Andrew likes Agents

**Andrew Ng's The Batch writeup on Agents** highlighted the significant improvement in coding benchmark performance when using an iterative agent workflow, with **GPT-3.5** wrapped in an agent loop achieving up to **95.1%** correctness on HumanEval, surpassing **GPT-4** zero-shot at **67.0%**. The report also covers new developments in **Stable Diffusion** models like **Cyberrealistic_v40**, **Platypus XL**, and **SDXL Lightning** for Naruto-style image generation, alongside innovations in LoRA and upscaling techniques. Discussions on **local LLM deployment** and optimization focus on hardware setups and finetuning strategies for efficient inference and multi-user serving. Emad's departure from **Stability AI** and new **Sora** videos from **OpenAI** were also noted.