Some thoughts on LLMs and software development

> My former colleague Rebecca Parsons, has been saying for a long time that hallucinations aren’t a bug of LLMs, they are a feature. Indeed they are the feature. All an LLM does is produce hallucinations, it’s just that we find some of them useful.

What a great way of framing it. I've been trying to explain this to people, but this is a succinct version of what I was stumbling to convey.

I have been explaining this to friends and family by comparing LLMs to actors. They deliver a performance in-character, and are only factual if it happens to make the performance better.

https://jstrieb.github.io/posts/llm-thespians/

The analogy goes down the drain when a criterion for good performance is being objectively right. Like with Reinforcement Learning from Verifiable Rewards.

Nobody that I'd be using this analogy with is currently using LLMs for tasks that are covered by RLVF. They're asking models for factual information about the real world (Google replacement), or to generate text (write a cover letter), not the type of outputs that are verifiable within formal systems—by definition the type of output that RLVF is intended to improve. The actor analogy is still helpful for providing intuition to non-technical people who don't know how to think about LLMs, but do use them.

Also, unless I am mistaken, RLVF changes the training to make LLMs less likely to hallucinate, but in no way does it make hallucination impossible. Under the hood, the models still work the same way (after training), and the analogy still applies, no?