Share graph · provenance running forward
Amber Hall
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
signals with this person attached
Landed in
distinct clusters
Elected
of those, now fields
Descended
experiments and published items
Drops
What descended
Prompt caching: use for stable prefixes over 2k tokens; expect 30–45%, not 60%
Every LLM judge ships with a human agreement score or does not ship
Distil to a small model only after the frontier baseline is measured on the same eval
Agents act under delegated, scoped, expiring authority — never a service account
Measure ROI from telemetry and cycle time, not surveys
Give citizen developers a paved road and a retention policy, not a review board
What does inference actually cost right now?
Retrieval or fine-tuning for this?
What eval tooling do we use?
When does on-prem inference make sense?
When do we need to move to post-quantum crypto?
Sovereign inference and the end of US default
Learning without weights: where continual learning actually lands
Where the tokens go
The judge on trial
The canary suite
Small model, back of the store
What the assistant is worth
Who signed for that
Inference under seal
Does it still agree with itself?
Learning without retraining
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.