🗳️ AI最新资讯

🌐 Andrej Karpathy 演讲: State of GPT

Andrej，AI Researcher & Founding Member, OpenAI，他YouTube频道的深度学习课程也值得一看。最近发表的演讲State of GPT讨论了：

ChatGPT训练流程，从标记化到预训练，监督下的微调，以及从人类反馈中强化学习（RLHF）。深入研究有效使用这些模型的实用技术和心理模型，包括提示策略、微调、快速增长的工具生态系统以及它们的未来扩展。

Learn about the training pipeline of GPT assistants like ChatGPT, from tokenization to pretraining, supervised finetuning, and Reinforcement Learning from Human Feedback (RLHF). Dive deeper into practical techniques and mental models for the effective use of these models, including prompting strategies, finetuning, the rapidly growing ecosystem of tools, and their future extensions.

相关链接：
[State of GPT | YouTube]
[State of GPT | pdf]
[Alex Volkov - targum.video on Twitter: Talk notes]
[炼丹不易，用丹有趣：State of GPT的番外解读]

🏷️ #AInews #openai

🐟 @protoolkit
All about AI and Productivity.