The article reflects on the author's experiences with various large language models (LLMs) since discovering their potential for coding through OpenAI's ChatGPT. The author evaluates 14 different LLMs with real-world programming tasks and highlights that just four can be recommended for creating working plugins. While ChatGPT Plus and Perplexity Pro are notable for their performance, the author notes that free versions often suffice. However, many LLMs do not meet programming needs especially for larger projects, with mixed results in quantifying AI productivity when coding.
Not all chatbots can code alike. It's been a little over two years since that first test, and even now, four of the 13 LLMs I tested can't create working plugins.
I've tested 14 large language models... Four chatbots I recommend you use include ChatGPT Plus and Perplexity Pro, both costing $20/month.
The free versions of ChatGPT and Perplexity do well enough that you could probably get by without paying, but AI productivity varies widely.
Unless it's a small, simple project, AIs can't write entire apps or programs, but they excel at writing a few lines and fixing code.
Collection
[
|
...
]