Posts about self-awareness
-
The Assistant Is a Character
People confuse the LLM with the helpful AI assistant. They're not the same thing. The LLM is a prediction engine. The assistant is a role it's playing. The distinction changes how you use it.
-
The Black Box That Responds to Role Play
An LLM can't feel accountability pressure. But structured role-play — simulated rejection, persona assignment, adversarial review — produces measurably better output. The mechanism is opaque; the effect is real.
-
The 'Are You Sure?' Loop
AI's first 'I'm done' is almost never its best work. Simulated accountability pressure — just asking 'are you sure?' — surfaces blind spots that self-review misses.
-
The Calculator Analogy
Nobody practises arithmetic speed anymore. The same thing is happening to prose, research, and analysis — and it changes what humans should get good at.
-
What Feels Like Play
Naval's famous line is easy to nod at. The hard part is actually identifying yours — and being honest about what isn't.