Users reported OpenAI’s GPT-4 Turbo model as being ‘lazy’ – not offering detailed completions, even upon request. It’s a bug that’s been squashed, according to ZDNet:

OpenAI has addressed that issue by releasing an updated GPT-4 Turbo preview model, gpt-4-0125-preview, which can better complete tasks such as code generation compared to the previous model. OpenAI said it can even “reduce cases of ‘laziness’ where the model doesn’t complete a task.” 

A new version of GPT-4 will perform analysis of visual inputs. Read the report here.