proof

content/blog/Introducing Honcho's Dialectic API.md

@@ -119,7 +119,7 @@ We can leverage this substrate for agent coordination with more depth and nuance
 
 This is just the start. Just like you can appendage memory and tools to an LLMs we can augment this substrate in a number of ways--from designing multi-party protocols, to enabling zero knowledge or confidential environments, or recording transactional data on blockchains or other types of public or private immutable ledgers.
 
-That kind of richness puts us one step closer to the dream of a semantic web, one as replete with meaning as the physical world *and* machine grokkable. The things that matter to me can be used to personalized an atomic agent *just in time*, without sacrificing important context. That intelligent microservice can be more aligned with me than human economic actors and professional services, which are plagued with high-latency interest misalignment and information asymmetry.
+That kind of richness puts us one step closer to the dream of a semantic web, one as replete with meaning as the physical world *and* machine grokkable. What *matters* to me can be used to personalize an atomic agent *just in time*, without sacrificing important context. Intelligent microservices can be more aligned with me than human economic actors and professional services, which are plagued with high-latency interest misalignment and information asymmetry.
 
 Honcho and agent dialectics can eliminate the principal-agent problem for this new economic paradigm, digitally extending human agency and identity further than ever before. 
 

content/notes/LLM Metacognition is inference about inference.md

@@ -4,4 +4,4 @@ For wetware, metacognition is typically defined as ‘thinking about thinking’
 
 In large language models, the synthetic corollary of cognition is inference. So we can reasonably define a metacognitive process in an LLM architecture as any that runs inference on the output of prior inference. That is, inference itself is used as context--_inference about inference_. 
 
-It might be instantly injected into the next prompt, stored for later use, or leveraged by another model. This kind of architecture is critical when dealing with user context, since LLMs can run inference about user behavior, then use that synthetic context in the future. Experiments here will be critical to overcome [[Machine learning is fixated on task performance|the machine learning community's fixation on task completion]]. At Plastic, one of the most interesting species of metacogntion is [[Loose theory of mind imputations are superior to verbatim response predictions|theory of mind and mimicking that in LLMs]] to form high-fidelity representations of users.
+It might be instantly injected into the next prompt, stored for later use, or leveraged by another model. This kind of architecture is critical when dealing with user context, since LLMs can run inference about user behavior, then use that synthetic context in the future. Experiments here will be critical to overcome [[Machine learning is fixated on task performance|the machine learning community's fixation on task completion]]. For us at Plastic, one of the most interesting species of metacogntion is [[Loose theory of mind imputations are superior to verbatim response predictions|theory of mind and mimicking that in LLMs]] to form high-fidelity representations of users.