Its also why Google Search "went to shit years ago"
Technically adept people would search using ordered keywords and phrases, which would have excellent results with Google 2006:
Dario Turkey NBA "never coming over"
But regular people agonized over this because to them a search was
What were some of the memes about Dario staying in turkey
Google put immense effort into calibrating search for regular people instead of engineers.
Christ, thank you! I’ve been saying this for years and no one I’ve spoken to, even engineers, could acknowledge the level of “chunking” that’s been engrained in them over the years for turning inquiries into keyword/phrase shorthand, and that this is NOT something most people want to do, and is the killer app of Google AI. This time around, you CAN type in an input box what you would say to a human in everyday conversation, AND expect a reasonable response. That’s invaluable to a casual user.
> this is NOT something most people want to do
I've always felt that "proper" and responsible LLM use for search [0] would be two boxes: You can describe what you want in the first, and it'll propose search terms in the second, and then those get executed normally.
Yes, the "average user" [1] might not usually care about the second box... Until they need to because the query/results are wrong.
Showing them in tandem means:
1. Users are at least capable of learning through exposure.
2. Users may realize a key term can be added which the model could never have guessed.
3. Users may recognize a term in there that doesn't make sense, allowing them to detect a translation error.
4. If good search-terms leads to a bad outcome, it is possible for someone to report and diagnose it, rather than a fully black-box mystery.
_____
[0] Not just for websites, but also things like internal business software, or SQL queries.
[1] The average that might not exist. ( https://www.thestar.com/news/insight/when-u-s-air-force-disc... ) There are some features that everybody needs, just at different times.
In the words of Edsger Dijkstra, "Projects promoting programming in 'natural language' are intrinsically doomed to fail." I think for something as bespoke as a search engine, a DSL that accepts quotes, logical operators, and specific terms definitely allows for far greater specificity than natural language can (at least in an equivalent amount of text).
I think the two-tiered input-output approach you propose makes sense. Allowing users to inspect and mutate lower-level languages allows the user to make modifications as needed. I think it's very much in the spirit of free software.
But then again, for text-based search specifically (search engines, notes, etc.), I think there is some value in querying the LLM directly, as it is able to fuzzy search by inspecting its weights. This results in a lesser degree of specificity, which allows for more false positives, but can maybe capture similar words (i.e., synonyms / typos / tenses) or higher-level semantic concepts.
Maybe they're just two different search algorithms, and the user should be able to choose between them.
Thanks for linking the article, I found it very interesting.
Your described thinking pattern does not apply to 95%+ users, and might add confusion leading to retention loss (e.g. 2 text boxes? Wtf, two boxes? What do i type in the second one? Whatever i’ll switch to the usual). Every project with at least 100K non-tech users I’ve worked on, has shown that sort of thinking just doesn’t translate.
And regarding “average doesn’t exist” - that’s true. But no company does a/b testing to land on average. I’d assume a good 85%-kinda pass rate for these type of experiments.
It's not just engineers, I think it's more an age thing.
For a certain cohort (eg those currently between 35 and 45) who did any sort of grade school computer/library classes in the 90's/early2000's, 'chunking' or keyword searching was one of the main skills taught.
I mean, I'm in my mid-30s, and "keywording" and "how to use search engines" was taught in my US Midwest public school library/media center.
If you are a fast typer, maybe the longer query might just come out naturally.
If you are properly lazy, you must expect or at least attempt to get results for the shorter query. Especially on a phone.
It's not about shorter vs longer.
Many people who learned to search the Internet in early 2000s learned "boolean search queries" (terms connected with AND or OR). They're talking about the difference between boolean search queries and natural language search queries.