Comment by Rapzid
19 hours ago
I think we've all seen where an LLM names a session, issue, or PR based on its early understanding and fails update it later.
AI isn't being asked to review the title, and it doesn't have experience or think, so of course it's not going to flag it.
No human reviews anything anymore so of course they aren't going to catch it.
Edit: AI for as good as it is at "writing" is terrible at writing and particularly at naming things. I had an AI name a client OpenAICompatibleEmbeddingClient. "Brooooo.. I think "compatible" is implied, who names stuff like that?!"
That means that it supports other services with OpenAI-compatible embeddings APIs (not just OpenAI's own API). Seems reasonable!
`OpenAICompatible` is also a widely used phrasal description of a part/version of the OpenAI API that is supported by quite a lot of endpoints.
- https://lmstudio.ai/docs/developer/openai-compat
I've seen that used as a description for 2years or so.
Fortunately I didn't ask it for excuses and so it didn't give them like a pedantic junior on the spectrum.
Which they will happily do if you ask them "why" they did something. 100% they will give their best "well actually" impression.
LLM-based AI is a synthesis of human observed behavior
But does it bring synergy with our current paradigm?
Descriptive type names are a good thing. Id argue that one isnt that bad, but llms do take it to another level sometimes.