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

121–130 of 184 posts

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

#121

Post by fendy3002 »

akiselev wrote: post #80
skrebbel wrote: post #79

Earlier quoted context omitted.

Yeah but… i can look through 100 log lines manually faster than writing a good gpt prompt. This would get useful if I can easily paste like 1M lines of logs (a few minutes of data for us), but even if that would work, it’d be prohibitively expensive I think. In other words, I still don’t completely grok the use case that’s being shared here.

The use case here is looking through logs for software that aren't familiar, especially stuff that gets touched too infrequently to internalize like, say, driver logs on a Linux workstation. If it's faster for you to read the logs yourself, you should continue to do that. If it's bespoke personal or commercial software, chances are GPT isn't going to be trained on its meaning anyway. Most people aren't going to be fa…

To add on it, sometimes adjacent logs can help to find solution, which by using the conventional google way, you'll need to analyze those yourself. With gpt, you don't need to, or they're helping you navigate on it.

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

#122

Post by abhgh »

simonw wrote: post #117
iso1631 wrote: post #83

Earlier quoted context omitted.

> OpenAI DO NOT WANT your private data in their training data But they do want it. I can see many old chat logs. Data is a liability. Does "clear conversations" in chat.openai.com actually remove them? Or jst mark them as "deleted", but they remain in a database. I just did a data export, then a clear conversation, then another data export. The second export was empty, which seems suspiciously fast to me

I didn't say they weren't storing the data - obviously they have to store it to provide the (popular) chat log feature. I said they didn't want it in the altar training data that they use for the pre-training phase of training future language models.

I'm genuinely trying to understand (based on this and another comment above): wouldn't storing data for pre-training vs fine-tuning carry the same risks?

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

#123

Post by stevenhuang »

qbasic_forever wrote: post #99
csomar wrote: post #88

Earlier quoted context omitted.

Strong disagree. Will be writing a blog post how GPT-4 understands languages that don't even exist (at least not formally).

It's confabulating (or hallucinating) meaning. GPT has no understanding of anything. Given an input prompt (tell me what this made up language sentence means for example), it's reaching into its training set and stochastically parroting a response. There is no cognition or understanding of language.

> it's reaching into its training set and stochastically parroting a response

Yes, this is how humans work too.

Also I hope the irony of trotting out this oft-repeated quip much like a stochastic parrot would isn't lost on you :P

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

#124

Post by 0xdeadbeefbabe »

Bootvis wrote: post #37
darkwater wrote: post #30

Earlier quoted context omitted.

> Making meal plans: what is being done here? making a list of meals to eat each day of the week? isn't this just a question of thinking what one would like to eat? why is it easier to have the meals chosen by someone else? Do you have children? Meal planning can be a quite tedious and frustrating task if you want to cook at home, eat healthy, eat tasty, vary the dishes and have meals that kids will accept.

In addition, for recipes, it’s just a better Google. If I do “Give me a concise recipe for X” it gives me one. No fluff, no ads. Just ingredients and steps. For example. I asked for pasta carbonara, concise and then even more concise. Final result: Quick Carbonara (4 servings) Ingredients: 12 oz pasta 4 eggs 1 cup cheese 8 oz bacon 4 garlic Salt, pepper Parsley (opt) Cook pasta, save water. Mix eggs, cheese. Fry baco…

Whoa, where's the backstory for that recipe. Guys, I think we need more AI safety.

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

#125

Post by ohgodplsno »

darkwater wrote: post #111
ohgodplsno wrote: post #98

Earlier quoted context omitted.

Great if you want italians to get a stroke upon reading that you're putting bacon in carbonara, as well as your arteries dying at the thoughts of the sheer amount of pasta you've just made.

Ahahaha as an Italian that made me laugh! Anyway I wonder if it would better to ask ChatGPT to give the recipe in Italian (so it pulls memories from the Italian blogosphere corpus) and then translate it to English (or your language of choice)

Don't worry, being french, I am used to making you guys get strokes. Carbonara with cream baby!

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

#126

Post by qbasic_forever »

stevenhuang wrote: post #123
qbasic_forever wrote: post #99

Earlier quoted context omitted.

It's confabulating (or hallucinating) meaning. GPT has no understanding of anything. Given an input prompt (tell me what this made up language sentence means for example), it's reaching into its training set and stochastically parroting a response. There is no cognition or understanding of language.

> it's reaching into its training set and stochastically parroting a response Yes, this is how humans work too. Also I hope the irony of trotting out this oft-repeated quip much like a stochastic parrot would isn't lost on you :P

No, humans don't work like your simplistic view of a neural network. I as a human can apply logic and deduction to figure out how something works despite never having experienced or learned about it directly for example. GPT cannot do this and can only guess or make up responses when faced with a problem that requires such reasoning.

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

#127

Post by famouswaffles »

13years wrote: post #118
famouswaffles wrote: post #113

Earlier quoted context omitted.

Base GPT-4 was highly calibrated. read open ai's technical paper. also, this paper on gpt-4 performance of medical challenge problems confirmed the high calibration for medicine https://arxiv.org/abs/2303.13375

Thanks, but I didn't find any details about performance of pre reinforcement training and after. Looking to understand more about the assertion that hallucinations are introduced by the reinforcement training.

https://arxiv.org/abs/2303.08774 The technical report has before and after comparisons. It's a bit worse on some tests. and they pretty explicitly mention the issue of calibration (how well confidence on a problem results in the ability or accuracy solving that problem).

Hallucinations are a different matter.

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

#128

Post by simonw »

abhgh wrote: post #122
simonw wrote: post #117

Earlier quoted context omitted.

I didn't say they weren't storing the data - obviously they have to store it to provide the (popular) chat log feature. I said they didn't want it in the altar training data that they use for the pre-training phase of training future language models.

I'm genuinely trying to understand (based on this and another comment above): wouldn't storing data for pre-training vs fine-tuning carry the same risks?

What risks are you talking about?

If you mean the risk that OpenAI will have their own security hole that leaks that stored data then yes.

If you mean the risk that someone will ask a question about your company and ChatGPT will answer with some corporate secrets then no.

This all depends very much on what they are using the ChatGPT data for. My theory is that they treat it very carefully to avoid "facts" from it being absorbed into the model - so even "fine tuning" may be inaccurate terminology here.

I really, really wish they would be more transparent about how they use this data.

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

#129

Post by stevenhuang »

qbasic_forever wrote: post #126
stevenhuang wrote: post #123

Earlier quoted context omitted.

> it's reaching into its training set and stochastically parroting a response Yes, this is how humans work too. Also I hope the irony of trotting out this oft-repeated quip much like a stochastic parrot would isn't lost on you :P

No, humans don't work like your simplistic view of a neural network. I as a human can apply logic and deduction to figure out how something works despite never having experienced or learned about it directly for example. GPT cannot do this and can only guess or make up responses when faced with a problem that requires such reasoning.

GPT cannot do this? Not even a bit?

Well... that's definitely an opinion. A reasonable person would grant it _some_ level of reasoning ability, however flawed.

To dismiss it all as 'pattern matching' rather shows some confused ideas about how cognition works, as if pattern matching plays no role in human cognition or intelligence.

I'll understand difference in opinion if we're talking about more nebulous aspects like consciousness or qualia...

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

#130

Post by esafak »

lumb63 wrote: post #106

What’s wrong with “grep -i error”? That gets me to the source of the error, usually.

1. You don't know what the error means, or how to resolve it. 2. The real error can be surrounded by a wall of other errors and you have to figure out the root cause.
Post reply on HN