#147 - Google’s Gemini, EU AI Act Deal, Mixtral of Experts, Meta’s ‘Seamless’ translator
Last Week in AI
00:00
Language Model Recall and Prompting Techniques
Recall in language models works well with rational and coherent documents, but inserting non sequitur sentences can cause the model to forget information and fail to respond to related prompts. Prompting techniques, such as providing relevant context before asking a question, have been found to improve the model's ability to recall information. This highlights the challenge of comprehensively auditing the capabilities of language models, as they can demonstrate presence but not absence of capabilities.
Transcript
Play full episode
