BlueDot Rapid Grants
Amount hiddenAmount: $****Funding amount is privateDate Awarded: May 31, 2026
Details
- Funder
- BlueDot
- Purpose
- Phase 1 was funded by a $650 BlueDot Impact Rapid Grant; the deliverables below are public. The estimator recovers known ground-truth effects on a synthetic testbed (all three 95% credible intervals contain the truth) - a pre-registered go/no-go gate, cleared before any real-model spend. The rho* frontier separates a genuinely causal case (rho* = 0.69) from a decorative baseline (rho* = 0.05). In real planted-hint audits of an open model (Llama-3.1-8B, up to n = 103 per run, free-tier inference), 36.9% of runs followed the planted hint, mostly without acknowledging it in the CoT - and the auditor flagged them (verdicts still heuristic until the golden set below validates them). A real caught transcript is public. MIT-licensed repo with a 124-test CI suite: https://github.com/thylinao1/bayes-cot-faithfulness - interactive demo and evidence: https://thylinao1.github.io/bayes-cot-faithfulness/site/ BlueDot https://bluedot.org/programs/rapid-grants , search for Maksim Silchenko
Metadata
- Created
- Jul 13, 2026, 6:20 AM UTC