ChatGPT-5 fails simple tasks, researchers criticize

bfmtv.com (French)

ChatGPT-5 is facing widespread criticism for unreliability and inaccuracies, failing even simple tasks. Researchers and users are highlighting inconsistencies, particularly with image generation and factual errors, contradicting claims of "doctorate-level" performance. These "hallucinations" have led to significant disappointment and questioning of OpenAI's latest model's capabilities.


With a significance score of 3.1, this news ranks in the top 11% of today's 31012 analyzed articles.

Get summaries of news with significance over 5.5 (usually ~10 stories per week). Read by 10,000+ subscribers:


ChatGPT-5 fails simple tasks, researchers criticize | News Minimalist