971–980 of 1001 posts
If the current iteration of search engines are producing garbage results (due to an influx of garbage + SEO gaming their ranking systems) and LLMs are producing inaccurate results without any clear method proposed to correct them, why would combining the two systems not also produce garbage? The problem I see with search is that the input is deeply hostile to what the consumers of search want. If the LLM's are partic…
Genuine question: is there a present or planned value proposition for people like me who already have decent search skills? Or are these really for children/elders who (without making any normative claim about whether this is a good thing or not) can't be arsed to perform searches themselves? Does someone else have good search skills but mingle traditional search engines with LLMs anyways? Why? I use LLMs every day b…
Could OpenAI make it impossible for startups to try to build AI search engines by signing all these paid agreements with publishers?
"""Search will be available at chatgpt.com (opens in a new window), as well as on our desktop and mobile apps. All ChatGPT Plus and Team users, as well as SearchGPT waitlist users, will have access today. Enterprise and Edu users will get access in the next few weeks. We’ll roll out to all Free users over the coming months.""" Can confirm that free users who signed up for the waitlist can use it right now (even if th…
I signed up for the wait list as well and got the email. However there is no search button on the web interface (free tier). Is there anything I am missing?
LLMs are just not the right thing to _be_ search. Just like I use the LLMs to generate prompts, I would use LLMs to help guide my search terms to cover what my first query missed. This can help to deSEO my searching too. This is really useful for deep topics of course.
OpenAI _could_ have approached the problem with this mindset.
Earlier quoted context omitted.
> A better example might be "is dietary saturated fat a major factor for heart disease in Western countries?". The current government publications (which answer "yes") for this are probably wrong based on recent research. The government cannot be relied upon as a source of truth for this. I know it was just an example, but actually no, the role of dietary saturated fat as a factor for heart disease remains very much…
https://pmc.ncbi.nlm.nih.gov/articles/PMC9794145/ Remarkable how easy it is to cling to propaganda
Been thinking about this a lot [1]. Will this fundamentally change how people find and access information? How do you create an experience so compelling that it replaces the current paradigm? The future promised in Star Trek and even Apple's Knowledge Navigator [2] from 1987 still feels distant. In those visions, users simply asked questions and received reliable answers - nobody had to fact-check the answers ever. C…
One thing is clear, in the vast majority of cases we don't have a single truth, but answers of different levels of trustworthiness: the law, the government, books, Wikipedia, websites, and so on.
A human would proceed differently depending on the context and the source of the information. For example, legal questions are best answered by the law or government agencies, then by reputable law firms. Opinions of even highly respected legal professionals are clearly less reliable than government law itself and are likely to be a point of contention/litigation.
Questions about other facts, such as the diameter of the earth or the population of a country, are best answered by recent data from books, official statistics and Wikipedia. And so on and so forth.
If we are not sure what the correct answer is, a human would give more information about the context, the sources, and the doubts. There are obviously questions that cannot be answered immediately! (if it's to easy to find the truth, we would not need a legal system or even science!) So no machine and no amount of computation can reliably answer all questions. Web search does not answer a question. It's just trying to surface relevant websites to a bunch of keywords. The answering part is left as an exercise for the user ;)
So an AI search with a pretense of understanding human languages makes the task incredibly harder. To really give a human-quality answer, the AI not only needs to understand the context, but it should also be able to reason, have common sense, and be a bit self-aware (I'm not sure...). All this is beyond the capabilities of the current generation of AI. Therefore, my conclusion is that the "search" or better said the "answer" cannot be solved by LLM, no matter how much they fine-tune and tweak it.
But we humans are adaptable. We will find our way around and accept things as they are. Until next time.
Earlier quoted context omitted.
ChatGPT 4o and 4o-mini with Search were able to answer this question without any issues. Maybe you didn't enable the search functionality? --------------- 4o: Yes, Paul Edwin Zimmer wrote a fourth novel in his Dark Border series titled Ingulf the Mad , published in 1989. This installment focuses on the characters Ingulf Mac Fingold and Carrol Mac Lir, detailing their meeting and acquisition of mystical swords. Notabl…
Why is it that comments complaining about flaky AI responses never share the chat link, and then invariably someone replies with examples of the AI answering correctly but also fail to share the chat link?
4o-mini: https://chatgpt.com/share/6725f6fb-3b84-800b-9b4d-3e82554fbf...
I can't figure out how to share the 4o one. The UI is weird.
Been thinking about this a lot [1]. Will this fundamentally change how people find and access information? How do you create an experience so compelling that it replaces the current paradigm? The future promised in Star Trek and even Apple's Knowledge Navigator [2] from 1987 still feels distant. In those visions, users simply asked questions and received reliable answers - nobody had to fact-check the answers ever. C…
I agree that this is the core question, but I'd put it as: Who Gets To Decide What Is True? With a search paradigm this wasn't an issue as much, because the answers were presented as "here's a bunch of websites that appear to deal with the question you asked". It was then up to the reader to decide which of those sites they wanted to visit, and therefore which viewpoints they got to see. With an LLM answering the que…
Independent Tribunal: https://www.independenttribunal.org/ (a project of mine)
Even in the of law there are various schenanigans and loopholes such as "legally true" :)