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

Tell HN: ChatGPT is fantastic for finding and solving issues in logs

news.ycombinator.com

Post reply on HN
Print view View original

61–70 of 184 posts

Re: Tell HN: ChatGPT is fantastic for finding and solving issues in logs

#61

Post by waboremo »

TacticalCoder wrote: post #26

How does that work with logs? Logs are often... Huge? How many lines of logs can you paste? Because if I first need to narrow down the log to the problematic part, I kinda already have my problem right there no? Or do you mean I do something like grab the lines with "error" in the log, hoping there aren't too many, then ask ChatGPT what it thinks about this: [ 0.135036] kernel: ACPI Error: AE_NOT_FOUND, During name l…

Why wouldn't you use a basic filter on logs before even reading them (or passing them elsewhere)? Maybe even get ChatGPT to write that for you if you're so inclined but it can just be a simple command as grep works fine.

After that, even if it's still a massive file, chunking it to ChatGPT should work within its limits (although I haven't personally used it for logs so I can't recommend this).

Re: Tell HN: ChatGPT is fantastic for finding and solving issues in logs

#62

Post by q7xvh97o2pDhNrh »

ttul wrote: post #33

I used it to transform cryptic credit card statement items into company names, which then allowed me to query my Gmail archives for receipts and invoices from these vendors, automating a manual process of accounting backup discovery that is the bane of my very existence. I even got GPT-4 to assess whether an email likely relates to an invoice or payment so that I could limit the amount of noise extracted from my emai…

I keep seeing anecdotes like this, and I wonder: How do you feel about the privacy aspect of this?

To do this, you had to feed your email into GPT-4, right?

Re: Tell HN: ChatGPT is fantastic for finding and solving issues in logs

#63

Post by therein »

dragonwriter wrote: post #32
williamcotton wrote: post #29

Earlier quoted context omitted.

Considering the fact that the RLHF for ChatGPT was done only in English but then worked just as well for every other language I would wager that specific types of logs being present in the training set is less important than it may seem.

> Considering the fact that the RLHF for ChatGPT was done only in English but then worked just as well for every other language Does it work just as well for every other language, or does it work acceptably well for an important subset of other languages?

It works well for a surprisingly large set. My tests involved Turkish and Azerbaijani and I'd assume it is distant enough that I was impressed.

Re: Tell HN: ChatGPT is fantastic for finding and solving issues in logs

#64

Post by garysahota93 »

ttul wrote: post #33

I used it to transform cryptic credit card statement items into company names, which then allowed me to query my Gmail archives for receipts and invoices from these vendors, automating a manual process of accounting backup discovery that is the bane of my very existence. I even got GPT-4 to assess whether an email likely relates to an invoice or payment so that I could limit the amount of noise extracted from my emai…

Would you be open to making this logic open source? I'd LOVE to do this as well. (I use LunchMoney.app for all spend tracking, but don't have my receipts logged)

Re: Tell HN: ChatGPT is fantastic for finding and solving issues in logs

#65

Post by sharemywin »

zeroDivisible wrote: post #28

This is a great feature and I did use it few times to test. However, be aware of potentially leaking your company's private or sensitive information when doing this.

https://openai.com/policies/api-data-usage-policies

OpenAI will not use data submitted by customers via our API to train or improve our models, unless you explicitly decide to share your data with us for this purpose. You can opt-in to share data.

Any data sent through the API will be retained for abuse and misuse monitoring purposes for a maximum of 30 days, after which it will be deleted (unless otherwise required by law). The OpenAI API processes user prompts and completions, as well as training data submitted

Re: Tell HN: ChatGPT is fantastic for finding and solving issues in logs

#66

Post by ReaLNero »

dragonwriter wrote: post #32
williamcotton wrote: post #29

Earlier quoted context omitted.

Considering the fact that the RLHF for ChatGPT was done only in English but then worked just as well for every other language I would wager that specific types of logs being present in the training set is less important than it may seem.

> Considering the fact that the RLHF for ChatGPT was done only in English but then worked just as well for every other language Does it work just as well for every other language, or does it work acceptably well for an important subset of other languages?

I speak a Slavic language spoken by ~2 million people, and I asked GPT-4 to tell me an old fable in my language. It did so fantastically, with no grammatical errors. I tried some more things -- it speaks it fluently, though admittedly not always idiomatically.

Re: Tell HN: ChatGPT is fantastic for finding and solving issues in logs

#67

Post by croes »

toomuchtodo wrote: post #8
swah wrote: post #2

Yesterday I dumped a broken markdown table and asked for the first "column" as CSV values. Works really well for this stuff too.

I love that it’s replacing sed, awk, and cut in the same way you’d bring artillery to a knife fight.

But sed, awk etc.results are predictable and reproducible.

That's not guaranteed with ChatGPT.

Re: Tell HN: ChatGPT is fantastic for finding and solving issues in logs

#68

Post by ogogmad »

mrbungie wrote: post #18
toomuchtodo wrote: post #8

Earlier quoted context omitted.

I love that it’s replacing sed, awk, and cut in the same way you’d bring artillery to a knife fight.

I've seen some really f**ed up text formatted files in the wild. In those cases I really see value in using something more "intelligent" (and declarative rather than imperative) rather than coding a non-trivial number of [python|bash] lines of code, especially when dealing with one-timers.

I think our operating systems are going to have this stuff installed one day. It might replace most uses of the CLI.

Re: Tell HN: ChatGPT is fantastic for finding and solving issues in logs

#69

Post by phlip9 »

Yeah it's pretty awesome! I used GPT-4 last week to fix my corrupted SSD. Granted I already narrowed down the kernel logs to a few suspicious lines, but I just pasted those 10 lines in and asked for a fix. Pasting in GPT's arcane `fsck` incantations and boom -- fixed SSD. Saved me an hour or two of hassle reading man pages and stack overflow posts.

Re: Tell HN: ChatGPT is fantastic for finding and solving issues in logs

#70

Post by simonw »

q7xvh97o2pDhNrh wrote: post #62
ttul wrote: post #33

I used it to transform cryptic credit card statement items into company names, which then allowed me to query my Gmail archives for receipts and invoices from these vendors, automating a manual process of accounting backup discovery that is the bane of my very existence. I even got GPT-4 to assess whether an email likely relates to an invoice or payment so that I could limit the amount of noise extracted from my emai…

I keep seeing anecdotes like this, and I wonder: How do you feel about the privacy aspect of this? To do this, you had to feed your email into GPT-4, right?

I think there's a widely held misconception that anything you paste into GPT-4 will be used as raw training data by the model.

Some people even seem to believe that it's learning continuously, so something you paste in could show up in an answer for another user a few minutes later.

My mental model of how this works is somewhat different:

- It takes months to train a model on raw data, and OpenAI train new ones (that get released to the public) quite infrequently.

- OpenAI DO NOT WANT your private data in their training data. They put a great deal of work into stripping out PII from the training data that they do use already (this is described in their papers). They're not going to just paste in anything that anyone typed into that box.

Here's the problem though: they DO use ChatGPT interactions to "improve" their services. I don't think that means piping the data directly into training, but they clearly log everything and use those interactions as part of subsequent rounds for things like fine-tuning and RLHF.

Also they had that embarrassing bug a few weeks ago where some users could see the titles of conversations had by other users.

So it's not irrational to worry about pasting data into GPT-4 - it gets logged, and it could leak by accident.

But I'm confident that data passed to ChatGPT isn't being piped in as raw training data for subsequent versions of their live models.

(I hope I'm right about this though - I thought about blogging it, but OpenAI's transparency isn't good enough that I'd feel comfortable staking my reputation on this)

Post reply on HN