https://missingpackage.dev/https://missingpackage.dev/about/https://missingpackage.dev/explorables/https://missingpackage.dev/explorables/alignment/https://missingpackage.dev/explorables/alignment/chapters/00-maphttps://missingpackage.dev/explorables/alignment/chapters/01-specificationhttps://missingpackage.dev/explorables/alignment/chapters/02-generalizationhttps://missingpackage.dev/explorables/alignment/chapters/03-model-organismshttps://missingpackage.dev/explorables/alignment/chapters/04-honesty-cothttps://missingpackage.dev/explorables/alignment/chapters/05-scalable-oversighthttps://missingpackage.dev/explorables/alignment/chapters/06-interpretabilityhttps://missingpackage.dev/explorables/alignment/chapters/07-auditing-evalshttps://missingpackage.dev/explorables/alignment/chapters/08-control-securityhttps://missingpackage.dev/explorables/alignment/chapters/09-values-welfarehttps://missingpackage.dev/explorables/alignment/chapters/10-research-agendahttps://missingpackage.dev/explorables/post-training/https://missingpackage.dev/explorables/post-training/chapters/00-maphttps://missingpackage.dev/explorables/post-training/chapters/01-sfthttps://missingpackage.dev/explorables/post-training/chapters/02-rl-foundationshttps://missingpackage.dev/explorables/post-training/chapters/03-reward-modelshttps://missingpackage.dev/explorables/post-training/chapters/04-rlhfhttps://missingpackage.dev/explorables/post-training/chapters/05-direct-preferencehttps://missingpackage.dev/explorables/post-training/chapters/06-rlvr-reasoninghttps://missingpackage.dev/explorables/post-training/chapters/07-scaling-rlhttps://missingpackage.dev/explorables/post-training/chapters/08-character-safetyhttps://missingpackage.dev/explorables/post-training/chapters/09-evals-methodhttps://missingpackage.dev/notes/https://missingpackage.dev/work/https://missingpackage.dev/writing/https://missingpackage.dev/writing/how-i-run-a-coding-agent-overnight/