National Design Studio launches Rampart Edge, a tiny on-device privacy filter model
kevinnbass · x · 2026-10-17
Jared Z at National Design Studio launched Rampart Edge, an on-device privacy model that filters personal user data before it reaches the cloud. After extensive hill-climbing and data labeling, the weights are small enough to fit in a notebook, noticeably speeding up load times for hundreds of thousands of users.
More from Models
- Perplexity decider v1.2 lands #3 on Decision Index as longer training erodes backbone skills — antoine_chaffin · 2026-10-17
- Perplexity's 4B decider model distills from its 27B sibling using the same training recipe — antoine_chaffin · 2026-10-17
- Perplexity traces decider v1.2 regressions to longer training, mitigates via model souping — antoine_chaffin · 2026-10-17
- Perplexity details decider data hygiene: official splits only, deduped, 16.6% of one stage — antoine_chaffin · 2026-10-17
- Perplexity says rivals train on Decision Index benchmark sets, opts to follow for fair comparison — antoine_chaffin · 2026-10-17
- Dual-mask fine-tuning recovers cacheability with only -0.4 DI vs full bidirectional — antoine_chaffin · 2026-10-17