cavendish

Share graph · provenance running forward

CD

Claire Dubois

Sector owner · Banking · firm

What they dropped, which clusters it landed in, what got elected, and which experiments and findings descended from it. Everyone’s is visible to everyone, symmetrically. Show outcomes, not counts — no totals, no rankings, no rollups.

Dropped

24

signals with this person attached

Landed in

19

distinct clusters

Elected

16

of those, now fields

Descended

22

experiments and published items

Drops

What descended

recommendationTested

Prompt caching: use for stable prefixes over 2k tokens; expect 30–45%, not 60%

recommendationTested

Every LLM judge ships with a human agreement score or does not ship

recommendationTested

Distil to a small model only after the frontier baseline is measured on the same eval

recommendationTested

Agents act under delegated, scoped, expiring authority — never a service account

recommendationTested

Measure ROI from telemetry and cycle time, not surveys

recommendationAssessed

Give citizen developers a paved road and a retention policy, not a review board

standing answerTested

What does inference actually cost right now?

standing answerTested

Retrieval or fine-tuning for this?

standing answerAssessed

What eval tooling do we use?

standing answerAssessed

When does on-prem inference make sense?

standing answerAssessed

When do we need to move to post-quantum crypto?

positionAssessed

Sovereign inference and the end of US default

positionAssessed

Learning without weights: where continual learning actually lands

experiment · concludedValidated

Token cost ledger across six client patterns

experiment · concludedRefuted

Judge calibration against human panel

experiment · measuring

Release canary suite v2

experiment · measuring

Edge SLM for in-store classification

experiment · running

Nightingale measurement run: coding-assistant ROI

experiment · running

Delegated-authority broker for agent tool calls

experiment · running

Confidential inference on a TEE for banking PII

experiment · voting

Temporal decision memory for a claims agent

experiment · proposed

Non-weight-bound learning via retrieval-updated skills

Follow this person’s finds

Following someone whose drops are consistently good is the internal version of the external voice watchlist, and often a better source than any detector.