Users of OpenAI's ChatGPT have reported a series of issues affecting the tool's functionality. A notable bug has been identified that prevents error messages from being displayed, hindering users' ability to correct code. Additionally, changes intended to address GPT's 'laziness' by removing short response pressure have inadvertently caused problems with code block outputs and significantly slowed down the service. The persistence of these issues, particularly with code outputs in ChatGPT (Premium, GPT-4), has led some users to consider looking for alternatives.
It seems that OPENAI has been trying to fix the lazy Gpt and has created the broken gpt in ChatGPT. https://t.co/ZkIGd7x1NC
ChatGPT (Premium, GPT-4) still completely broken for code outputs. Not good. Looking for alternatives now. https://t.co/nPdiRlxlcS
ChatGPTโs prose is mediocre But most writers havenโt seen how GPT can smash even the worst writersโ block and help you โbreak storyโ. Hereโs how: https://t.co/k1pwtIbp5x
ChatGPT engineers are struggling OpenAI -โFixesโ GPT laziness by removing short response pressure, and adding a 2nd message auto continue if there is still content to write -breaks code blocks cuz the second message closed the block in the first -nukes capacity, slow as hell https://t.co/7EhB4pLcs2
Seeing a strange bug today on ChatGPT (4), where it is breaking code outputs: https://t.co/w3oeBW9ZSI
ChatGPT Code Interpreter seems to have stopped displaying error messages - when an error occurs it still loops and attempts to fix it, but I can't see what the error was any more. Makes it much harder for me to help nudge it towards a fix for the problem! cc @OpenAI