I disagree. Some things are hard to Google, because you can't frame the question right. For example you know context and a poor explanation of what you are after. Googling will take you nowhere, LLMs will give you the right answer 95% of the time.

Once you get an answer, it is easy enough to verify it.

I agree. Since I'm recently retired and no longer code much, I don't have much need for LLMs but refining a complex, niche web search is the one thing where they're uniquely useful to me. It's usually when targeting the specific topic involves several keywords which have multiple plain English meanings that return a flood of erroneous results. Because LLMs abstract keywords to tokens based on underlying meaning, you can specify the domain in the prompt it'll usually select the relevant meanings of multi-meaning terms - which isn't possible in general purpose web search engines. So it helps narrow down closer to the specific needle I want in the haystack.

As other posters said, relying on LLMs for factual answers to challenging questions is error prone. I just want the LLM to give me the links and I'll then assess veracity like a normal web search. I think a web search interface allowed disambiguating multi-meaning keywords might be even better.

> Some things are hard to Google, because you can't frame the question right.

I will say LLMs are great for taking an ambiguous query and figuring out how to word it so you can fact check with secondary sources. Also tip-of-my-tongue style queries.

If you’re looking for a possibly correct answer to an obscure question, that’s more like fact finding. Verifying it afterward is the “fact checking” step of that process.

A good part of that can probably be attributed to how terrible Google has gotten over the years, though. 15 years ago it was fairly common for me to know something exists, be able to type the right combination of very specific keywords into Google, and get the exact result I was looking for.

In 2025 Google is trying very hard to serve the most profitable results instead, so it'll latch onto a random keyword, completely disregard the rest, and serve me whatever ad-infested garbage it thinks is close enough to look relevant for the query.

It isn't exactly hard to beat that - just bring back the 2010 Google algorithm. It's only a matter of time before LLMs will go down the same deliberate enshittification path.

> For example you know context and a poor explanation of what you are after. Googling will take you nowhere, LLMs will give you the right answer 95% of the time.

This works nicely when the LLM has a large knowledgebase to draw upon (formal terms for what you're trying to find, which you might not know) or the ability to generate good search queries and summarize results quickly - with an actual search engine in the loop.

Most large LLM providers have this, even something like OpenWebUI can have search engines integrated (though I will admit that smaller models kinda struggle, couldn't get much useful stuff out of DuckDuckGo backed searches, nor Brave AI searches, might have been an obscure topic).

It's not the LLM alone though, it's “LLM with web search”, and as such 4o isn't really a leap at all there (IIRC perplexity was using an early Llama version and was already very good, long before OpenAI adding web search to ChatGPT).