Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AI for AWS Documentation

awsdocsgpt.com

Post reply on HN
Print view View original

91–100 of 134 posts

Re: AI for AWS Documentation

#91

Post by jacurtis »

mjhay wrote: post #72

It can't be worse than Amazon's own AWS documentation.

To be fair to AWS, their documentation has improved dramatically the past 24 months or so. Not perfect, but the difference between 2019 and 2023 is dramatic.

Also, I'd argue that it is very easy to be worse than AWS's own docs. A chatbot that hallucinates inaccurate answers, while sounding plausible and confident is far worse than documentation that is 100% accurate, but lacking in some areas.

I'd rather receive an answer of "I don't know" or "it isn't documented" than an explanation that seems legit, so I spend 15 hours building a solution in accordance to a LLM's response and then find out that its not possible or real the way it was explained by the LLM.

Re: AI for AWS Documentation

#92

Post by NoZebra120vClip »

What if you could train an LLM on the body of source code for AWS (or whatever you choose as your SaaS) and so it would actually know deeply, exactly, intimately exactly how AWS works, and how to do anything and everything in it? Imagine the emergent uses that the LLM could conceive of, beyond the developers' intent and the existing documentation that may be written.

With the bonus effect that you could retrain the LLM as often as you like, as new software is released, and it could always be aware of the latest features (and even the bugs and vulnerabilities.)

Re: AI for AWS Documentation

#93

Post by jitix »

ec109685 wrote: post #87

Asked it whether you should use a shared vpc: Made this up as reason for dedicated vpc: “Better performance: By using dedicated hardware, you have better control over the performance of your instances in the VPC. This can be beneficial for applications that have stringent performance requirements.”

I think ChatGPT and LLM models in general are more suited for "What is xyz" or "How is xyz done" family of questions. Basically a smart search engine.

Beyond that it will simply have the output/personality of a person with rote-memory.

Re: AI for AWS Documentation

#94

Post by klysm »

jacurtis wrote: post #86
scarface_74 wrote: post #41

Earlier quoted context omitted.

One of my pet peeves about almost every answer on Stack Overflow is that the answer always starts with client=boto3.client( , access-key,secret-key) There is never a reason to include those last two parameters. It’s always a security risk no matter how you do it.

For that matter, using an access-key or secret-key at all is basically an anti-pattern now. In the past few months AWS has added to their UI a popup box that asks you why you are creating access keys, it makes you answer it before generating the keys. Once you give it the answer it tells you better ways to do almost anything you're trying to do, and you have to agree to ignore those suggestions one more time before a…

I really do appreciate the effort they’ve gone through there though - they didn’t have to.

Re: AI for AWS Documentation

#95

Post by esquire_900 »

klysm wrote: post #94
jacurtis wrote: post #86

Earlier quoted context omitted.

For that matter, using an access-key or secret-key at all is basically an anti-pattern now. In the past few months AWS has added to their UI a popup box that asks you why you are creating access keys, it makes you answer it before generating the keys. Once you give it the answer it tells you better ways to do almost anything you're trying to do, and you have to agree to ignore those suggestions one more time before a…

I really do appreciate the effort they’ve gone through there though - they didn’t have to.

I think they do. Given the damage that leaked keys can do (especially in the Bitcoin mining area) it must be an expensive problem for them.

Re: AI for AWS Documentation

#96

Post by Aeolun »

It doesn’t distinguish between HTTP api gateway and REST api gateway.

When asked how to create a private HTTP gateway it happily tells you how to do it , but it’s actually impossible.

Re: AI for AWS Documentation

#97

Post by Aeolun »

jacurtis wrote: post #90
8note wrote: post #54

Earlier quoted context omitted.

This all looks about right, but how would somebody without aws experience be able to validate it without making a mess?

This to me is why I don't use ChatGPT. Every time I use it I get answers that are questionable in validity. I'd say that 3/4 of my questions have returned incorrect answers at least partially. Maybe 10% are wildly incorrect with the remainder being partially incorrect. So if it is wrong with MOST of the questions that I am able to validate myself, then how can I trust it on the questions that I am unable to validate…

Why’d he be so reluctant to confess to using ChatGPT? And why would he continue using it despite constant feedback that his performance was getting so much worse?

Re: AI for AWS Documentation

#98

Post by Aeolun »

avereveard wrote: post #78
8note wrote: post #54

Earlier quoted context omitted.

This all looks about right, but how would somebody without aws experience be able to validate it without making a mess?

It still isn't tho, this will work for testing, maybe, but each lambda will be it's own connection and that will exhaust db resources real fast, you're supposed to have a pooling proxy between lambdas and RDS.

Depends, if every lambda creates a single connection you can get to pretty high numbers before it becomes an issue.

Re: AI for AWS Documentation

#100

Post by SV_BubbleTime »

>This action allows you to filter your things based on the attribute name and value. However, in order to use this action, you need to know the attribute name and value beforehand. Since you don't know the attributes ahead of time, this method won't work for your case.

Well… Thanks a ton for that!

Great idea and setup, but not quite as helpful as I would like yet.

Post reply on HN