Search Different. Also see: WonderSwipeās more complete 30s demo video Iām Gary Fung. I started isoHunt.com as a hobby 15 years ago. Now Iām starting , my 2nd hobby. Iām hoping it can also be something more, and it never hurts to aim high. WonderSwipe Many have tried breaking Googleās search monopoly. I believe they all failed because no one, not even Microsoft with Bing/Yahoo, can attack Googleās search monopoly head on. Against Googleās AI brain trust, data and infrastructure, there can be no victory. But that also doesnāt mean everyone should give up and stop innovating in web search, as it is . stagnating First, what was the last great monopoly? Windows. What broke it? Itās not really broken, but iPhone, and smartphones by extension, are making PCs less and less relevant. You canāt depose the king but you can shrink the kingdom. (this is probably a poorĀ analogy) I believe with ever smarter AI, Google will continue being the dominant search engine. No one knows how to run a more optimized and scalable search engine than Google. But I see ways around the gatekeeper to human knowledge, because I believe thereās more to the whole search/research experience and knowledge curation for people, than just algorithms and infrastructure: A userland tool, a mobile frontend, where Google has failed to innovate other than āsimplyā transplanting desktopās search UI and maintaining search ranking algos. This is WonderSwipeās phase 1, which was launched on the iOS last week. App Store A real social layer for search: with WonderSwipeās highlights, you will curate and crowdsource the best bits of information on each search query. Highlighting will be as easy as long-pressing a summary in WonderSwipe. Make curating the best of human knowledge on the Web a more human process again. Human expertise and curation is not something AI can supplant. Fragmenting search options. With an easy UI at point of search input, you can easily choose DuckDuckGo (or whatever else) for private searches, Amazon (or ___) for shopping, Baidu for China, etc. Make search engines pluggable and by vertical, thus less reliant on any single search engine as the one stop shop. Vertical search engines are also more tailored for each vertical and can be better than Googleās one size fits all. (I know from isoHunt) Below is the what and the how of WonderSwipeās phase 1, as last week. The devil is in the details. Hereās my proposal to completely rethink how we search and curate knowledge, for fun and profit. And in the process, not just in service of feeding our eyeballs to the ad machine either, as we realize now more and more that our . launched Time is Not Well Spent I wonāt claim I have the whole product-market-fit figured out yet for WonderSwipe, so please tell me if this is crazy/lame/wonāt work/awesome/anything in between. WonderSwipe has launched on the iOS since 4/18! . Read on for why I think it is the biggest thing to search since Google itself, and watch our 30s demo video below for how. If you think itās awesome too, tell us and vote for us . App Store Get it now for free here ās icon, and WonderSwipe demoĀ video Thereās too much stuff online & too little time on the go to fuss with browser tabs or going back & forth in browser history. When was the last time you did some serious googling on your smartphone? According to and the domination of over desktop, not likely to be recent or frequently. For me, not unless Iām stuck with mobile Safari or Chrome without a laptop. Mobile websites, including Google itself, stuffing more ads above the fold on smartphonesā limited screen space compared to desktop havenāt helped the UX. stats like this time spent on mobile šš¼ So, hereās to use instead of conventional browsers, so mobile search stop sucking: 3 scenarios WonderSwipe 10ā100x article loading and browsing speed, as measured in-app. Even more drastic difference over slow data networks. Too slow; Didnāt search? No tabs: Easily swipe through search results, no clicks or background tab tab tab tab tabs needed.Hands-free mode: Automated browsing, with search result summaries read out like audiobooks and scrolled in-sync. Too many results; Didnāt browse? Reader mode (like , Safariās) with summarization of each search result, where possible. Too long; Didnāt read (TL;DR)? Pocket After 2 years of development, I believe my solution is ready. WonderSwipe is designed from the ground up to find the answers you search for, in the . With the Internetās enabling of prolific information overload and the recent backlash against Facebook (newsfeed), Youtube (autoplay), Snapchat (snapstreaks), etc. We want to create the opposite of a time sink, for truly . We want to create new, efficient and meaningful ways of information searching, curating and sharing. We are a counterpoint to time spent maximalists like the ad-driven social apps, we want to be time . Hereās of WonderSwipeās phase 1 launching on the , which Iād say is about half feature complete. fastest way possible time well spent minimizing demo videos App Store WonderSwipe demo ( , on mobile), on iPhone Xāāāsearching š in HD dunkirk date before or after pearl harbor iPhone 6 version Note that is a browser. Itās something different, a research and reference tool. It best when your search is non-trivial, and turns up informational articles to which WonderSwipe can do text extraction and summarization. WonderSwipeās phase 2 will add highlighting and annotation for your own reference, as well as making it sharable in a social layer so learners can help other learners like you, quickly sifting and surfacing diamonds in the search results rough. For every topic searchable. WonderSwipe not augments search This web scale social highlighting we believe will shift us towards more meaningful sharing and in learning and curating, by going beyond simplistic likes and hearts that festers in viral engagement metrics, driving sensationalism, fake news and time sinks for advertising. time well spent WonderSwipe for now at is the -browser, with the sole goal of making search and finding your answers buried in results . It does include in-app browser (SafariView on iOS) as a 1-tap fallback when you want the full HTML for some websites to function. (globe icon on bottom right of app, in the video) launch not ridiculously fast demo With my 11 years experience working on the BitTorrent search engine , and before that, using and watching Googleās development since its beginning. I believe WonderSwipe is shaping up to be the biggest user experience improvement in Web search, since Google itself. And that begins with us waking up to the fact that mobile search right now, is sucking. isoHunt More and more computing time shifts from desktop to mobile, while time spent on the Web in current browsersĀ shrink. Mobile web browsing havenāt fundamentally changed much. And all serious web browsing start with a search. The WebāsĀ Problem With the proliferation of content, web search is getting more tedious. Itās exacerbated on smartphones. I would tap on a promising search result, wait 5 seconds ( on the best cell network conditions), read a bit, see that it doesnāt concern what Iām looking for, tap back in browser to Googleās search page, scroll to another promising search result, rinse and repeat. Itās just too tedious and slow to do any serious search on a non-trivial topic of interest. rather optimistic This pattern is similar on desktop browsers, though itās better with the aid of faster WiFi, easy switching between browser tabs (so you can background load search results without all the click and wait), browser extensions, and easy Cmd-F / Ctrl-F to highlight keywords within found webpages for quick skimming. But what if you can conduct mobile search 10ā100x faster, with all the niceties I listed above in desktop browsers? Well all except one, WonderSwipe canāt give you fast WiFi everywhere. But it does compensate for slow networks, possibly going beyond desktop access speed in the overall search experience. (SX for short from here on, as in ) UX WonderSwipeās Solution This is what WonderSwipe offers, for your knowledge presenting super-smart phone: Navigate from search result to search result, by swiping through them horizontally, like you would swipe through a gallery of photos. The cornerstone of WonderSwipe is this completely gestural 2D UI. (more below) Right after Google return a page of search results, WonderSwipe goes to work, loading all 10 results in the background, in parallel. So the first result you swipe to may still take 5s like normal browsers (but likely less), further results you swipe to will take no wait time.This is the knowledge access I stated in title. worst case of 10x faster Each result will either be presented with the original HTML and Javascript of the webpage (above worst case for load time), if detected to be an article with a main body of text to extract (powered by the ), that text will be further summarized and presented instead.This article text extraction + summary avoids Javascript, HTML rendering and early image loading, which on average, even with the added mobile CPU processing in summarization. Blocking of in articles that require Javascript is a side-effect, and necessary for speeding up access for users like you, without compromise. or former Readability cuts result access time by another factor of 2 ads and otherwise undesirables If article summaries are presented, the full text of the webpage can be viewed by tapping one of the summaries. The paragraph containing that summary would be scrolled to in the origianl text. If an article was found by your previous search, or a search by any other user of WonderSwipe, the result with summary is cached in our cloud. Results from our cloud cache would take only ~0.5s to load! Thatās another factor of 10 in reduced load time, for a faster knowledge access. total of up to 100x WonderSwipeās debug console, logging timestamps of the ideal case. Here, 9 cached results load in parallel within a total of ~0.5s, inĀ total. And, bonus: Keywords of your search query are highlighted on each search result, in HTML webpages, extracted article texts or summaries. WonderSwipe stays in portrait mode while you read, even if youāre fussing with toilet paper and what not on your quest for knowledge and inevitably and unwittingly rotate your phone. You could read search results expanded in a full Web view, and only there is landscape mode enabled for images and videos. Turn your search results into an audiobook! On any summarized search result, tapping the š¢ speaker icon turns on text-to-speech mode. The current summary sentence in view is read, and the summaries scroll down as they are read. When all summaries of a search result are read, WonderSwipe āswipeā itself to the next summarized search result, read out the article title, and proceed reading its summary. This continues until you tap the speaker icon again to stop, or it reaches the end of up to 10 results on the current Google search page. Hands-free mode. Thumbnail images of search results are preversed and showcased as bouncy headers. On summarized articles, other found images are listed together below the summaries. Extract web links in copied text from another app, and do a 1 tap search for that link, summarized and all. (š Paste: <link> on bottom) A note that my up to 100x faster knowledge access benchmark is network dependent (obviously). Due to WonderSwipeās approach of article text-first-and-only loading, in parallel, further accelerated by cached summaries, the overall improvement may actually be even more profound when comparing WonderSwipe vs. conventional browsers over particularly slow, intermittent mobile networks. Iāve also not quantitatively included further knowledge transfer improvements, resulting from article summaries and search keyword highlights as those are somewhat subjective. WonderSwipeās current naive summarization algorithm compresses word count to ~40% of original text on average, so consider at face value another 2x factor in speeding up article reading. And depending on your ability, keyword highlights is a great aid in speeding up text scanning further still, to extract meaning as you skim over search results. So I could bump my benchmark up to 200x or more, but whoās counting whatās already an astronomical improvement? š speed reading Wonderful! And what about , you say? Browsing search results is so last millennium. Yes thatās useful, but that only speeds up the query input part in a serious topical search. If itās a trivial search like , WonderSwipe isnāt the solution itās designed for. Youād find the answer directly on the first page of search results, using WonderSwipe or any old-school browser. Or you could indeed just ask Siri or Google or Alexa or Cortana. voice search this If your search is non-trivial however, like ā ā, thatāll take some digging beyond even the first page of search results, and voice assistants are unlikely to give a simple answer (or any answer). Siri for one defaults to web search when it canāt give a simple, factual answer, and that happens often. You may not find any good answer while googling either, and youāll have to refine your search query. All of which involves skimming search results to decipher relevance, and this kind of non-trivial search is exactly what WonderSwipe designed for. is AI a threat to humanity is Design Philosophy WonderSwipe came out of my realization that mobile search is slow. Too slow, and we oftentimes donāt bother until a later time on a desktop, or none at all when you forget. Whatās the point of the Web being a Great Library of human knowledge, if our computing paradigm moved from desktop to mobile, and we take a collective step backward and no longer bother accessing this library? The problem is speed of access and knowledge transfer. There is more to the Web than timber. On the other hand, WonderSwipe is a browser replacement. Itās a superset, focused around search. Not all search results are articles with text that can be extracted and summarized. When WonderSwipe fails, on web apps for example that cannot function without Javascript, the original HTML webpage is rendered by default, or you can load it explicitly by opening Web view within the app. not WonderSwipe attempts to extract meaning (article text) wherever it can, and when it does, it further apply algorithmic summarization to solve your TL;DR problem, which is especially apparent on the go. So thatās a , beyond the measurable 100x load time reduction in the entire Search Experience. further cognitive load reduction In optimizing SX, I realized the workflow of the standard browser is one dimensional. You click a link, you go back, you click another link, you go back again or you click on a new link. Itās a linear timeline which you go back and forth in. But why be limited to a 1D UI, when you can swipe in 2D and flow from one search result directly to the next? Lists of search results are already conveniently sequenced for this, WonderSwipe just lays them all out horizontally. Swipe left or right for the next or previous search results, up and down to get into the summary and images or full text of a particular search result. Perfect, fluid and completely gestural in 2D, as itās meant for the modern smartphone. Which brings us to the name of the app. In making the singular centre of user interaction without buttons, it becomes a to access the knowledge of the Web. And infinitely soāāāon reaching the end of search results 1ā10, another swipe left automatically searches the next page on Google. Further swipes continue to results 11ā20, 21ā30, etc. swipes wonder And in each search result, for articles that split themselves into multiple webpages that youād normally have to tap āNextā in-between, WonderSwipe also attempts to fetch all article pages and present them as 1 singular body of text, which gets summarized together. Nifty! Attention is the NewĀ Scarcity To optimize for SX completely and without compromise, I suggest breaking the current proposition of the user in the Web ecosystem. For you the user are not Googleās customer, nor are you for most web publishers. If you didnāt pay them, you are just eyeballs for their true customers, the advertisers. Your convenience in reading and optimizing for knowledge access isnāt their priority, you with ads actually is. loser distracting But your attention is valuable. This is an attention deficit crowd. credit: cloudflare More valuable than ever, with the Webās overflow of information. , as we get less and less bored. Thus, optimizing SX from the ground up in the userās perspective is all the more important, and demands fundamental rethinking. The extraneous gunk websites carry, either intentionally for monetization, or unintentionally with non-optimal heavy design or otherwise legacy design thatās not responsive to the mobile small screen and slower networks. Without fixing them holistically client-side, the mobile web continues slipping into irrelevance. Thereās a saying: āThe Capitalists will sell us the rope with which we will hang them.ā Letās stop buying their ropes. Attention is the new scarcity This means optimizing knowledge extraction on the Web to its logical end. By dropping Javascript altogetherāāāads, tracking and interactivity, WonderSwipe is able to achieve that 10ā100x access speed-up without compromise. Web view is a button tap away for search results that need it, but serves only as a fallback on your explicit request. Which brings us to the mission statementā¦ š„š„š„ The Future To make WonderSwipe an even bigger wonder, with our mission to Hereās my rough roadmap: (Iāll write more about them later) Make the Web Yours. Improve article text extraction and summarization. Iām currently just using untuned, off the shelves libraries. Offline referencing and search, on locally cached prior search results. A for every web search: Bookmarking, highlighting and annotation. Privately useful first, communally beneficial secondāāāa private research and note taking tool, while also reduce friction from search query to knowledge for the whole Web. social curation layer Q&A, for the truly hard search queries with no relevant results found. Think lifelines like phone a friend on Who Wants to Be a Millionaire. Yes thereās Quora, but Iām looking for a more open system, and one more integratable with search queries. Explicit sharing thatās way more useful than . Think embeddable, curated search results. LMGTFY Personalized/recommended trending searches. Top new interesting searches of the day for some communal discovery. Extensions to supercharge certain categories of websites with additional, useful data. Example: price history on shopping search results, fake news check. An open API for evolving a new open standard. Build/use a better general search engine than Google (maybe). Bing, DuckDuckGo? Add other specialty search engines like Amazon for different verticals (definitely). Adopt , if it doesnāt fizzle out. BATs Create a KnowledgeCoin to let users fund authors, curators directly. If the ICO bubble hasnāt burst first. Resize app for (Apple) watches, tablets, TVs, AR glasses, VR googles. WonderSwipe on a demo search (30s ) video Questions and comments? I want to hear them! I canāt do this without your input. This is the most exciting idea and project Iāve started since isoHunt in 2003. I hope you find WonderSwipe as useful as I do. Read more about our thinking about problems we want to solve in search and knowledge sharing, by following us here on Medium (top of page), or: Vote for us and send us feedback on Product Hunt Chat with us on , for support questions or feedback Slack Follow us on Facebook us Tweet You want to just download WonderSwipe and give it a spin? For those who , you should have received an invite email with code to redeem WonderSwipe on TestFlight. If not, WonderSwipe has launched on the iOS on April 18. signed up for beta App Store Stay tuned. We are working on our Android version now.
