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…
OpenAI Finally Allows ChatGPT Complete Internet Access
101–110 of 118 posts
Re: OpenAI Finally Allows ChatGPT Complete Internet Access
#1021. I don't want to read through all materials in that topic but want an overview.
2. I can't describe the topic with the precise language for it, hoping ChatGPT can translate my naive description to the vocabulary for that field.
ChatGPT does bad in both of these cases. For (1) it just randomly browses 3~4 search results, as for (2) it always try to search in my original vocabulary. Why don't I search myself then, but to wait for the slow response?
Re: OpenAI Finally Allows ChatGPT Complete Internet Access
#103Earlier quoted context omitted.
Please don't paste ChatGPT or BARD answers as HN comments in general? In this specific case, no, LLMs don't reliably know about themselves. They're trained on a big corpus of internet text, then trained by rough reinforcement learning to say and not say certain things about themselves, then given a little more information about themselves in system prompts.
A LLM that can use tools is probably going to know it can use tools. Either it's trained to do so or the information is embedded in the context. 3.5 can't browse, only 4 so the above is perfectly correct.
Re: OpenAI Finally Allows ChatGPT Complete Internet Access
#104Re: OpenAI Finally Allows ChatGPT Complete Internet Access
#105Earlier quoted context omitted.
AI Kessler Syndrome. https://en.m.wikipedia.org/wiki/Kessler_syndrome
Is there an approximation/ratio in which the amount of digital garbage/hallucinations online generated by AI is so big that it cannot be used to train AI itself? Like are AI companies running against the clock because, say, in 5 years the internet will be flooded by false information to such an extent that it would render the internet as an invalid training ground. In a way requiring a snapshot of the internet pre-AI…
Re: OpenAI Finally Allows ChatGPT Complete Internet Access
#106Re: OpenAI Finally Allows ChatGPT Complete Internet Access
#107Earlier 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
Re: OpenAI Finally Allows ChatGPT Complete Internet Access
#108Earlier 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
I wonder why they don't list that under ultimate plan? On pricing page the selling point for ultimate is like: Hey, help us test things and help us by giving some money: https://kagi.com/pricing
Re: OpenAI Finally Allows ChatGPT Complete Internet Access
#109Earlier 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.
Re: OpenAI Finally Allows ChatGPT Complete Internet Access
#110Earlier quoted context omitted.
I thought Google's given Bard access to the internet?? I guess people still don't think to use Bard over ChatGPT
Even the Bard UI is worse. Being able to read the ChatGPT output as it's generated, instead of staring at a blank screen, is a massive time saver. And, I prefer ChatGPT trying stuff rather than Bard telling me that 'it can't do that right now' and 'we're trying to get better'. I've tried Bard, it's just not worth it.
There's an option in Bard's settings to enable real time replies.