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

Don't believe ChatGPT – we do not offer a "phone lookup" service

blog.opencagedata.com

Post reply on HN
Print view View original

91–100 of 284 posts

Re: Don't believe ChatGPT – we do not offer a "phone lookup" service

#91

Post by circuit10 »

coldtea wrote: post #24

ChatGPT doesn't "recommended" anything. It just recombines text based on statistical inferences that appear like a recommendation. It could just as well state that humans have 3 legs depending on its training set and/or time of day. In fact it has said similar BS.

> ChatGPT doesn't "recommended" anything. It just recombines text based on statistical inferences that appear like a recommendation.

I think that’s a bit pedantic and not very helpful… I’m not typing this comment, my brain is just sending signals to my hands which causes them into input data into a device that displays pixels that look like a comment

Re: Don't believe ChatGPT – we do not offer a "phone lookup" service

#92

Post by simonw »

hk__2 wrote: post #21
CabSauce wrote: post #10

Earlier quoted context omitted.

Not quite as alarming as these people most likely trying to stalk someone without their permission.

> Not quite as alarming as these people most likely trying to stalk someone without their permission. It’s so common to want to know where does a incoming call come from that it’s built-in in iOS. It has nothing to do with stalking, just with guessing if who’s calling you is a scammer or a company trying to sell you stuff.

I'm willing to bet people asking ChatGPT to help them resolve a phone number to a location are much more likely to be stalkers than people who are trying to identify spam calls.

Re: Don't believe ChatGPT – we do not offer a "phone lookup" service

#93

Post by gumballindie »

ChatGPT is hilariously buggy - I asked “it” how to use an open source library i made. The output was wrong ranging from a broken github url to outright broken or nonexistent code. I suspect it may even have used private code from other libs - couldnt find some of the output it generated anywhere public.

Re: Don't believe ChatGPT – we do not offer a "phone lookup" service

#94

Post by IncRnd »

behnamoh wrote: post #76
snowstormsun wrote: post #62

Earlier quoted context omitted.

I think "Explainable AI" is a related research direction, but perhaps not popular for language models.

Impossible to explain the inner workings of GPT-3 without having access to the model and its weights. Does anyone know if any methods exist for this?

I asked ChatGPT for some in-depth source code that realistically mimics chatgpt. ChatGPT replied with various answers in python. I'm not sure any of them are correct, though.

Re: Don't believe ChatGPT – we do not offer a "phone lookup" service

#95

Post by worldsayshi »

insane_dreamer wrote: post #77
mort96 wrote: post #15

That's quite the predicament. I hope OpenAI will listen, to this and to anyone else in a similar situation. I'm reminded of the cases of ChatGPT recommends random people's personal phone numbers for various services. But yeah, don't trust ChatGPT for anything. Just earlier today I tried my darnedest to convince it that 2 pounds of feathers doesn't weigh the same as 1 pound of bricks, and it just would not listen, pre…

> don't trust ChatGPT for anything Agreed. But then it begs the question: what purpose does ChatGPT serve (other than for entertainment purposes or cheating on your HS/college exam)? If you have to verify its information by other means, then you're not really saving much effort.

This was my initial thought as well. But I've noticed that my brain has started to find tasks that it would be quite useful for. Too bad it's almost always seem to be at capacity when I think of those cases. Guess I will have to pay up to figure out if it's actually worth it.

Re: Don't believe ChatGPT – we do not offer a "phone lookup" service

#96

Post by nl »

crazygringo wrote: post #54

I'm curious -- does anyone know of ML directions that could add any kind of factual confidence level to ChatGPT and similar? We all know now that ChatGPT is just autocomplete on steroids. It produces plausibly convincing patterns of speech. But from the way it's built and trained, it's not like there's even any kind of factual confidence level you could threshold, or anything. The concept of factuality doesn't exist…

> does anyone know of ML directions that could add any kind of factual confidence level to ChatGPT and similar?

Yes. It's a very active area of research. For example:

Discovering Latent Knowledge in Language Models Without Supervision (https://arxiv.org/abs/2212.03827) shows an unsupervised approach for probing a LLM to discover things it thinks are facts

Locating and Editing Factual Associations in GPT (https://arxiv.org/pdf/2202.05262.pdf) shows an approach to editing a LLM to edit facts.

Language Models as Knowledge Bases? (https://aclanthology.org/D19-1250.pdf) is some slightly older work exploring how well LLMs store factual information itself.

Re: Don't believe ChatGPT – we do not offer a "phone lookup" service

#97

Post by shagie »

VectorLock wrote: post #88

This is the biggest problem I encounter when trying to use ChatGPT on a daily basis for computer programming tasks. It "hallucinates" plausible looking code that never existed or would never work, especially confusing whats in one module or API for something in another. This is where ChatGPT breaks when pushed a bit further than "make customized StackOverflow snippets." For example I asked ChatGPT to show me how to u…

Have you tried using the code-davinci-002 model instead of ChatGPT?

For example - https://platform.openai.com/playground/p/default-translate-c...

The codex models are intended for doing work with code rather than language and may give better results in that context. https://help.openai.com/en/articles/6195637-getting-started-...

Re: Don't believe ChatGPT – we do not offer a "phone lookup" service

#98

Post by IncRnd »

VectorLock wrote: post #88

This is the biggest problem I encounter when trying to use ChatGPT on a daily basis for computer programming tasks. It "hallucinates" plausible looking code that never existed or would never work, especially confusing whats in one module or API for something in another. This is where ChatGPT breaks when pushed a bit further than "make customized StackOverflow snippets." For example I asked ChatGPT to show me how to u…

It does indeed sound problematic to use ChatGPT daily for computer programming tasks. ChatGPT is not a snippets manager but text completion.

It may be more helpful to look for better answers on Amazon's help pages for SNS and AWS SDK.

Re: Don't believe ChatGPT – we do not offer a "phone lookup" service

#99

Post by int_19h »

codetrotter wrote: post #69
ninjakeyboard wrote: post #17

ChatGPT gets the rules to the pokemon trading card game wrong. It will tell you you can use 4 energy a turn. Convincingly. Not sure how it hallucinates this. The rule is 1 per turn.

A few days ago I asked ChatGPT if “pannekake” and “kannepake” are anagrams of each other. It correctly stated that they are, but when it went on to prove that this was the case, it generated a table of the frequencies of the individual letters in these two words, and the table looked like this. Letter | Frequency in | Frequency in | “pannekake” | “kannepake” - - - - - - - - - - - - - - - - - - - a | 2 | 2 e | 2 | 2 k…

Anything that has to do with individual words doesn't work well, but as I understand, this is an artifact of the tokenization process. E.g. pannekake is internally 4 tokens: pan-ne-k-ake. And I don't think that knowing which tokens correspond to which letter sequences is a part of the training data, so it has to infer that.

Re: Don't believe ChatGPT – we do not offer a "phone lookup" service

#100

Post by nl »

renewiltord wrote: post #46
Xylakant wrote: post #23

Earlier quoted context omitted.

> Because ChatGPT is so new, we are in this weird period where people haven't learned that is just as incorrect as the rest of us. It’s worse than that. It’s wrong, you cannot correct it and it makes up supporting citations on the fly. Very few humans behave like that.

I think very many humans behave like that, actually. A recent example is people claiming that Flint, MI still has leaded water. But in the past, HN users "corroborated" that Apple is spying on them etc. Fabrication is well and alive among us.

> A recent example is people claiming that Flint, MI still has leaded water.

Doesn't it?

According to [1]:

The residential lead service line replacement was initially set to be finished in 2019, according to a settlement agreement with the city. That deadline was eventually pushed back to the fall of 2022 and has most recently been set for completion in August 2023, according to city officials.

and

"More than 95% of lead pipes in Flint have been replaced, and we will continue the work until the job is done," Flint Mayor Sheldon Neeley said in a recent statement on the water filters.

It sounds to me a lot like Flint, MI still has leaded water?

[1] https://abcnews.go.com/US/flint-residents-urged-filter-water...

Post reply on HN