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

OpenAI Finally Allows ChatGPT Complete Internet Access

gizmodo.com

Post reply on HN
Print view View original

51–60 of 118 posts

Re: OpenAI Finally Allows ChatGPT Complete Internet Access

#51

Post by rrrix1 »

civilitty wrote: post #28
simonw wrote: post #13

I've been relatively unimpressed with the ChatGPT browse mode. My problem with it is that it seems to run really obvious, naive searches. Most of the time I ask it something, then see what it's searching for and think "oh no, that's not going to return anything more useful than what I could have found myself". It's also pretty slow. I'm very much looking forward to having a search assistant which can go ahead and wad…

It’s also pretty useless at understanding any page that’s even remotely complex. I asked it to tell me when the next baseball home game is so I can avoid traffic when going to the downtown library and it couldn’t answer even that basic question. The search results defaulted to the team’s official calendar but the day numbers were displayed as images so they could style them in the team’s font, making them invisible t…

This example is more likely due to that specific page/site lacking any kind of accessibility information (e.g. how people who are blind, deaf or have other disabilities can use the internet), rather than being large or complex.

Relatedly, in my experience, for some reason most internet properties relating to anything sports related (MLB, NFL, NHL, or even small town little league) have absolutely terrible, extremely over complicated user interfaces.

Re: OpenAI Finally Allows ChatGPT Complete Internet Access

#52

Post by CSMastermind »

zachthewf wrote: post #17
simonw wrote: post #13

I've been relatively unimpressed with the ChatGPT browse mode. My problem with it is that it seems to run really obvious, naive searches. Most of the time I ask it something, then see what it's searching for and think "oh no, that's not going to return anything more useful than what I could have found myself". It's also pretty slow. I'm very much looking forward to having a search assistant which can go ahead and wad…

Have you tried perplexity.ai? It has become my go-to for LLM + browsing. It is really fast and does a pretty good job with retrieval and summarization.

Do you know what model perplexity uses under the hood?

I just tried it out with my normal test queries and found it to be far worse than Google's Bard.

Re: OpenAI Finally Allows ChatGPT Complete Internet Access

#53

Post by kelseyfrog »

setuid9002 wrote: post #14
judge2020 wrote: post #3

Earlier quoted context omitted.

This time it's not scraping the internet (like a robot) but actually acting as a direct user agent for the human typing their prompt, so I wouldn't be against them ignoring robots.txt.

Wait, so a simple web scraper script has to comply with robots.txt. But if I want to completely ignore the robots.txt, I only have to make my script more complicated (ChatGPT)?

Yeah, it's like one weird trick for web scraping.

Re: OpenAI Finally Allows ChatGPT Complete Internet Access

#54

Post by kelseyfrog »

londons_explore wrote: post #45
gumballindie wrote: post #36

Is there a complete list of ip addresses openai uses for scraping? I suppose they dont honour robots.txt, despite claiming to do so, and this may be one way to reliably block them.

I've seen no suggestion of them not honouring robots.txt... I suspect that any case of them not honoring it is probably due to your site content being available on archive.org or common crawl or some other service.

Is there an open license or ToS that would disallow OpenAI access?

Re: OpenAI Finally Allows ChatGPT Complete Internet Access

#55

Post by Spivak »

jtbayly wrote: post #38
rolisz wrote: post #10

Earlier quoted context omitted.

Your browser is also automating things, you're not resolving DNS and writing all the http requests by hand.

So because something is automated somewhere, nobody has to follow robots.TXT anymore?

You have it backwards, when a human initiates the request, like clicking on a link, your browser (rightfully) will ignore robots.txt. Unattended requests like scrapers do respect robots.txt. This is a case where ChatGPT is acting more like a browser with a funny way of displaying the final result. Each request is initiated by a human so it would likely be reasonable to ignore it in this case.

Re: OpenAI Finally Allows ChatGPT Complete Internet Access

#56

Post by spott »

Reviving1514 wrote: post #30
wordpad25 wrote: post #26

Earlier quoted context omitted.

ChatGPT, Claude and prepexity are each $20/mo Chatgpt4 seems most powerful but Claude offers unlimited context which can be used to summarize entire books Prepexity can browse and summarize web Which one should I subscribe to?

Kagi ultimate is 25 a month and has Claude, GPT4, and AI web search. Been using it a month or so and it's great.

Do you have a source for that? All I can find is here [0], which doesn't mention GPT4 or Claude.

[0]https://help.kagi.com/kagi/plans/ultimate-plan.html

Re: OpenAI Finally Allows ChatGPT Complete Internet Access

#57

Post by dewey »

spott wrote: post #56
Reviving1514 wrote: post #30

Earlier quoted context omitted.

Kagi ultimate is 25 a month and has Claude, GPT4, and AI web search. Been using it a month or so and it's great.

Do you have a source for that? All I can find is here [0], which doesn't mention GPT4 or Claude. [0] https://help.kagi.com/kagi/plans/ultimate-plan.html

> For Starter and Professional members this mode uses gpt-3.5-turbo, and for Ultimate members it uses gpt-4.

https://help.kagi.com/kagi/ai/assistant.html

Re: OpenAI Finally Allows ChatGPT Complete Internet Access

#58

Post by spott »

karaterobot wrote: post #31
judge2020 wrote: post #3

Earlier quoted context omitted.

This time it's not scraping the internet (like a robot) but actually acting as a direct user agent for the human typing their prompt, so I wouldn't be against them ignoring robots.txt.

My understanding is that the philosophy behind robots.txt is owners not wanting their content automatically included in someone else's product, if not duplicated and recorded wholesale. The important idea seems to be ownership, not the ability to browse. If OpenAI had two agents, one with no memory, and one with a memory, that would be better: you could disallow ChaptGPT-storage and allow ChatGPT-user, for example. B…

https://platform.openai.com/docs/plugins/bot/chatgpt-user-an...

There are two agents, but apparently you can't allow one but disallow another.

Re: OpenAI Finally Allows ChatGPT Complete Internet Access

#59

Post by 13rac1 »

CSMastermind wrote: post #52
zachthewf wrote: post #17

Earlier quoted context omitted.

Have you tried perplexity.ai? It has become my go-to for LLM + browsing. It is really fast and does a pretty good job with retrieval and summarization.

Do you know what model perplexity uses under the hood? I just tried it out with my normal test queries and found it to be far worse than Google's Bard.

Paid accounts can use the Perplexity LLM, GPT-4, or Claude 2.

Re: OpenAI Finally Allows ChatGPT Complete Internet Access

#60

Post by spott »

dewey wrote: post #57
spott wrote: post #56

Earlier quoted context omitted.

Do you have a source for that? All I can find is here [0], which doesn't mention GPT4 or Claude. [0] https://help.kagi.com/kagi/plans/ultimate-plan.html

> For Starter and Professional members this mode uses gpt-3.5-turbo, and for Ultimate members it uses gpt-4. https://help.kagi.com/kagi/ai/assistant.html

Thanks! That is good to know.
Post reply on HN