Feature Spotlight: Query Rules
You’re running an ecommerce site for an electronics retailer, and you’re seeing in your analytics that users keep ...
Technical Writer
You’re running an ecommerce site for an electronics retailer, and you’re seeing in your analytics that users keep ...
Technical Writer
What do OpenAI and DeepMind have in common? Give up? These innovative organizations both utilize technology known as transformer models ...
Sr. SEO Web Digital Marketing Manager
As a successful in-store boutique manager in 1994, you might have had your merchandisers adorn your street-facing storefront ...
Search and Discovery writer
At Algolia, our business is more than search and discovery, it’s the continuous improvement of site search. If you ...
JavaScript Library Developer
Analytics brings math and data into the otherwise very subjective world of ecommerce. It helps companies quantify how well their ...
Technical Writer
Amid all the momentous developments in the generative AI data space, are you a data scientist struggling to make sense ...
Sr. SEO Web Digital Marketing Manager
Fashion ideas for guest aunt informal summer wedding Funny movie to get my bored high-schoolers off their addictive gaming ...
Sr. SEO Web Digital Marketing Manager
Imagine you're visiting an online art gallery and a specific painting catches your eye. You'd like to find ...
Senior Software Engineer
At Algolia, our commitment to making a positive impact extends far beyond the digital landscape. We believe in the power ...
Senior Manager, People Success
In today’s post-pandemic-yet-still-super-competitive retail landscape, gaining, keeping, and converting ecommerce customers is no easy ...
Sr. SEO Web Digital Marketing Manager
There are few atmospheres as unique as that of a conference exhibit hall: the air always filled with an indescribable ...
Marketing Content Manager
To consider the question of what vectors are, it helps to be a mathematician, or at least someone who’s ...
Search and Discovery writer
My first foray into programming was writing Python on a Raspberry Pi to flicker some LED lights — it wasn’t ...
Technical Writer
How well do you know the world of modern ecommerce? With retail ecommerce sales having exceeded $5.7 trillion worldwide ...
Sr. SEO Web Digital Marketing Manager
In a world of artificial intelligence (AI), data serves as the foundation for machine learning (ML) models to identify trends ...
Director of AI Engineering
Imagine you’re a leading healthcare provider that performs extensive data collection as part of your patient management. You’re ...
Search and Discovery writer
In an era where customer experience reigns supreme, achieving digital excellence is a worthy goal for retail leaders. But what ...
Marketing Content Manager
Just a few years ago it would have required considerable resources to build a new AI service from scratch. Of ...
VP, Engineering
Since OpenAI announced ChatGPT and people started to try it out, there have been plenty of breathless proclamations of how it will upend everything. One of those upendings is search. Go on Twitter or LinkedIn (or Bloomberg!), and you can read how ChatGPT and similar LLMs are going to replace Google and other search engines.
But, really?
No, Google has little to worry about, at least in the short– to mid–term. Search engines have been around for decades, and will be around for decades more. The lack of real danger to them has to do with search relevance and user experience in chat-based environments.
I’ve worked in search at Algolia for seven years, the last four exclusively on natural language, voice, and conversational search. I’ve learned what works and what doesn’t, and while I’m long on LLMs (large language models), I’m not long on replacing the existing search paradigm. Here’s why.
Query Formulation
The first reason has to do, ironically, with query formulation. I say ironically here because much of the work around artificial intellence (AI) and machine learning (ML) in search is to make query formulation less of a hurdle. In the past, the most basic search engines matched text to the exact same text inside results. That means that if you searched for JavaScript snippets, then JavaScript snippets had to be exactly in the document you wanted to find. The problem is that it forced the searcher to try and predict which text is going to be in the documents.
Here’s an example: let’s say you’re cleaning your gas stovetop and you realize that it’s warm, even though you haven’t used it in a while. With an unintelligent search engine, you need to ask yourself before you search: “Should I use the word warm or hot? Does it make a difference in the results I’ll get back?”
Intelligent, ML–driven search works to take this burden away by expanding what counts as a match and including “conceptually” similar matches, like warm and hot. Searchers spend less mental energy on determining the right search term, and they are much more likely to find the information they wanted originally.
ChatGPT responses are, however, heavily dependent on the prompt (i.e., query) formulation. OpenAI “lists this as a limitation”:
ChatGPT is sensitive to tweaks to the input phrasing or attempting the same prompt multiple times. For example, given one phrasing of a question, the model can claim to not know the answer, but given a slight rephrase, can answer correctly.
Sometimes this manifests when searching things the searcher already knows a lot about, but it’s much more of an issue when the searcher is hazy about details. If someone searches for what the suffix -gate means, there’s a very, very good chance that the correct result is about political scandals. Google and Kagi reflect this, ChatGPT does not:
(The end of ChatGPT’s response is saying that the use of the suffix -gate is rare. Tell that to Washington!)
This is even more stark when it comes to typos. We all make typos, don’t we? And sometimes we spell words incorrectly because we don’t know any better. For example, the phrase cum laude is an uncommon one in daily life, and so there will be people who want to know more about it and don’t know the correct spelling. How does ChatGPT handle a spelling of come lad compared to Kagi?
This isn’t a case of ChatGPT not having the answer. It does when you use the correct spelling:
Search must understand searchers even with misspellings, or else the experience is a step back. Understanding and matching different spellings is difficult. At Algolia, we take two approaches: one is a straightforward edit distance between text; the other is via our upcoming AI Search that matches on concepts and takes into account contextual clues to better match the correct spelling even when the edit distance is large.
There’s another problem with ChatGPT, which is how it shows the incorrect results. Or, really, how it shows the results generally.
Search layouts have been, typically, the same for decades. Specifically: a set of results in order from most to least relevant (however that is measured). That has changed somewhat in recent years. With search engines bringing in answer boxes, side boxes, suggested searches, multimedia searches, and more. Take a look at a Bing search page:
Of course, Bing is an outlier. This one search results page includes approximately 20 different components: streaming options, video results, image results, and webpage results. Maybe that’s too much. Google, Kagi, and others have less. But the point is that searchers always get options.
It’s important for searchers to get options because the first result isn’t always the best for the search. It may be “objectively” the best overall, but a search is a combination of a query, an index, a user, and a context. All of those combined might lead results beyond number one to be the most relevant at that time. This blog post claims that the number one result on a Google search is clicked 28% of the time. Whether that number is precisely right, it is generally correct: the majority of clicks tend not to be the first result.
What is chat-based searching? Only the first result.
Even more, it’s in a chat-based context. In a conversational interface, users expect always to get a response that is relevant, with a minimal amount of “I don’t know” responses.
At Algolia, I’ve seen this with some of our customers who have used our search as a fallback for their chatbots. Chatbot natural language understanding (NLU) can sometimes have a high failure rate (we’ve seen customers approaching 50% failure) and search seems like a natural fallback. We’ve had to tailor the chatbot UX, though, not presenting the first result as a response, but instead showing a few results and being clear that the user is seeing a fallback. It’s what users expect.
Chat also robs information of context. Landing on a page and seeing related information is good: it helps frame the information you find and perhaps even show you where the original snippet was incorrect or misleading.
Take someone who wants to know about the baseball home run record. This person has heard that the record used to have an asterisk. But why? What was the record? This famously refers to Roger Maris’ 61 home run season in 1961, but the searcher doesn’t know, and so searches why was the home run record with an asterisk? Compare the answers from ChatGPT, Google, and Kagi:
ChatGPT provides an answer about the home run record from ‘98 with Mark McGwire, which has been controversial years later, but isn’t the home run record with an asterisk. Google gives the correct answer in an answer box along with links out to sources, and Kagi provides results. Of these, Kagi might even be the best because while Maris’ is the one that comes to mind when people say “astrisk,” both McGwire and Bonds also have controversy attached to theirs.
To be fair, OpenAI is aware of this. Here’s a tweet from CEO Sam Altman:
But I do think that the lack of context and multiple choices is inescapable within a pure chat context. That’s why chat is great for finding business hours; less great for learning what it’s like to go through boot camp or why people like RomComs.
This isn’t even touching on product search. A large amount of money spent on search these days is not on SEO for Google, but building search for a site’s own product catalog. In these situations, it is so important for searchers to be able to see options, filter down with a click, and generally get deep into a “discovery phase.” This is not what chat is suited for.
There are other hurdles: legal (Australia has a law requiring payment from Google and Facebook for news; what will they think when the news is automatically summarized without sources?), cost, and speed immediately come to mind. These may one day be surmountable. So, too, might the overly confident incorrect results.
But user experience: this one isn’t going away. Okay, yes, you might argue that it’s easy enough to fix. A chat-based system could show multiple results at once and let the user decide which is the best. Maybe even rank them by confidence. Then it could even link out so that a searcher could see the information and decide if it’s accurate. Even better, why not also include suggestions for follow-up queries or multimedia that might be interesting?
Congratulations, you’ve just rebuilt a search UI.
So, in short: LLMs are great. Understanding user intent is fantastic. Automatic summarization is powerful. Search is going nowhere.
Powered by Algolia Recommend