frontier models
Continual Learning Made a Bid for Sovereign AI
Thomson applies a mid- and post-training stack to an open-weight base while trying to preserve plasticity and stability.
Summary
Thomson applies a mid- and post-training stack to an open-weight base while trying to preserve plasticity and stability.
The authors report competitive results across agentic, safety, legal, tax, multilingual and deep-research evaluations, with broad gains and little of the forgetting seen in narrow adaptation. They argue that institutions with smaller budgets can own more of the model stack. Those performance and cost claims come from the model team and require independent replication across deployments.
Why it matters
Thomson applies a mid- and post-training stack to an open-weight base while trying to preserve plasticity and stability.
Limits and context
No additional limitation was separately recorded.
Key claims
Thomson applies a mid- and post-training stack to an open-weight base while trying to preserve plasticity and stability.
Evidence: source-2026-08-28-013
Sources
- arXiv preprint 2608.27147arXiv · primary research
Corrections
No corrections have been recorded for this story.