Metadata →
Taking notes helps you give AI the right context to get better results. Notes turn your hidden knowledge into clear information AI can use. This makes your thinking deeper and saves time when working with AI. [!note]
Excelente recurso para explicar la importancia de cultivar un contexto mediante toma de notas. El establecimiento de una relación a largo plazo con tus notas, en donde se va sedimentando progresivamente ideas personalmente relevantes, es el camino ideal para hacer que los modelos trabajen realmente como esperas. Los modelos no son el daemons ni genios, son g descorporeizada.
Highlights
id995879748
it is so important to turn tacit knowledge — knowledge that just exists in our head and we cannot articulate — into explicit knowledge so that we can share it with other people, which is the source of why note-taking came into place. Before, level one was just us in our brain. We have things swirling in it, and because we kind of know what they are, we say, okay, that’s fine, right? Don’t need to write anything. Now, until the second iteration, we developed writing systems and we realized, okay, there are things that we need to unload in order for our brains to do more. So that’s why we started to translate this tacit knowledge into explicit knowledge, because then we can work with other people.
La importancia de hacer explícito el conocimiento implícito. Este principio es el que está a la base de la ingeniería de contextos y que respalda la iniciativa de cultivar una bóveda de Obsidian para lograrlo.
id995882407
And now we’re adding on another layer. It’s not just us and other people, but there’s also an AI that has access to other kinds of information so we can put it together and all move forward. And having a note-taking system that has the important information that the LLMs can use makes everything better. Then you can use it to work on the things that take you a lot of time.
Hacer el conocimiento tácito explícito es útil para pulirlo mediante redescripción representacional y para comunicarse claramente con otros y lograr articular trabajo efectivo. En esta lógica, los modelos de lenguaje no son más que un “otro” adicional: una entidad con un coeficiente g asintótico pero completamente disembodied. El contexto que nosotros le ponemos es lo que le da al modelo su utilidad.
id995886835
What kind of notes do we need to have? Well, luckily there are just six categories we have to think about. And I’m drawing straight from context engineering because to be able to communicate with AI, we might as well use its rules and its way of thinking. We mentioned three already that mostly are covered in prompt engineering, which is: we have to give it a role, and then give it some general idea about the goal and the audience that is going to use that output. Then also we want to give it some constraints around style or format and these kinds of things. Most people know this part already. Now the next three things are more covered in context engineering and also notes that we want to have, which are about the inputs, the source of truth, as well as judgment.
Los 6 tipos de información que hacen que la interacción con un modelo de lenguaje sea más efectiva.
id995887178
if you’ve used AI for a while, then you probably noticed it has several frameworks that it keeps on using. For example, for formatting, it uses heading options so that as it goes through, it organizes things by headings. Or it likes to say a lot, “It is not this, it is that.” A great little via negativa there. But the problem with its frameworks is it keeps on using the same ones, and it keeps on using very generic ones when it produces output.
Este es un uso básico de la IA que produce resultados mediocres y que queda rápidamente en evidencia.
id995887392
Studies have shown that if we just outsource our thinking, then yes, as we go on, the quality of the output drops. Also, we are disengaged from the thinking experience. But that’s not the only way to use an LLM. Studies have also found that depending on how you use it, you can deeply engage and actually think deeper and access things that you didn’t have the mental capacity to do before.
El efecto del uso de IA en la magnitud del involucramiento, la profundidad de la reflexión y el desarrollo de capacidades está completamente en función del tipo de uso que se le da. Específicamente, del nivel de agencia que uno tiene respecto del modelo: ¿definimos nosotros la interacción o nos dejamos llevar por sus sesgos? Esto es algo que se puede vincular con la diferencia entre el uso y la relación con el analista en Winnicott.
id995887854
what is holding us back from being more engaged in the thinking process is: have we downloaded the context out from our brain and into the LLM? So when we have a conversation, it’s an intelligent one. It’s one that’s based on the information that we wanted to work with.
Cultivar un contexto jerárquico y curado para el uso de los Modelos de Lenguaje genera un feedback positivo, en el sentido de que se vuelven más útiles y dan más ganas de usarlos.
id995890308
A few moments later. What does it find? I am fundamentally interested in building the case that creativity and structured thinking are not opposites. They are partners. My notes consistently reject the false dichotomy of logical and creative thinkers. Okay. It just articulated that better than me.
Aquí muestra el ejemplo de realizar una consulta personalmente relevante, primero en modo incógnito y después con su bóveda Obsidian como contexto. Esto, además de ser un muy buen ejemplo para mostrar la importancia del cultivo del contexto en el uso efectivo de los modelos de lenguaje, muestra cómo esta dialéctica puede ayudarnos a pulir nuestro pensamiento, ayudándonos a ver patrones que no necesariamente seríamos capaces de identificar.
id995891609
if you are working on something and you want to build on top of it — you want the ideas to compound and not just build sandcastles — then you have to document it. It has to be explicit so that AI can work with it
Trabajar de esta manera es como utilizar el modelo de lenguaje como un espejo que se refleja a sí mismo, al cual uno progresivamente le va corrigiendo su superficie para que te refleje más a ti mismo. En cierto sentido, es como la diferencia entre un ambiente estéril (usarlo como incógnito) y la riqueza de un ecosistema antiguo y complejo: tiene un carácter único. Si uno se toma el trabajo de marcar su posición respecto de ideas de interés personal y las sedimenta explícitamente, con el tiempo el modelo tendrá un contexto que permite replicar ese ecosistema como un holograma preciso.