guide
Semiotic Processing: Build the Rest of the Computer
Five principles for using language models as processors of meaning while keeping reliable state, rules, and verification in the surrounding system.
Writing
Ideas for systems that people can live with.
Essays, notes, guides, and working frameworks about meaning, technology, learning, and creativity.
Start here
essaySystems from the GapsWhy and how I do what I do in all my systems work, at SkillSaige and beyond.Read the articleInterested in semiotic processing and how you can apply it? Start with this:
guideSemiotic Processing: Build the Rest of the ComputerFive principles for using language models as processors of meaning while keeping reliable state, rules, and verification in the surrounding system.Read the articleLatest writing
note
When does an interpretation become system state?
A model can propose what someone meant. The system has to decide whether that proposal becomes a lasting change.
essay
Maybe the LLM shouldn't be the core of the system
If the model is one bounded processor inside a larger system, the model can remain probabilistic while the system becomes testable again.
note
When does the system need a language transform?
A language transform earns its place where a designed system encounters meaning that its ordinary rules cannot use directly.
note
Test the transform at the boundary
Evaluate whether a language transform preserves the distinctions the system needs, then test the system's rules separately.
note
Stateless doesn't mean contextless
A language transform can receive the context it needs for one operation while the system remains responsible for memory and state.
note
Start with the system, then find the transform
Design the behavior people need first. Then ask whether a stateless language transform makes one part of that system better.
essay
Can you test an LLM like normal software?
If you've even considered using AI for business (or really production software of any kind), you should probably be asking this question.
essay
Why do LLMs hallucinate?
A practical look at why LLMs hallucinate, and what you can do about it (spoilers, "more prompts, more training" isn't the answer).
essay
Computerized Screaming Void of the Collective Human Subconscious (Now a Subscription!)
“We’ve made a computerized screaming void of the collective human subconscious. Would you like to talk to it?” What LLMs become when you take a step back, and why it's actually not that scary in the light.
essay
What if LLMs Are Something Else Entirely?
When we really look at the technology without preconceptions of AI, LLMs stop looking like "synthetic intelligence" and more like a very weird, very new kind of compute.
essay
Systems from the Gaps
Why and how I do what I do in all my systems work, at SkillSaige and beyond.