michaelstewart

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

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.

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).

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.

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)

yes! great theme

exactly

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).

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}

Thanks!

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.

Yes, that's what I find interesting about this. It's $3/year for first year and renewal, and you can do up to 10 years. It's also from a reputable registrar not one you've never heard of.

https://docs.aws.amazon.com/Route53/latest/DeveloperGuide/cl...

Wraith is a cool open source project that we played around with a bunch before starting Diffd. This is roughly what the same diff of Stripe as shown in our demo will look like with Wraith: http://www.diffd.com/imagemagick_compare.png

We have been considering going down that route and releasing Diffd as an open source project while offering a hosted version that is the easiest way to do things in parallel and across multiple browsers and operating systems.

However, we expect that initially most will add Diffd as a manual step at the end of their pipeline. So, it's not like their ability to push code is completely dependent on a third party, it's just another check.

Taking a dependence on Diffd is going to be less risky than depending on a third party for your CI server like Travis CI, CircleCI or CodeShip.

An automatically curated list of changes made to various state and federal laws would be super cool. I remember reading a NYT article [1] that highlights the need for something like this to monitor changes that are being made to supreme court rulings years after they are issued.

[1] http://www.nytimes.com/2014/05/25/us/final-word-on-us-law-is...

Thanks lazyant. Clicktwin looks cool, I think people might find the instant deployment to s3 useful if they had a dynamic website that was falling over from high load.

You might also be able to achieve a similar sort of backup with Cloudflare.

We will be adding that as part of the product demo page but at the moment it just shows what your customers will experience. So currently, we receive those videos ourselves.

In the actual product, the end users don't receive a copy of the videos.

Thanks Arnaud!

No, you don't need any plugins. The WebRTC part of the demo only works in Chrome, Firefox and Opera. The product still works in all browsers it just doesn't offer the option for screen recording.

Maybe try refreshing the demo page? http://www.plot.io/product/

Thanks!

If you want to use a LaTeX template, this might be helpful: http://www.sharelatex.com/

I would definitely talk to a lawyer. You might be able to incorporate a company but not legally work for your company.

AFR and the Australian are not bad.

Yeah it seems fairly problematic, I remember an article on HN about how easily it could be circumvented. I'm not sure what Square is doing to protect transactions. However, with over $300M in VC money I'm sure Square will cover any fraud until they figure out a way to make things more secure just like PayPal did in 2000.

The variance of the combined Gaussian will not always shrink with more data. Consider the case that you have one sensor that predicts 100m at a high accuracy and then you get another sensor predicting 10,000m with the same accuracy. At first you thought you had a very good idea of the location then with more information you realize that you actually have no idea and you get a Gaussian with mean of 5,050m and a very high variance.

AirBnB offers insurance.