{"data":{"slug":"post-training","etype":"concept","name":"Post-training (RLHF, RLVR and after)","cat":"Training & Inference","subtitle":"Where a raw predictor becomes an assistant — and, lately, a reasoner.","summary":"After pre-training, models are shaped: supervised fine-tuning on demonstrations, RLHF against human preferences, and now reinforcement learning on verifiable rewards (math checkers, passing tests) that produced the reasoning models. Post-training's share of total compute is rising sharply — labs describe it as the new frontier of differentiation, which is why data-labeling firms and RL environments became strategic assets.","attrs":null,"kf":null,"aliases":["RLVR","SFT"],"ticker":null,"exchange":null,"hq":null,"founded":null,"website":null,"status":null,"region":null,"asof":"2026-01-15","sources":[{"url":"https://arxiv.org/abs/2501.12948","label":"DeepSeek-R1 (RL for reasoning)"}]},"meta":{"found":true,"count":1,"served_from":"site cache (no live upstream calls)","as_of":"2026-10-14T08:56:03+00:00","disclaimer":"Research and information only — not investment advice. Structured records carry basis labels (vendor spec / reported / estimate); market quotes are delayed/indicative.","attribution":"Records compiled from vendor documentation, official filings and reputable public reporting; market quotes via financial data providers. See /data-sources."}}