Hacker News Reader

Comment by sovietmudkipz | Hacker News Reader

This is exactly the kind of software that people should be making. Even if this one is bad, the concept is very sound.

I want to have a specialist AI that is trained to help me learn how to use the software. 100% what should be happening.

General AI should know how to do stuff too but having an specialist AI implies that the company/group of people/person is making sure to tune the model.

Just an IMO.

View on HN

MDN implemented an "AI explains" feature, and the reception is extremely negative.

https://github.com/mdn/yari/issues/9208

Is it? It's true there are a lot of very loud messages on that linked issue, but only MDN knows how many people are using and engaging with their system compared to on that thread. We, as the general public, don't know anything other than there's a vocal group of dissidents, and what MDN tells us. Which I looked and didn't find stats on its usage.

Why?

You can ask the same questions to ChatGPT and get the same or better answers.

I also know from personal experience with ChatGPT, that you can use it to:

- convert Python/boto3 to any language that has an AWS SDK

- convert CloudFormation to Terraform or the CDK

- write scripts that use the SDK

You will get the occasional hallucination.

Ideally, specialist models are small enough to run locally.

Here's one example question that ChatGPT utterly fails at, but that this answers fine: "What is Amazon CodeCatalyst?"

ChatGPT: "I'm sorry, but as of my knowledge cut-off in September 2021, there was no service, tool, or product known as Amazon CodeCatalyst offered by Amazon Web Services (AWS). [...]"

A lot of stuff in AWS has changed since Q3 2021.

It feels like the AWS vendor lock-in strategy is constant change.

ChatGPT is not up to date unless you start using the plugins. This sort of indexing is based on vector databases and various intermediate prompting. If you want to get technical, the academic term is "Retrieval Augmented Generation".

Hallucination is unfortunately inevitable when it comes to any autoregressive model, even with RAG. You can minimize hallucination by prompting, but you'll still see some factually incorrect responses here and there (https://zilliz.com/blog/ChatGPT-VectorDB-Prompt-as-code).

I unfortunately don't think we'll be able to solve hallucination anytime soon. Maybe with the successor to the transformer architecture?

Hallucination is naturally a concern for anyone looking to depend upon LLM-generated answers.

We’ve been testing LLM responses with a CLI, we’re using it to generate accuracy statistics, which is especially useful when the use-case Q/A is limited.

If ‘confidence’ can be returned to the user, then at least they can have an indication if there is a higher quality-risk with a given response.

I was looking at the CloudLinux[1] docs the other day and noticed an "Ask GPT?" feature which I found quite helpful.

[1] https://docs.cloudlinux.com

Reply on news.ycombinator.com