9/10. We Confuse the Process with the Facts About the Process

Your execution engine shouldn't just run the workflow; it must record every step as an immutable fact. We use Datomic not just for the domain data, but for the orchestration itself—workflows, stages, tasks. These are entities.

8/10. The Knowledge Graph as Constraint

Many see the Knowledge Graph solely as a source for Retrieval-Augmented Generation (RAG). This misses half the value. In a high-stakes system, the KG is also a constraint. It provides the deterministic boundaries within which the LLM is allowed to operate.

7/10. The Tyranny of Structure vs. The Power of Data

We often force information into rigid schemas too early. A well-designed engine stores intermediate results—the outputs of LLM calls—as simple, serialized data (like EDN payloads).

6/10. Isolating the Plumbing

We often complect the core logic of a task (the prompt engineering, the tool definitions) with the accidental complexity of its execution (error handling, retries, timing, validation). This entanglement guarantees rigidity.

5/10. Dynamic Adaptation vs. Static Plans

A static workflow definition is a plan made when you know the least. Agentic systems, by definition, adapt. The path depends on the results of the previous stochastic step. The engine must support dynamic stages guided by "assessors."

4/10. The Necessity of an Immutable Ledger

In high-stakes environments, "It usually works" is malpractice. When an LLM makes a decision, you must know why. This requires more than logs. It requires an immutable, accretive Execution Ledger.

3/10: Composition over Command: The Functional Dataflow

If your architecture diagrams look like flowcharts, you're building a brittle system. Flowcharts are about control and sequence—concepts that stochastic components actively resist. Instead, design for dataflow.

2/10 Facts, Time, and the Peril of Caching Hallucinations

Stochastic systems demand memoization. But caching an LLM output is fraught. What if the underlying facts in your knowledge graph change? A naive cache returns a stale lie. Information is situated.

1/10: The Illusion of Control

We crave determinism. We build orchestration engines that execute Directed Acyclic Graphs with atomic precision. Then, we insert a stochastic black box - an LLM - into a stage and expect the precision to hold. This is a fundamental misunderstanding.

Just having a look around the uLisp site and was impressed to see the detailed performance benchmarks including power www.ulisp.com/show?36M3 - I added time * average power as some boards are really quick, but high power o_O
#uLisp #embedded #benchmarks #microcontroller #lisp #programming #lowpower

Next programming...

Bios update with flashrom went perfectly using a UM232H with a level shifter and LM317 to get the 1.8v required for the SPI BIOS chip

#bios #coreboot #electronics