https://www.williamliu.ai/ https://www.williamliu.ai/blog/ https://www.williamliu.ai/blog/feed.xml https://www.williamliu.ai/podcasts/ https://www.williamliu.ai/podcasts/agentic-coding-capability/ https://www.williamliu.ai/podcasts/agentic-coding-capability/feed.xml https://www.williamliu.ai/podcasts/agentic-coding-capability/se0-series-overview-the-new-data-unit-for-coding-agents/ https://www.williamliu.ai/podcasts/agentic-coding-capability/t1e0-foundations-of-agentic-coding-overview/ https://www.williamliu.ai/podcasts/agentic-coding-capability/t1e1-from-code-generation-to-agentic-work/ https://www.williamliu.ai/podcasts/agentic-coding-capability/t1e2-agent-computer-interface/ https://www.williamliu.ai/podcasts/agentic-coding-capability/t1e3-trajectories-as-training-data/ https://www.williamliu.ai/podcasts/agentic-coding-capability/t1e4-swe-bench-real-issues-real-repositories/ https://www.williamliu.ai/podcasts/agentic-coding-capability/t1e5-swe-agent-and-the-agent-computer-interface/ https://www.williamliu.ai/podcasts/agentic-coding-capability/t1e6-aider-benchmark-fix-your-own-mistakes/ https://www.williamliu.ai/podcasts/agentic-coding-capability/t1e7-github-copilot-cloud-agent-session-to-reviewable-work/ https://www.williamliu.ai/podcasts/agentic-coding-capability/t2e0-evaluation-and-code-review-for-coding-agents/ https://www.williamliu.ai/podcasts/agentic-coding-capability/t2e1-how-to-evaluate-a-coding-agent-in-practice/ https://www.williamliu.ai/podcasts/agentic-coding-capability/t2e2-public-tests-hidden-tests-and-oracle-tests/ https://www.williamliu.ai/podcasts/agentic-coding-capability/t2e3-leaderboard-literacy/ https://www.williamliu.ai/podcasts/agentic-coding-capability/t2e4-code-review-agents-the-other-half-of-agentic-coding/ https://www.williamliu.ai/podcasts/agentic-coding-capability/t2e5-evaluating-review-quality/ https://www.williamliu.ai/podcasts/agentic-coding-capability/t2e6-code-review-benchmarks-and-datasets/ https://www.williamliu.ai/podcasts/agentic-coding-capability/t2e7-swe-bench-verified/ https://www.williamliu.ai/podcasts/agentic-coding-capability/t2e8-swe-bench-live/ https://www.williamliu.ai/podcasts/agentic-coding-capability/t2e9-aider-polyglot-benchmark/ https://www.williamliu.ai/podcasts/agentic-coding-capability/t2e10-terminal-bench-2-0/ https://www.williamliu.ai/podcasts/mastering-language-models/ https://www.williamliu.ai/podcasts/mastering-language-models/feed.xml https://www.williamliu.ai/podcasts/mastering-language-models/se0-series-overview-mastering-language-models-from-architecture-to-optimization/ https://www.williamliu.ai/podcasts/mastering-language-models/t1e0-foundations-of-sequence-modeling-the-transformer-revolution/ https://www.williamliu.ai/podcasts/mastering-language-models/t1e1-attention-is-all-you-need-the-transformer-breakthrough/ https://www.williamliu.ai/podcasts/mastering-language-models/t2e0-scaling-and-training-large-models-efficiently/ https://www.williamliu.ai/podcasts/mastering-language-models/t2e1-scaling-laws-for-neural-language-models-predicting-progress/ https://www.williamliu.ai/podcasts/mastering-language-models/t2e2-training-compute-optimal-large-language-models-the-chinchilla-lesson/ https://www.williamliu.ai/podcasts/mastering-language-models/t2e3-scaling-data-constrained-language-models-when-fresh-text-runs-out/ https://www.williamliu.ai/podcasts/mastering-language-models/t3e0-advanced-distributed-training-overview/ https://www.williamliu.ai/podcasts/mastering-language-models/t3e1-gpipe-pipeline-parallelism/ https://www.williamliu.ai/podcasts/mastering-language-models/t3e2-megatron-lm-tensor-parallelism/ https://www.williamliu.ai/podcasts/mastering-language-models/t3e3-zero-memory-sharding/ https://www.williamliu.ai/podcasts/mastering-language-models/t3e4-fsdp-fully-sharded-data-parallel/ https://www.williamliu.ai/podcasts/mastering-language-models/t3e5-distributed-training-architecture/ https://www.williamliu.ai/podcasts/mastering-language-models/t3e6-flashattention-io-awareness/ https://www.williamliu.ai/podcasts/mastering-language-models/t3e7-flashattention-2-parallelism/ https://www.williamliu.ai/podcasts/mastering-language-models/t3e8-ssd-self-distillation-code-generation/ https://www.williamliu.ai/podcasts/mastering-language-models/t3e9-test-time-scaling-overtraining-compute-optimal/ https://www.williamliu.ai/podcasts/mastering-language-models/t4e0-finetuning-specialization-lora-beyond/ https://www.williamliu.ai/podcasts/mastering-language-models/t4e1-lora-low-rank-adaptation/ https://www.williamliu.ai/podcasts/mastering-language-models/t4e2-qlora-quantized-finetuning/ https://www.williamliu.ai/podcasts/mastering-language-models/t4e3-lowra-under-two-bits/ https://www.williamliu.ai/podcasts/mastering-language-models/t4e4-continual-learning-llms/ https://www.williamliu.ai/podcasts/mastering-language-models/t5e0-reinforcement-learning-from-human-feedback-rlhf/ https://www.williamliu.ai/podcasts/mastering-language-models/t5e1-proximal-policy-optimization-algorithms/ https://www.williamliu.ai/podcasts/mastering-language-models/t5e2-learning-to-summarize-with-human-feedback/ https://www.williamliu.ai/podcasts/mastering-language-models/t5e3-training-language-models-to-follow-instructions-with-human-feedback/ https://www.williamliu.ai/podcasts/mastering-language-models/t5e4-training-a-helpful-and-harmless-assistant-with-reinforcement-learning-from-human-feedback/ https://www.williamliu.ai/podcasts/mastering-language-models/t5e5-constitutional-ai-harmlessness-from-ai-feedback/ https://www.williamliu.ai/podcasts/mastering-language-models/t5e6-direct-preference-optimization-your-language-model-is-secretly-a-reward-model/ https://www.williamliu.ai/podcasts/mastering-language-models/t5e7-rlhf-deciphered-a-critical-analysis-of-reinforcement-learning-from-human-feedback-for-llms/ https://www.williamliu.ai/podcasts/mastering-language-models/t5e8-robust-reinforcement-learning-from-human-feedback-for-large-language-models-fine-tuning/ https://www.williamliu.ai/podcasts/mastering-language-models/t5e9-reinforcement-learning-from-human-feedback-progress-and-challenges/