I wanted to hate this but... I can't, it's pretty cool.
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.
michaelstewart1 day ago
Totally- using this as a chrome custom search was the origin of this idea. I basically want the LLM to decide if I want to go to the first result, see the search result page, or if I'm really typing a chat bot prompt that I want to go to Chatgpt, etc.
michaelstewart1 day ago
Here's the system prompt used for anyone that's curious:
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}
Oh so cool! Do you know of other themes like it, also open source?
refset8 hours ago
Unfortunately not, I've just had this one opened in my browser for ages as a reminder (after seeing it on HN IIRC) and recognised it again in the OP instantly :)
Jotalea23 hours ago
I've never heard of it and I already like it.
michaelstewart1 day ago
yes! great theme
jpau1 day ago
> A URL shortener that runs a lightweight model (gemini-1.5-flash)
That probably explains why it was so much faster than others in my testing (everyone else had migrated off of it)
sailfast1 day ago
That is correct. The speed at which these are getting deprecated is a constant pain in the rear.
0xffany1 day ago
The first thought that came to mind was Google's "I'm feeling lucky!" button. I'm glad you mentioned it and even used it in the project!
michaelstewart1 day ago
Exactly- linking to I'm feeling lucky is the 80/20 of it. We use DuckDuckGo's "I'm feeling Ducky" in most cases since Google usually adds a redirect interstitial page (with the exception of links to youtube).
garyfirestorm9 hours ago
At the minimum I was hoping it would work for their own page
Can I use this to generate links to news stories that I stumbled across many years ago, but that Google is unable to find for me anymore? Because that would be really useful.
whycombinetor1 day ago
LMGTFY without the snark
michaelstewart1 day ago
exactly
squirrellous22 hours ago
Great idea and execution!
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.
indigodaddy1 day ago
This is a super clever idea. Congrats. These are the types of ideas/sites that we need to coalesce with AI!
stevage1 day ago
Sounds like a good use case is using this as placeholder links while writing a blog post to avoid stopping and looking for links, then doing an automatic replacement of the vibe links with what they resolve to and fixing any incorrect ones.
I was hoping this would write those god damn CMakeLists.txt for me…
rgbrgb1 day ago
this is a good one, so fun. congrats and good work!
what's cost like rn with the lightweight model?
michaelstewart1 day ago
The lightweight model is incredibly cheap. Cost so far today $0.06. It within the same order of magnitude as the per-request cost of the write to cloudflare KV storage (which I'm using to cache the inference result).
cognomano17 hours ago
what-is-reality redirects to Wikipedia search. I’m not impressed. I wish I could tell the LLM: try again!
michaelstewart6 hours ago
thanks for flagging! the model is overly eager to choose a wikipedia redirect. I've updated the system prompt to encourage less use of wikipedia redirect and this query now takes you to chatGPT
tsehori9 hours ago
Another small idea - in case there is no website or route that is statistically strong related to the requested link (based on whatever the model outputs as "strength") then vibe-code a small website
michaelstewart8 hours ago
That's cool. I'm considering adding a feature like this for images. So you could just link to vb.lk/red-duck-200x300.png And it would generate (then cache) the image. Could be useful for placeholders, a bit like https://placehold.co/
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.
Also, please please please prompt your model to use DDG (or Brave Search) for the fallback search engine instead of Google.
michaelstewart1 day ago
Yes, unfortunately it's not going to pick up anything that's brand new immediately. Once it ranks for the term "vibe link" it should redirect there.
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.
righthand1 day ago
I typed in “beer” and it just redirected me to a Google search for beer…
zorkso1 day ago
cool idea!!
michaelstewart1 day ago
Thanks!
Cheer21711 day ago
> Now that computers can think, precision is optional.
And I'm triggered. Good troll.
satisfice19 hours ago
So it’s a canned Google search. some people get excited over the meagerest things.
kmckiern1 day ago
fun!
jongjong1 day ago
I really appreciate this kind of simple out-of-the-box thinking, leveraging innovation to reinvent basic primitives. This feels significant. I can already see some dystopian 'Dead Internet Theory' use cases for this but also could help to further decentralize the web in a positive way. This could be a game-changer for personalization. My gut is telling me this idea is more important than it seems.
I think combining this tech with vector embeddings with similarity matching for personalization could be a real game-changer and can be done cheaply.
I wanted to hate this but... I can't, it's pretty cool.
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.
Totally- using this as a chrome custom search was the origin of this idea. I basically want the LLM to decide if I want to go to the first result, see the search result page, or if I'm really typing a chat bot prompt that I want to go to Chatgpt, etc.
Here's the system prompt used for anyone that's curious:
Great seeing another example here of The Monospace Web design theme https://owickstrom.github.io/the-monospace-web/
Oh so cool! Do you know of other themes like it, also open source?
Unfortunately not, I've just had this one opened in my browser for ages as a reminder (after seeing it on HN IIRC) and recognised it again in the OP instantly :)
I've never heard of it and I already like it.
yes! great theme
> A URL shortener that runs a lightweight model (gemini-1.5-flash)
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
Oooh, that it very good to know- thank you.
That probably explains why it was so much faster than others in my testing (everyone else had migrated off of it)
That is correct. The speed at which these are getting deprecated is a constant pain in the rear.
The first thought that came to mind was Google's "I'm feeling lucky!" button. I'm glad you mentioned it and even used it in the project!
Exactly- linking to I'm feeling lucky is the 80/20 of it. We use DuckDuckGo's "I'm feeling Ducky" in most cases since Google usually adds a redirect interstitial page (with the exception of links to youtube).
At the minimum I was hoping it would work for their own page
https://vb.lk/take-me-to-vibe-link
That very first link, https://vb.lk/generate-an-image-of-what-you-think-my-office-... prompted ChatGPT to generate an eerily accurate pic of my office. I didn't know how much stuff it was "remembering" about me.
Can I use this to generate links to news stories that I stumbled across many years ago, but that Google is unable to find for me anymore? Because that would be really useful.
LMGTFY without the snark
exactly
Great idea and execution!
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.
This is a super clever idea. Congrats. These are the types of ideas/sites that we need to coalesce with AI!
Sounds like a good use case is using this as placeholder links while writing a blog post to avoid stopping and looking for links, then doing an automatic replacement of the vibe links with what they resolve to and fixing any incorrect ones.
Thank you for sharing. This feels like a modern day version of https://letmegooglethat.com/.
I was hoping this would write those god damn CMakeLists.txt for me…
this is a good one, so fun. congrats and good work!
what's cost like rn with the lightweight model?
The lightweight model is incredibly cheap. Cost so far today $0.06. It within the same order of magnitude as the per-request cost of the write to cloudflare KV storage (which I'm using to cache the inference result).
what-is-reality redirects to Wikipedia search. I’m not impressed. I wish I could tell the LLM: try again!
thanks for flagging! the model is overly eager to choose a wikipedia redirect. I've updated the system prompt to encourage less use of wikipedia redirect and this query now takes you to chatGPT
Another small idea - in case there is no website or route that is statistically strong related to the requested link (based on whatever the model outputs as "strength") then vibe-code a small website
That's cool. I'm considering adding a feature like this for images. So you could just link to vb.lk/red-duck-200x300.png And it would generate (then cache) the image. Could be useful for placeholders, a bit like https://placehold.co/
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 yet https://vb.lk/vibe-link does not redirect back to vb.lk.
Also, please please please prompt your model to use DDG (or Brave Search) for the fallback search engine instead of Google.
Yes, unfortunately it's not going to pick up anything that's brand new immediately. Once it ranks for the term "vibe link" it should redirect there.
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.
I typed in “beer” and it just redirected me to a Google search for beer…
cool idea!!
Thanks!
> Now that computers can think, precision is optional.
And I'm triggered. Good troll.
So it’s a canned Google search. some people get excited over the meagerest things.
fun!
I really appreciate this kind of simple out-of-the-box thinking, leveraging innovation to reinvent basic primitives. This feels significant. I can already see some dystopian 'Dead Internet Theory' use cases for this but also could help to further decentralize the web in a positive way. This could be a game-changer for personalization. My gut is telling me this idea is more important than it seems.
I think combining this tech with vector embeddings with similarity matching for personalization could be a real game-changer and can be done cheaply.
[dead]