Sign up to save tools and stay up to date with the latest in AI
bg
bg
1

LLMs are not suitable for brainstorming

May 16, 2024 - piaoyang0.wordpress.com
The author discusses the limitations of large language models (LLMs) like GPT-4 in brainstorming and creative thinking. While acknowledging that LLMs can demonstrate some form of independent and creative thinking, the author argues that they are not effective tools for brainstorming, especially in cutting-edge scenarios. This is because LLMs are trained to mimic existing patterns in human-produced data and not specifically taught to brainstorm. They often converge to the consensus in existing data, and their idea generation tends to align with the frequency and attention given by the media and main info sources, which can overshadow the evaluation of these ideas based on their actual practicality and creativity.

The author suggests that this is a fundamentally hard problem in the current LLM scheme and proposes potential solutions. These include curating a fine-tune dataset of good brainstorm examples on non-conventional topics, using methods like RLAIF to iteratively critique LLM’s response in terms of creativity, and changing the training process to seek out knowledge, thinking, and deductive reasoning skills. The author also raises several big questions in the field, such as the need for a world model, the correct paradigm for AGI, and the need for real-world feedback to reach AGI.

Key takeaways:

  • Language Learning Models (LLMs) like GPT-4 have some independent and creative thinking abilities, but they are not good tools for effective brainstorming, especially in cutting-edge scenarios.
  • LLMs are trained to follow existing patterns in human-produced corpus and not natively taught to brainstorm, often converging to consensus in existing data.
  • LLMs are only suitable for better-than-average level brainstorms and cannot provide much useful insights for truly frontier problems.
  • The author suggests potential solutions such as curating a good fine-tune dataset of good brainstorm examples, using methods like RLAIF to critique LLM’s response in terms of creativity, and changing the training process to seek out knowledge, thinking and deductive reasoning skills.
View Full Article

Comments (0)

Be the first to comment!