According to OpenAI's blog, Codex excels most at "mapping... simple problems to existing code", which they describe as "probably the least fun part of programming".
[11] OpenAI claims that Codex can create code in over a dozen programming languages, including Go, JavaScript, Perl, PHP, Ruby, Shell, Swift, and TypeScript, though it is most effective in Python.
Additionally, they brought up several safety issues, such as over-reliance by novice programmers, biases based on the training data, and security impacts due to vulnerable code.
[9] According to a study by researchers from New York University, approximately 40% of code generated by GitHub Copilot (which uses Codex) in scenarios relevant to high-risk CWEs included glitches or other exploitable design flaws.
[14] The Free Software Foundation expressed concerns that code snippets generated by Copilot and Codex could violate copyright, in particular the condition of the GPL that requires derivative works to be licensed under equivalent terms.
In one example the model outputted the training data code implementing the fast inverse square root algorithm, including comments and an incorrect copyright notice.