Ten posts, each aimed at a specific reader — AI infrastructure teams, vector-DB-heavy companies, RAG platforms, agent builders — plus two longer-form pieces. Existing content, restyled into this index rather than rewritten; full posts still live on the current Field Notes page linked below.
| # | Title | Written for |
|---|---|---|
| 01 | The Byte Budget: The Vector Line Item Nobody Forecasts | AI infrastructure teams |
| 02 | Data-Oblivious Compression: What "No Training, No Codebook" Actually Buys You | AI infrastructure teams |
| 03 | Compressed-Domain Search: Querying Without Decompressing First | Vector-DB-heavy companies |
| 04 | Migrating Off pgvector Without Swapping Your Database | Vector-DB-heavy companies |
| 05 | Recall You Can Defend: How to Read a 0.98 Fidelity Number Honestly | Enterprise RAG platforms · methodology |
| 06 | Disk-First vs RAM-First: Where Your RAG Index Should Actually Live | Enterprise RAG platforms |
| 07 | The Memory Tax on Agents: What Long-Lived Context Costs to Store | High-cost LLM / agent builders |
| 08 | When "Just Add More Nodes" Stops Working: The Scaling Wall at 100M Vectors | High-cost LLM / agent builders |
| 09 | A Practitioner's Guide to Benchmarking Vector Compression | Cross-cutting · methodology |
| 10 | The Electricity Cascade: The kWh Hidden in Your Vector Index | Cross-cutting · environmental thesis |
| Title | Author | Format |
|---|---|---|
| The Machine That Forgets: A Short History of AI's Memory Problem | Precog Labs, Jul 2026 | MD |
| Compressed-Domain Search | Precog Labs |