Share graph · provenance running forward
Dylan Desmarchelier
Senior Platform Analyst · inference · lab
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
Route through a gateway you control; do not standardise on a vendor's garden
Open-weight models for classification and extraction; frontier for agentic loops
Which model for structured extraction?
When does on-prem inference make sense?
Sovereign inference and the end of US default
Learning without weights: where continual learning actually lands
Right model, right task
Close enough to switch?
Inference under seal
Learning without retraining
The agent that watches the shop
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.