update: FAL results report with final eval numbers + conclusions 99c09f5 verified rtferraz commited on 3 days ago
add: FAL demo results report (preliminary β eval crash pending fix) f46c90b verified rtferraz commited on 3 days ago
add: Modal deployment lessons learned β TRL dependency hell postmortem 81195a7 verified rtferraz commited on 3 days ago
add: ADR-003 Future-as-Label demo β detailed implementation plan with research validation d75cbbf verified rtferraz commited on 3 days ago
add: V4.2 Final Report β complete project retrospective with evidence-based analysis 22cca8b verified rtferraz commited on 11 days ago
docs: add V4.1 run report β detailed evaluation with per-task analysis and V4.2 roadmap 482efc4 verified rtferraz commited on 17 days ago
docs: add V4 run assessment with lessons learned and improvement roadmap cfaf49c verified rtferraz commited on 17 days ago
ADR-002: V4 Instruct-Only GRPO β revises dual-model plan based on model repo audit 50e0e4d verified rtferraz commited on 19 days ago
Add comprehensive investigation report β performance audit, unexplored alternatives, literature-backed recommendations 4312bfd verified rtferraz commited on 20 days ago
Add session checkpoint: v3 launch decision with full context bead5cb verified rtferraz commited on 21 days ago
Add v3 thinking control patch - task-aware system prompts + think efficiency reward 0f39df7 verified rtferraz commited on 21 days ago
docs: add ADR-001 next steps with detailed execution plans b47b36b verified rtferraz commited on 21 days ago