https://ajing.github.io/ 2026-06-29 https://ajing.github.io/posts/ 2026-06-29 https://ajing.github.io/start-here/ 2026-06-29 https://ajing.github.io/topics/ 2026-06-29 https://ajing.github.io/topics/agents/ 2026-05-28 https://ajing.github.io/topics/evaluation/ 2026-06-29 https://ajing.github.io/posts/2026-06-29-testing-pretraining-ideas-across-model-scales/ 2026-06-29 https://ajing.github.io/posts/2026-06-29-why-embeddings-cannot-solve-eval-contamination/ 2026-06-29 https://ajing.github.io/posts/2026-06-29-pretraining-contamination/ 2026-06-29 https://ajing.github.io/posts/2026-05-28-agent-eval-difficulty-trajectory-constraints/ 2026-05-28 https://ajing.github.io/posts/2026-04-13-mercor-breach-what-leaked-about-ai-training/ 2026-04-13 https://ajing.github.io/posts/2026-03-11-improving-llm-i18n-tool-use-agency/ 2026-03-11 https://ajing.github.io/posts/2026-03-08-unverifiable-rewards-rl-frontier/ 2026-03-08 https://ajing.github.io/posts/2026-03-05-instruction-following-post-training-data/ 2026-03-05