josh 4c1c0e9ff2 Overhaul model system with multi-stage training, variants, benchmarks, and eval ...

Replace the single-stage training + flat capability score with a realistic AI
development pipeline: pre-training with Chinchilla scaling laws, SFT with
specializations, alignment with safety/capability tradeoffs (RLHF/DPO/Constitutional),
model families with distillation/fine-tuning/quantization variants, named benchmark
suite with compute-costing eval jobs, and segment-specific market quality.

Phases 1-6 of the model rework plan: new types, engine rewrite, save migration,
training events/risk system, concurrent training, variant creation, benchmark
evaluation with leaderboard, and market integration.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-04-25 07:36:34 -04:00

..

game-engine

Overhaul model system with multi-stage training, variants, benchmarks, and eval

2026-04-25 07:36:34 -04:00

shared

Overhaul model system with multi-stage training, variants, benchmarks, and eval

2026-04-25 07:36:34 -04:00

tsconfig

Add Hono backend with PostgreSQL, auth, cloud saves, and leaderboard

2026-04-24 17:35:18 -04:00