Experts weigh in on ChatGPT’s performance decline

Share post:

OpenAI’s ChatGPT has been criticized for a decline in its accuracy for math, code generation, problem solving, and sensitive questions since March. A study by Stanford University and UC Berkeley found that GPT-4, the underlying technology for ChatGPT Plus, has performed worse than its predecessor, GPT-3.5, on these tasks.

In response to these criticisms, OpenAI has introduced a new feature called “custom instructions.” This feature allows users to add specific requirements to their prompts, which will be considered in every conversation going forward. This is intended to help users get the responses they need from ChatGPT, even if the model’s performance has declined.

Some experts like Simon Willison, a former Google engineer, finds some aspects of the paper unconvincing. While Arvind Narayanan, a computer science professor at Stanford University, emphasizes that the model’s capabilities and behavior are distinct aspects.

Hence, experts suggest that refining prompts can help address some of GPT’s issues. By using specific, context-rich, and detailed prompts, users can achieve better responses and minimize the impact of the recent decline in performance. Online courses focused on prompt optimization and understanding language model training can aid in creating more effective prompts.

The sources for this piece include an article in AnalyticsIndiaMag.

Featured Tech Jobs


Related articles

AI surpasses human benchmarks in most areas: Stanford report

Stanford University’s Institute for Human-Centered Artificial Intelligence (HAI) has published the seventh annual issue of its AI Index...

Microsoft and OpenAI partner to build a $100 Billion AI supercomputer “Stargate”

In a bold stride towards computational supremacy, Microsoft, in partnership with OpenAI, is reported to be laying the...

US Bill Aims to Unveil AI Training Data Sources Amid Copyright Concerns

In a significant move toward transparency, a bill was introduced in the US Congress on Tuesday by California...

AI presents an “extinction level threat” – US Gov’t Report: Hashtag Trending for Tuesday, March 12, 2024

A new US government report warns that AI presents an “extinction level threat to the human species. Elon Musk is outsourcing his Grok AI code. Hackers have breached the Cybersecurity and Infrastructure Security Agency in the US and a researcher shows how to steal a Tesla by leveraging a feature of the Tesla charging stations.

Become a member

New, Relevant Tech Stories. Our article selection is done by industry professionals. Our writers summarize them to give you the key takeaways