I’ve seen a few articles saying that instead of hating AI, the real quiet programmers young and old are loving it and have a renewed sense of purpose coding with llm helpers (this article was also hating on ed zitiron, which makes sense why it would).
Is this total bullshit? I have to admit, even though it makes me ill, I’ve used llms a few times to help me learn simple code syntax quickly (im and absolute noob who’s wanted my whole life to learn code but cant grasp it very well). But yes, a lot of time its wrong.
Phind has been decent for me when I’m looking for prior art and/or research papers on something I’m trying to develop/implement. It’s nice to be able to pose a question as I would to a colleague and get references back that I can read for myself.
Sadly, it still hallucinates some stuff, and when it doesn’t it tends to give me references that are tangentially related to my query but don’t actually cover it.