Evaluating AI's general performance & finding models for unrestricted prompting remains a challenge

Duration: 0:58 Views: 232 Submitted: 1 year ago

Tags: ai artificial intelligence data data science technology twiml tech machine learning podcast ml generative ai large language models llms multimodal models grounding embodiment autoregressive models fine-tuning diffusion models text-based models language models back translation self alignment university of washington meta tokenization prompts rag luke zettlemoyer chat gpt open ai parameters icml 2023 bing transformers tokens image generation reasoning sparsity