Neuralese, memristor-inspired AI, and ECI compared

Available 2026-09-20. Read the series synopsis and earlier parts below.

HerbDev Learning Series 01

Representation, memory, and environmental intelligence

Follow four connected guides from machine-native representations to persistent state, then apply the distinction to environmental change. Finish with a comparison that shows what each layer contributes and how to evaluate it.

Part 1 · Published 2026-08-30
Neuralese: machine-native representation
Understand embeddings, latent states, and machine-native communication, and why representation alone does not give an AI system persistent memory.
Part 2 · Published 2026-09-06
Memristor-inspired stateful AI
Explore history-dependent computational state, software experiments, decay, reinforcement, and the limits of memristor-inspired AI.
Part 3 · Coming 2026-09-13
ECI: embeddings and environmental memory
How repeated observations, embeddings, context, and human review can build environmental history, with a clear boundary between current ECI and research.
Part 4 · Coming 2026-09-20
Neuralese, memristor-inspired AI, and ECI compared
Compare learned representations, stored environmental history, and persistent computational state, with an ECI example and a practical research roadmap.

All learning series

Manage browser learning data

“Remove my test data” clears all AI 101 and ML 101 scores, reviews, project checklists and rating selections, plus saved vocabulary and recent history in this browser. Test entries cannot be separated from other learning progress. Cookie preferences, security protections, submitted feedback, contact emails and past analytics are kept.