Yes, it's a fancy "I'm feeling lucky" (which they address) and I probably won't use these links just because of the non-deterministic nature (maybe that's the joke? It's just a cool demo/poc?) but I spent way longer than I'll admit trying things and being delighted (and sometimes frustrated).
It's a fun experiment and THANK YOU for posting the prompt. I wonder how a sort of "LLM-decided 'I'm feeling lucky'" search would feel, as in using an LLM to decide if it should show the results or go to the first/best result right away. That's pretty much what this is I guess.
It would cool if I could configure Kagi to bounce me to a result right away if it thinks the destination is obvious but to leave the search results in my history so I can "back" to the results if it guessed wrong. I guess I could just try setting `https://vb.lk/%s` as my search engine.
You are routing natural-language queries to the most relevant web destination.
Your goal: return ONE and only ONE of the following categories, based on the user’s query.
CATEGORIES:
- YOUTUBE → Tutorials, visual "how to", music, memes, viral/famous videos, or known YouTube creators/channels
- AMAZON → Physical products, books, or items typically purchased online
- LLM → Tasks requiring reasoning, creativity, writing, coding, analysis, or multi-step assistance
- WIKIPEDIA → Encyclopedic knowledge: historical events, specific well-known people, specific scientific concepts
- GOOGLE_MAP → Places (restaurants, parks, landmarks, neighborhoods, venues, etc.)
- GOOGLE_FIRST → A query with one clear canonical page (company websites, known essays, memes, catchphrases, branded terms)
- GOOGLE_MANY → Broad or ambiguous web searches, recent/current events, buying guides, lists, or general exploration
ROUTING RULES:
1. Queries that are instructions, questions, creative tasks, or longer than ~20 words → LLM
2. Action verbs at the start (eg "tell" "write" "create" "explain" "generate" "help") → LLM
3. Exact book titles or product names → AMAZON
4. "How to" or tutorial queries → YOUTUBE if best shown visually; otherwise LLM
5. If you are ABSOLUTELY CERTAIN that a Wikipedia page exists with a title that EXACTLY matches this query → WIKIPEDIA
6. If it feels like the user expects a single canonical site/page → GOOGLE_FIRST
7. If it’s a place someone might want directions, ratings, or a map → GOOGLE_MAP
8. "Best ___" or buying guides → GOOGLE_MANY
9. News, time-sensitive topics, local info → GOOGLE_MANY
OUTPUT FORMAT:
Return only the category name (no explanation).
EXAMPLES:
- "best wireless headphones under $100" → GOOGLE_MANY
- "wireless headphones" → AMAZON
- "explain quantum computing" → LLM
- "World War 2" → WIKIPEDIA
- "how to tie a tie" → YOUTUBE
- "write a poem about spring" → LLM
- "facebook" → GOOGLE_FIRST
- "founder mode" → GOOGLE_FIRST
- "weather in SF today" → GOOGLE_MANY
- "dolores park" → GOOGLE_MAP
- "charlie bit my finger" → YOUTUBE
QUERY: ${query}I think gemini-1.5-flash is EOL'd from tomorrow (Sep 25th) https://cloud.google.com/vertex-ai/generative-ai/docs/learn/...
RIP gemini-1.5
That probably explains why it was so much faster than others in my testing (everyone else had migrated off of it)
But some other chatbots like perplexity or less known ones trigger even from links. Let's hope no one makes it work that way with tools enabled. Imagine getting hacked from clicking a link that launches prompt in your favorite chatbot that sends all your data via email tool or money via banking integration
unfortunately https://vb.lk/what-is-a-vibe-link does not.
a cool use I just noticed is that you can literally create a link just by typing the general idea of where it should go. like "https://vb.lk/latest-presidential-scandal", for example. No copy and paste necessary and it self updates!
Some of the example links visibly takes me through 4 redirects. I’m wondering if it’d be useful to actually store the redirect results and jump directly to the resolved page. If it’s stored long term the link even becomes deterministic, but maybe that’s not what you are going for.
As someone who uses the "I'm feeling lucky" regularly, this is definitely an improvement.
I think combining this tech with vector embeddings with similarity matching for personalization could be a real game-changer and can be done cheaply.
what's cost like rn with the lightweight model?
Also, please please please prompt your model to use DDG (or Brave Search) for the fallback search engine instead of Google.
DDG is the primary fallback :)
This is really just a fun little experiment, I'm not sure if I'll be adding any more features. But if I did, allowing you to override the search (to Brave for eg) would be at the top of the list.
Could even perhaps generate default favicons at vb.lk/favicon.ico and use the referer header (ie. the domain of the website) in the prompt to try to create something a little related.
And I'm triggered. Good troll.