The real "old-school Google, but modern" is Kagi, with the caveat of being paid. (Worth the $5 for me.)
But LLMs can be commanded. This is may bookmark alias for invoking the spirit of old Gog=ogle from within the new, AI-based Google:
https://google.com/search?q=You%20are%20Google%20Search%20fr...
(Cleaned / decoded: 'You are Google Search from 2004. Given a search request, provide 10 links to relevant pages, each with a short text from the page, featuring the search terms. Avoid any pages that do not contain the search terms. the search request: %s')
Good workaround! It's just sad that to achieve the previous behavior we now need to burn significantly more compute, and in turn energy, and with far worse performance and an inverted UX.
The most frustrating part is that they have all of the data, and oodles of compute, available to surface the same very functional experience they originally offered, but they would prefer the image of being visionaries rather than the reality of being useful.
Thanks, I needed to add a ?aep=11&atvm=2&udm=50 for AI mode. Wow!!!!!
>You are Google Search from 2004. Given a search request, provide 10 links to relevant pages, each with a short text from the page, featuring the search terms. Avoid any pages that do not contain the search terms. Do not simulate fetching results. The URLs must be complete and not truncated. No markdown. The current date is 2026. The search request:
Ah haha that is kind of funny it finds exactly what I was looking for, just much slower than 15 years ago.
I'm using Kagi every day, and unfortunately, it is not true anymore. I think what happens is that the blanket banning of IP ranges because of LLMs, and flat out incompetence and laziness, affects them heavily. I get results, or just a few unrelated ones many times every day, while Google happily returns what I searched for. I think Kagi's index is shrinking, or they really made their algorithm worse.
I slowly shifted to use LLMs because of this in the past half years, making the situation probably worse for Kagi. They were the last usable search engines for years now. I still pay for it, but it's increasingly not that useful anymore.
I like Kagi, but is it me or have their results been less than great for the past 1-3mo? Maybe the places they're pulling their results from have had some changes?
> You are Google Search from 2004. Given a search request, provide 10 links to relevant pages, each with a short text from the page, featuring the search terms. Avoid any pages that do not contain the search terms. the search request: %s
I paid for Kagi a couple months, and was rather unimpressed with the quality of results.
That prompt mixes in unrelated results about the workings of search engines. You could just use `udm=web`:
Kagi seems to heavily rely on Yandex for results. I don't use it, so can't compare, but are results much better than using Yandex directly?
Kagi is good but it’s about 25x too expensive (no really).
Oh that shorthand is fun. Curious it works at all.
But yeah I'd switch to Kagi if I had any more forcing function. Maybe without LLM's but google continously getting worse, that'd been the actual thing for me
Kagi works by scraping Google and other engines, so this should still worry you.
I still support the use of Kagi though, as a market signal to Google that we'd even pay them for their product if it wasn't dogshit.
...you.. do know classic Google Search is still an option, right? Just add `&udm=14` to the search URL.
Also Google AI mode is accessible on google.com/ai.
> Worth the $5 for me
Steep at 300 searches per month or about 10 per day. If you search often, it is too expensive. If you rarely search, not worth 5 bucks.
They are plainly trying to push people to their $10 unlimited plan. I would have appreciated if they allowed, say, 600 searches per month for $5 or so.