I know a ton of people absolutely hate this level of "LLM code + LLM PR description + LLM PR review" but my boss would have an orgasm if I was able to use AI half as well in our org... :/
My conclusion from the project I'm working on is that, as of this day, there is no way to have both this so-called 20x performance improvement _and_ any kind of quality. Or security if whoever is running the agent has any token in an .env anywhere on the same file system.
We'll see in which direction the CTO takes this. My bet is not on quality.
It is sad. This is a new reality. No one reads code, it is agents all the way down. It has been long enough now that I can safely say AI has not sped up project delivery nor improved quality when it did ship.
It is sad. This is a new reality. No one reads machine code, it is compilers all the way down. It has been long enough now that I can safely say C has not sped up project delivery nor improved quality when it did ship.
I'm not so sure this is true anymore. It may have been years ago but... can you honestly say "the Bun project was fully AI written, therefore the quality is poor"?