For a while now, ChatGPT has been impressing the users with its performance. From solving difficult questions, drafting emails, generating excuses, to completing assignments, ChatGTP has proven its abilities.
It has even aced difficult exams like the MBA programme from Pennsylvania's Wharton School.
Recently, the AI was subjected to simulated exams including Uniform Bar Exam, LSAT, GRE, and all the AP exams. It cleared all exams with good grades, except for one: English language and Literature.
Ethan Mollick, a professor from Wharton shared the GPT-4’s scorecard on Twitter. While many claimed that the AI relies on the data from the internet and hence it's 'cheating', the professor believes otherwise.
He clarifies that despite the use of deep knowledge, the AI still has to process the data, and apply these theories in order to answer the questions.
At a time when many fear being replaced by the increasing reliance on technology and AI, its failure to clear the English literature exam has brought a bit of relief in people, proving that AI can't replace everything, afterall!
One user wrote, "Wow these results are absolutely impressive! GPT-4 is acing exams left and right, even outperforming many humans. It's fascinating (and a bit unnerving) to see the potential impact of AI on education and testing."
Another user wrote, "There's something so beautiful about ChatGPT passing everything except English literature, which neatly exposes its pretty severe limitations.
Check more reactions:
(At The Quint, we question everything. Play an active role in shaping our journalism by becoming a member today.)