting with a spoon

[Adrian Valera @adrianvalrom]

@c_sanve A mi eso nunca me ha pasado, ni me volverá a pasar

[Adrian Valera @adrianvalrom]

Always in your 🧠 and sometimes in your ❤️

[Archie McKenzie @archiemckenzie_]

“we sandboxed the agent”

meanwhile the agent:

[Adrian Valera @adrianvalrom]

This one has just a slight touch of AI

[marcos valera @_MarcosValera]

https://t.co/oazbHtllHb

new edition

[Adrian Valera @adrianvalrom]

@davidlloayza @dhh Amazinnnnnng