Lesson 086: Embedding probes on tiny corpora
Focus
Assume an auditor reruns everything you claim; narrate checkpoints aloud. Token Embedding probes on tiny corpora:86 keeps neighbouring lessons differentiable.
Key ideas
- Thread: Embedding probes on tiny corpora · drill v6 · spin
569286. - Habit: pair every model utterance with a trace_id you could paste into Grafana.
- Guardrail: write one RACI bullet referencing this lesson tomorrow.
Deep dive notebook
Synthetic drill artefacts
Retrieval partitioning plan
| Slice | Tokens | Retrieval mode | Notes |
|-------|--------|----------------|-------|
| FAQs | 445 | hybrid@0.55 | keep tables contiguous |
| Policies | 508 | dense@0.69 | include footnotes |
Drill: justify why chunk boundaries fall where they do for lesson 86.
Practice
Practice Paste the worked-example template into a wiki stub and annotate owners. — 86 Bump literals mindset by 24.