Description of App
From Your Eyes is an assistant technology that brings together human and artificial intelligence and offers both fast and qualified visual explanation service to visually impaired and visually impaired users. There are three hundred and thirty million visually impaired people worldwide. One million of them are in Turkey, and ten million are in the United States. FYE consists of three parts: visually impaired users, trainable artificial intelligence services and descriptors. Visually impaired users can take any photo or select an image from their existing library and upload it to the application. Artificial intelligence delivers a draft description to the user immediately after the visual is loaded into the application. If the visually impaired user thinks that this draft description should be improved, he can also enter the description section in which aspect he wants it to be detailed and send it to the descriptors with a single click.
This request reaches the descriptors as a notification. When a descriptor enters the application, it selects an image from the request pool and makes written improvements to the text by comparing the image and the draft description. The process ends when the advanced draft is sent back to the user. The underlying AI services learn about these improvements with machine learning.
Comments
Try to get it to describe a video
I tried to get it to describe a video, and waited, and waited, and waited, and then it was uploaded, but then it didn’t give any description at all. It just said one photo and then give me a bunch of choices like how to help it improve, things like that. But as far as giving me any sort of a description, it failed miserably. Maybe it wanted to give me a hope of a description?
Can you list those choices?
What is this bunch of choices that you were given?
LLM
Couldn't find this info in the description, what LLM is used to generate the responses? They all have their strengths and weaknesses and it would be interesting to know what to expect.
OpenAI/GPT
It utilizes OpenAI's language model, but has its own independent AI for processing submitted files. The CEO informed us they had been looking for other alternatives after the DDoS attacks OpenAI had faced earlier this month.
Thank you
Thank you for the fast reply. Do you know which of OpenAI's models is used, GPT-3.5 or GPT-4?
It said
After it displayed the fact that a video was uploaded, then it said, teach your artificial intelligence, send this to a volunteer to be described, your descriptions, etc.
GPT 4 is now free for everyone, right?
Well, they should switch to GPT 4 soon, but I don't know what they're up to. All I know is that they were looking for some other alternative back when GPT was down.
As for video descriptions, I don't know what the exact cause is, but would already recommend waiting for the new AI trained with 15 million visuals. By the way, have you tried choosing the option to teach the AI on that screen? Or have you tried having FYE describe a photo instead, and compared the screens that you would get?
An Update
Based on the explanation from the company's founder during a conversation with her, you may change the app's interface language as well as that of descriptions by going to the My Profile option on the home/main screen and then selecting the My Preferences option. I also suggested that they make it possible to change the language from the device settings.
Reputation is earned; one can't buy or fake it.
Here's a recent live interview by Emre Taşgın on FYE and the CEO of From Your Eyes, Zülal Tannur: https://www.youtube.com/watch?v=CQJI4SGWAwM&pp=ygUNRW1yZSBUYcWfZ8Sxbg%3D%3D
Yes, I do know it's in Turkish. So are my comments, but they summarize several of the recent events, and all the points and concerns that users share. So what I'm gonna do now is just paste them as they are. That's all. No translation, no interpretation whatsoever unless requested! Ask Uncle Google, Apple, GPT or any other translation service of your choice, or a Turkish speaker to translate everything below from Turkish to English so that you make sure I don't mistranslate, omit or add/make up anything if you don't trust me. It was none other than me who first posted about this new app, and also did his best to answer several questions on both the new app and the old one despite much credible criticism due to the fact that you were, and are, not able to make use of the new AI. You've kept asking why the app is on the App Store even though it should still be beta-tested by a narrower group as it does not have the new AI as yet. Some have even been kinda prejudiced and biased mostly, if not solely, due to the fact that the app was released by a team from Turkiye. And I've done my best to acknowledge that all those concerns, aside from the bias and racist attitude that I strongly condemn, were and are totally understandable and that I also share them, while still encouraging you to give the app a chance. But now, as stated in my comments on the Youtube video, I've begun feeling more and more abused. So I'll now prove that FYE depends on its users much more than Zülal thinks, just like any other app. This is why it's also me posting his own comment here without hiding his frustration even when the reputation of a Turkish team is at stake. As I've stated multiple times already, I'm in no manner affiliated with From Your Eyes, let alone representing the company as an employee or a member of its team. So I'll share my honest feedback no matter what, and hope that this teaches Zülal a well-deserved lesson after all that has happened. The sooner she learns this lesson, the better for her and us all, because I still want to think FYE does have potential, albeit being wasted so rapidly.
Chances are, you wouldn't have ever known about FYE had someone from Turkiye not posted about it. Likewise, it's equally likely that you wouldn't have known about all the disappointment that many users experience had I not posted about it here. This should be a good opportunity for Zülal to finally acknowledge how users play a crucial role in spreading positive or negative feedback on any app or service. It will also be none other than me to clearly mention that if/when she finally comes to acknowledge how just saying that users are an essential part of the community, and truly acknowledging this fact through one's behaviors, are not necessarily the same thing, but not before I first make her acknowledge that I have offered particularly more support, suggestions and detailed bug reports that have helped make FYE how it is right now compared to the other members of that WhatsApp group mentioned in my comment. My purpose is to draw attention, and make her and everyone notice certain points that I have been posting about certain other developers as well, rather than destroying FYE's reputation. Let me repeat that I will also most likely be the first and only person to post about any revolutionary features that FYE gets, including the long-awaited new AI, and any positive changes in Zülal's attitude. Do note that, while I appear to be addressing or posting about Zülal or FYE, this piece of my mind is about every single one of such certain companies exploiting those with disabilities and their needs by claiming they don't have such a large customer base and therefore need to earn more so that they can maintain and/or develop existing and new apps. Things are extra-challenging if you live in Turkiye or elsewhere where exchange rates are a barrier especially if you wish to use certain apps, given that developers are now moving away from one-time purchases to subscription-based plans. Anyway, here's my whole comment on the interview and FYE:
Bu yorumu en başından en sonuna kadar hiçbir nokta atlanmadan, bilhassa Zülal tarafından okunması için yazıyorum ve kendisinden de sadece bana değil, herkese cevap vermesini talep ediyorum.
Bu yorumda;
• FYE hakkındaki AppleVis gönderim (İngilizce)
• baba programlar kanalında FYE hakkında yapılan videoya yorumum
• Emre Bey'e bu canlı yayını, Zülal'in tavrı, From Your Eyes ve FYE hakkında yazdıklarım
• İsmini şimdilik vermediğim bir arkadaşıma mesajım
• Bunlar dışında burada paylaşacağım görüş ve tespitlerim yer alacak. Bazılarını direkt aktarırken bazılarından alıntılar yapacağım. Ana fikri ve argümanları bozmadan eksiltme ve kısaltma, belirli kısımları tamamen çıkarma, daha önce eklemeyi unuttuğum şeyleri tamamlamak için yıldız (*) işaretleri arasında belirli ifadeler ilave etme gibi şeyler yapabilirim ancak burada sıraladığım her şeyin aslını kaynaklarında bulabilirsiniz. İsimleri ve kaynakları vermem de bundan. İsimlerini verdiğim şahıs ve kurumların da bunda bir mesuliyeti yok. Kendileri kanaatlerini paylaşmak istemedikçe onlardan sadece bu alıntıların doğruluğunu teyit etmelerini isteyebilirsiniz. Ben bunu şeffaflık için yapıyorum ve burada zikrettiğim her şeyi bizzat onlardan talep edebileceğinizi belirtiyorum. Onların burada yer alma sebebi bu. Zaten onlara mesaj gönderen de benim ve cevap verilecekse evvela bana verilir. Ben cevaplardan kaçmam hatta istediğim cevapları alamadığım için bu yorumları yaptım. İkna edici makul cevapları da asılsız ithamlar veya karalama kampanyası olarak nitelemem.
1. FYE hakkındaki AppleVis gönderim (Bunu ümitle yazdım.)
Gönderi bağlantısı: https://applevis.com/apps/ios/health-fitness/fye
2. baba programlar kanalında From Your Eyes Hakkında Kimse Bunları Konuşmadı! başlıklı videoya yorumumun tamamı (Bunu hayal kırıklığına rağmen ümitle yazdım.)
“ Ben eski uygulama bile yokken bu fikrin ilk doğuşuna şahitlik eden, FYE’yi AppleVis’te paylaşan ve Zülal’i üniversiteden de tanıyan biriyim. Zülal’le şahsen de tartıştığımız zamanlar vardır ve kişi olarak da her tavrını tasvip etmeyebilirim ama bu yorumu, kendisini sıkça tanıttığı şekliyle From Your Eyes’ın kurucusu ve CEO’su ile FYE uygulaması hakkında yazıyorum. Nötr kalmaya dikkat edeceğim. Doğrusu, ben de birçok zaman Zülal’e uygulama hakkında geri bildirim ya da kendisinin ifadesiyle “ileri bildirim” vermek için bile ulaşamadığımdan ötürü bu yorumu burada yazıyorum ve herkese ulaşmasını istiyorum. Zülal’in hakikaten meşgul olduğunu ve uygulamayı iyileştirmek için çalıştığını tahmin ediyorum ama ben de uygulama hakkında belki kimsenin deneyip bulmadığı problem ve öneriler gönderiyorum ona. Gönderdiğim şeylerden bazılarını çok beğendiğini söyleyip not alıyor, bazılarını hakikaten yapıyor hatta video betimleme fikri bana aitti ama bazılarına cevap dahi alamıyorum. Mesela 3 mesaj göndermişsem teşekkür edip biri hakkında cevap verebiliyor. Uygulama mağazalarda yayınlanmadan önce bir süre daha beta olarak kalmasını da tavsiye edenlerdendim. Eski uygulamayı tamamen kaldırıp yeni bir uygulama çıkarmalarını neden doğru bulmadığımı da anlattım ve bunun sebebini sordum ama ona da cevap alamadım. *Bunun cevabını canlı yayında aldık çok şükür!* Eski uygulamayı devam ettirirlerse indirme ve betimleme sayıları, yorumlar ve diğer her şey kalacaktı. Uygulamayı kaldırmak için bir gerekçeleri olabilir ama benimle paylaşılmadıkça benim zihnimde mesele açıklığa kavuşmaz. Paylaşmadıkları şeyi de ben bilemem. Şeffaflık probleminden daha çok yönetim ve organizasyon zayıflığı gibi geliyor bana. Zülal’in benden bu tür bir şeyi kasten gizleyeceğini zannetmiyorum ama ifade ettiğim gibi, geri bildirimlerime de cevap alamadığım zamanlar az değil. Kullanıcı grubu olarak da bir paylaşıma açık grup, bir de duyuru grubu kurulabilirdi. WhatsApp’ta topluluk ve hatta kanal oluşturmak da mümkün artık. Grup paylaşıma kapalı olduğu için, kullanıcıların Zülal’e özelden gönderdiği şeyler gruba iletilecekse önce Zülal’in filtresinden geçiyor. Bu videoyu da grupta kendi yorumuyla birlikte paylaşmış ve hukuki adımlar da dahil olmak üzere karşılık vereceklerini belirtmiş ama her bildirimin “ileri bildirim” olmayacağını fark etmesi gerekir. Tabii, şunu ifade etmem gerekiyor: “Hayalet buton” veya etiketsiz düğme probleminin Zülal de farkındaydı ve bunlar son güncellemelerle çözülmüş görünüyor. *Hayalet düğmelerin etiketsiz düğmelerden farklı olduğunu, FYE'de etiketsiz düğme problemi olmadığını ben de bizzat anlattım insanlara.* Uygulama içinde VoiceOver’ın “opaklık katmanı” dediği şey ise “Kapat” düğmesine karşılık geliyor ve “opaklık katmanı” olarak etiketlenmesinden FYE’nin geliştirici ekibi sorumlu değil gibi görünüyor. Bu noktalarda haksızlık etmemek gerekir. Bir de uygulamayı takip etmeden, hakkında fazla şey bilmeden indirip deneyen ama iyi betimleme alamadığını söyleyen kişiler var. Bunda da hem bu kişiler hem de Zülal ve FYE ekibi kusurlu. Eski uygulama varken onu bırakıp yeni bir uygulama yaptılar, bu yeni uygulamanın beta testini iyi yönetemediler ve uygulamayı mağazalara göndermekte acele ettiler, problemler varken ve yeni yapay zeka hazır değilken uygulamayı herkese açtılar ve eski uygulamayı kaldırıyorlar. Bunlar benim kendilerine de söylediğim şeyler. Yerli teknolojimiz diye bir uygulama çıkarıp bunu insanlara anlatamazsanız ve iki kelimenizden üçü İngilizce olursa, her şeyi duyurup pazarlamakta bu kadar acele ederseniz ve sonra beklentileri karşılayamazsanız neticenin bu olacağı açıktır. Bu kitleyi elde tutmak için bir stratejiyse kısmen başarılı ama hem Türkiye’de hem dünyada hayal kırıklığına ve itibar kaybına sebep olduğunu da bizzat gördüm. İki uygulama arasındaki farkları yeterince bilmeyen kişiler, FYE’yi Be My Eyes’la kıyaslıyor. Batı’da zaten bir ön yargı var Türkiye’den çıkan bir uygulamaya karşı. Türkiye’deki insanlarda da bu ülkede yapılan her şeyi küçümseme hastalığı var. Ben FYE’nin hakikaten çığır açabileceğini düşünüyorum ama süreç beceriksizce yönetildiği için ben de insanları buna ikna edemiyorum.
Not: Uygulamaya yeni isim bulmak için Zülal bir form paylaşmış ve fikirlerimizi yazmamızı istemişti, ben de “AI2C (A-Eye to See)” yazmıştım. Hâlâ bu ismin daha iyi olacağını düşünüyorum.”
Video bağlantısı: https://www.youtube.com/watch?v=Ez5W_11Ucr4&pp=ygUTQmFiYSBQcm9ncmFtbGFyIEZZRQ%3D%3D
3. Emre Bey'e yazdıklarımdan alıntılar (Bunları sadece hayal kırıklığı ile yazdım.)
“... çünkü son yayınınızdaki tavrı da hala bazı şeyleri anlamaya istekli olmadığını gösteriyor. Siz her defasında düzeltseniz de yine İngilizce kelimeler kullanması bunu açıkça gösteriyor ve kullanıcılardan uzak bir dil kullandığını ispatlıyor. Kendisi her sorunuza konuyu saptırarak verilerle cevaplayacaksa ben de bizzat kendisinin her beyanını veri olarak kabul edip delil olarak ortaya koyarım. Zülal'in her şeyden önce şuna karar vermesi gerekiyor: Uygulamayı Zülallerin hayallerini gerçekleştirmek için mi yapacak yoksa kâr elde etmek için mi? Kendisi Zülal olarak bu soruyu cevaplasaydı Zülal'in betimleme alabilmek için ücret ödemesini ister miydi? From Your Eyes kullanıcılarından bir şey beklemeden kaynaklarını yatırımcılarından alan bir şirket mi yoksa yerli olma iddiası ile kullanıcılarını sömüren girişimlerden biri haline mi gelecek? Şirketleri STK'lardan ayıracaksa, şirketlerin farkı da kâr amacı gütmekse, From Your Eyes için kullanıcıları bu kadar önemliyse biz burada kâr kaynağı mı oluyoruz? From Your Eyes kullanıcılarından bir şey beklemiyorsa işin bize dönük yönü STK'larınkinden çok farklı olmuyor mu? O halde From Your Eyes'ı STK'lardan farklı kılan, kullanıcıları değil, aldığı kurumsal destek mi oluyor? From Your Eyes'ın STK'lar gibi sahipsiz olmasını engelleyen de bu mu oluyor? O halde Zülal kullanıcılardan hiçbir şekilde ücret talep edemez! Size de birkaç eleştirim var: Siz sorularınızı öyle sormuşsunuz ki eleştirilerinizi ilk seferde direkt açıkça ifade etmemişsiniz. Net konuşmaktan çekinmişsiniz demiyorum ama sizin kullandığınız dolaylı üslup da Zülal'in karmaşık cevaplarla konuyu saptırıp kendi istediği yöne çekebilmesine yol açarak onun işine yaramış. Tabir yerindeyse biraz sıkıştırdığınızı hissettirmenizi beklerdim. Bu soruları Zülal'e benim sorma fırsatım olsaydı muhtemelen Zülal'in hiç cevap veremeden birkaç saniye beklediği, ne diyeceğini bilemediği zamanlar olurdu. Belki de yayını terk ederdi veya beni de karalama kampanyasının parçası olarak nitelerdi. Bir de sizin Zülal'e neden WhatsApp grubunun kapalı olduğunu, tutamayacakları sözleri vermiyorlarsa yapay zekâ için niçin net ve iddialı tarihler vermeye defaatle devam ettiklerini sormanızı isterdim. Her şeyin reklamını yapıp pazarlamaya vakit harcadıkları, ileri bildirim dedikleri şeyleri filtreledikleri, bunca tarih verilip beklentiler karşılanamasa da elde kalan kullanıcıları tutmak için her şeyi yaptıkları da doğrudur. Ben bunu zaten böyle düşünüyordum ama daha önce ifade etmemişim. Bakalım, benim şahsen de tanıdığım Zülal'e ulaştıramadığım bu şeyleri sizin vasıtanızla ulaştırabilecek miyiz? ...”
“Şunları eklemeyi unutmuşum. Zülal neden artık tarih vermiyor? Tutamayacağı sözleri vermemek için mi? Peki, Eylül ve Kasım’daki aksaklıklardan sonra mı öğrenmiş iddialı konuşup kesin tarih vermemeyi? *Emre Bey'in yayınında artık iddialı tarihler vermediğine dikkat ettim.* Öyleyse Eylül’deki hayal kırıklığı yetmeliydi ve Kasım’da tekrar tarih vermeye devam etmemeliydi. Siz buna risk yönetimi demişsiniz ama ben biraz da tevazu diyorum. Daha mütevazı bir insan yine tarih verebilir ama bunun tahmin olduğunu, aksi ihtimalleri dikkate aldıklarını da ifade eder. Tutamayacağı sözler vermemeyi de kendisi kasten yanlış tanımlıyor ve siz de buna müdahale etmediniz. Olmayan bir mükemmel yapay zekayı yaptıklarını iddia etmeleri verdikleri sözü tutmamak değil, yalan beyanda bulunmak olur. Devrim niteliğindeki mükemmel yapay zekalarını herkese açmak için defaatle tarih vermeleri ve o büyük günün hiç gelmemesi ise vaatlerin yerine gelmemesi olur. İşte budur tutamayacağı sözler vermek. Kelime oyunlarıyla, karmaşık cevaplarla, “dedike olmak” gibi başka hiç kimseden duymadığım İngilizce/Fransızca kelimelerle, Zülal Hanım’ın filtresinden geçen WhatsApp paylaşımlarıyla hakikat değişmez ve gizlenmez. ...”
4. İsmini vermediğim arkadaşıma mesajım
“... Ben dinledim bu iş artık canımı sıktığı için. Ben Zülal’i şahsen de tanıyorum ve bu From Your Eyes fikrinin de ilk çıkışına şahidim ama Zülal’i saf ve masumane bir heyecan ve iyi niyetle takip ve takdir edip sadece onun pazarladığı ve münasip gördüğü şeylerin yayılmasına hizmet eden, Zülal’in çok sevdiği tabirle uygulamanın “elçiliğini” yapan, From Your Eyes’ın kendisi için nasıl “fark yarattığını” paylaşan ama uğradığı hayal kırıklığını Zoom görüşmelerinden daha geniş ortamlarda paylaşmayan kişilerden olmayacağım.”
5. Bazı görüş ve tespitlerim
Bu zamana kadar her şeye rağmen FYE'yi insanlara tanıtmak için elimden geleni yaptığım gibi, şimdi de eleştirip her şeyi saf gerçekliğiyle insanlara anlatmanın zamanı gelmiş görünüyor. Zülal'in onca reklamını yaptığı video betimlemesi gibi birçok şeyin fikri bana aitti ve en çok hayal kırıklığına uğrayanlardan biri benim.
Kullanıcı topluluğu olarak tanımlanan WhatsApp grubunda paylaşılanlar, grupta paylaşanların rızası dışında grup dışına sızdırılmayacaksa uygulama neden grubun dışındaki herkese de açıldı? Bu gruba dahil olmayanlar geri bildirimlerini nasıl ulaştıracak? İleri bildirim mi demeliydim?
Grup içinde paylaşılanların dışarı açılmasına paylaşanlar kendileri izin veriyorsa Zülal ile özelden paylaşılanların gruba iletilmesine kim izin veriyor? Ben grup içinde dahi istediklerimi paylaşamayacaksam hatta Zülal'e özelden yazdığım WhatsApp mesajlarına ve e-postalara haftalarca cevap alamayacaksam grup dışında bir şey paylaşmaktan elbette çekinirim!
Hem geliştirici ekibinin hem UX ekibi olarak tanımlanan kullanıcı deneyimi ekibinin hem de Zülal'in kullanıcılara teknik bilgi ve talimat verme, geri bildirimlere cevap verme ve merak edilenleri cevaplama/açıklama becerisi oldukça sınırlı. Geliştiriciler teknik bilgiye sahip ancak düzgün Türkçe konuşmayı bilmiyor. Zülal, yapay neşesi ve gülümsemesi ile oldukça uzun cümleler kurarak fan kitlesini, kendisine Zülal Abla diyerek hâlâ iyi niyetle destek veren masum gençleri heyecanlandırıyor ancak uygulama hakkında en çok fikir ve hata paylaşarak asıl desteği veren benim gibi insanları yok sayıyor. Bakanlarla, Be My Eyes ve başka şirketlerle yapılan görüşmeler, alınan ödüller paylaşılıyor ama Zülal’in de bizzat itiraf ettiği gibi, From Your Eyes gücünü hakikaten kullanıcılarından alınıyor ve bu ihmal ediliyor. Ben de FYE’yi Be My Eyes’dan ve diğer alternatiflerden ayıran o müthiş özelliklerinin birçoğunu bizzat teklif eden kişi olarak kullanıcıdan daha çok kullanılan olduğumu düşünüyorum. Deneyim ekibi de beta testlerini yaptırmak için bize önce App Store Connect, sonra TestFlight yükleyip davetleri kabul ederek uygulamayı indirip test edebileceğimizi bile düzgün açıklayamadı. Bunlar da WhatsApp mesajları olarak elimde var.
* Note: I split this thing into two comments in Youtube, as one single comment would exceed the 10000 character limit.
New aı update
Now enjoy the aI image processing model trained with 15000000 data.
No, wait.
It should be me who can post about this app before everyone else, and I did tell you earlier that I would post about things that I liked and found useful and successful as well as those that I disliked and disapproved of. So yes, the new AI trained with 15 million visuals is now ready for public use, and I got quite elaborate descriptions on a par with those I would get from Be My Eyes. I also compared FYE to its former AI, and the results are outstanding. The new AI is currently available for photo and document descriptions/OCR, and is reported to be ready for video descriptions soon. Now this will make the app truly revolutionary if it works well enough. I proudly present a feature that I once suggested myself. Well, one of many to be exact.
Oh we are truly sorry Enes
May I respectfully ask of your highness to please let me post any updates on this app that I find interesting, or should I patiently wait for your majesty to post first so you’re lordship wouldn’t be offended?
I kindly suggest next time your excellence moves faster so none of the minions can steal your glory once again.
Humbly, your faithful subject.
Okay, I probably have to rephrase it.
Sorry, but I was a little... No, I was quite furious at that moment when I realized that post by this Turkish guy. He's been posting positive stuff about the app but just remains silent when bad stuff is posted about it. So I just want him to shut up as he does when people, and I in particular, criticize the developer and app. My previous response should actually have been directed straight at him. I'm also furious at how I've been treated and therefore want no biased comments to interfere in my posts. I am doing my best to offer unbiased findings and observations, and don't want anyone from Turkiye to get in my way unless they also wish to post honestly. You can always refer to my comment titled "Reputation is earned; one can't buy or fake it.".
A SHORT DESCRİPTİON OF THE UPDATED VERSİON OF AI
Hi there.
I am the founder and CEO of FYE.
We are open to all of your your comments.
You can download and start using the FYE mobile application from both the App Store and the Google Play Store using the links here. After downloading the application to your phone, you can easily complete the installation by making the necessary account selections and settings.
THEME SELECTION SCREEN:
After the application is downloaded, you can choose a theme from the theme selection screen for an accessible use or skip this part.
ACCOUNT SELECTION SCREEN:
After determining your account type by selecting whether you are a "Visual Impaired User" or a sighted "Volunteer Descriptor", you can log in or register from the login screen you encounter.
A. VISUALLY IMPAIRED USER ACCOUNT
If you are a visually impaired user, you will be directed to the home page when you first open the app. You can complete the settings for your account from the Profile section, access your latest notifications from the "Notifications" section and use the tab bar below. You can start using your artificial intelligence immediately by using the "Connect to FYE" button in the middle of the page.
USING YOUR AI ASSISTANT
After pressing the "Connect to FYE" button, you will be presented with three options: camera, gallery and document. While you can take a photo or video from the camera section, you can upload images of these two from the gallery section, or if you only want to read a PDF document, you can upload a document from your device by clicking the document option. Remember, a maximum of ten photos and only a maximum of one minute of videos can be sent at a time.
FILTER SCREEN:
After selecting the images to be depicted by artificial intelligence, a filter screen with three options opens. The "Introduce me and continue" button on this screen allows your artificial intelligence assistant to produce personalized descriptions for you based on your previous usage habits. The "Describe text only" button allows you to access only the text in an upload that contains both images and text. Materials such as menus and picture books in restaurants are ideal for this option. The "assign to my artificial intelligence assistant" part is one of the most popular parts. By clicking this option, you can teach your artificial intelligence assistant to describe the images you upload by pretending to be who it is. For example, you can learn about a cityscape through the eyes of a historical figure or a fictional movie character that never existed. This part is also ideal for solving complex problems in daily life. For example, when you attend a specific event, you can assign a special artificial intelligence assistant to that location so that you can easily orient yourself there. Your assistant will describe the environment for you in the most accurate way within the context of the event.
VISUAL DESCRIPTION SCREEN
Once the images are described, you can add this description to your favorites or perform further operations from the menu. For example, you can share your photo, add a caption to it so that you can easily find it in your description archive or delete it. You can ask and guide your artificial intelligence more questions or get more information by clicking the "I want to guide my artificial intelligence assistant more" button at the bottom of the screen. If you need a human to evaluate and improve the description, you can open a request for human improvement by clicking the "I need this description to be improved by volunteer descriptors" button. You will receive a notification when your improved description completed.
MY DESCRIPTIONS SCREEN:
From this screen, you can access your previous descriptions and categorize them. You can use this section as your own personal archive.
DISCOVER AND ENJOY WITH FYE SCREEN:
You can access your current score status and achievement badges from the "My achievements" section on this screen. Remember, every image you upload earns you points. The badges you earn in the application can help you announce your achievements to everyone.
My apologies Enes
It seems we both fell victim to the same sentiment.
Thank you for your cool headed answer.
No problem.
No problem.
Off topic a little ...
This is kind of off topic, but this is posted in the wrong category. How is this a health and fitness app? :)
I posted the entry
and guess I did that according to the information on the App Store.
I look forward to Apple watch support
Even if it's late, the arrival of the new aI is promising. I'll be happy to let you know when Apple Watch support and live descriptions arrive.
Enes, I believe you...
It is just weird that an app that basically does descriptions calls itself a health and fitness app.
I didn't say or imply you didn't.
Just wanted to clarify the situation and that I wouldn't be able to change the category as I thought fit anyway.
Very very good, but guiding the AI seems faulty
Welcome FYE to the stage of excellent visual assistance solutions!!! Now the adventure can begin and unfold with you!
Yes, with the new AI in place, descriptions produced by FYE are very much on par with Be My AI. And I get them even a bit faster.
All in all the app works great. I have found only one problem since the new AI is in place:
I tried to guide the AI a bit on an image and asked some more info, like in Be My AI.
I selected a photo on my device through the "Gallery" interface, and then I continued through the "Introduce me and continue" entry point, got my initial description (a very good one, five star rating), then double tapped "I want to guide my artificial intelligence assistant more". I entered my guidance and question into the edit field through dictation and double tapped "send". Nothing happened, just a "ding" sound. And the guidance interface reappeared practically instantly with an empty edit field as if it were ready to continue the conversation, but there was no reply. And a strange "1, null" label appeared underneath the "close" button, indicating that there was indeed something strange going on with this. I waited, retried, but to no avail. I had no better idea than to double tap "close" and in reaction to that the whole FYE interface disappeared except the bottom row of icons. I could bring the main interface back by choosing another section, and then going back to "homepage".
I tried this on multiple images with the exact same behaviour.
When FYE used to have the very dumb AI, I could converse with it through this interface.
Does this happen for others?
May I need to log out and log back in for this to work? I have FYE on my phone since last November and I am logged in since then. My FYE version is the latest: 1.0.11 (Dec 27, 2023)
I'm having the same problem…
I'm having the same problem while guiding the ai. And you can tell about the problem which you encounter by using the contact us section within the profile menu, I suppose, so it could gain more priority among the bug reports. I did that yesterday.
And Choosing fye from the share sheet does nothing, I sent that as well, but maybe you can try and send your experiences.
Thanks Fatih
Interestingly enough, sharing content with FYE via the share sheet works for me. I have tried it from the Photos and Mail apps on multiple images. When I double tap the button labelled "FYE" near the top of my share sheet, it takes me to the screen from where I can initiate a description ("Introduce me and continue" etc.). Then I get the description all right, and I can also find it later in the "My descriptions" category.
Thanks Fatih for mentioning the share sheet, because I haven't been aware that this is also an option for FYE, and I may not have tried this out.
You’re welcome.
You’re welcome.
Finally...
FYE now utilizes its new AI to describe videos shorter than a minute, something no other app like Be My Eyes or PiccyBot can ever do under the current circumstances. FYE still has certain problems of its own, like the fact that you can't ask additional questions or instruct the AI to improve its initial description, or that it usually fails to provide the text in images containing both visuals and text even though it does provide an abundance of details on the text, its attributes and for what purpose it may have been written, meaning it does detect the text. The company's CEO says that their next step will be what she calls instant image processing and descriptions, which sounds far-fetched to me, given certain technical limitations like connection speed even if the AI processes and describes images almost instantly.
One more thing: FYE can now be used on VisionOS according to the CEO.
FYE 1.0.12
Last week an update came out for FYE with "bug fix and improvements" (according to update description).
I thought that the non-working AI instruction / additional questions feature had finally been resolved. Yes, it was resolved, but in a funny, sort of FYE-like way: it simply got removed entirely from everywhere in the app! What an ingenious solution! This sadly indicates to me that the developers have no clue how to go on with this important feature and have no real plans with it. Furthermore this hints at them struggling with some serious issues in working with the OpenAI language model. This is a pity.
I thought then "okay, let's go on with this revolutionary video descriptions with the new AI thing then, maybe it is a success story indeed". And what did I get? "Operation failed" and a Back button. Nothing else, no video description whatsoever. On multiple tries on multiple days. No video I captured was longer than 10 seconds, and most were under 5 seconds. Not too impressive.
I must say FYE has a khmm interesting and unique development story. Maybe bizarre or absurd is a better word. It somehow originates from the darker side of the Moon. Nevertheless I still hope that some day it will be through with this long and winding maturation process. After all hope is always the last thing to die.
Finally I strongly suggest to the developers to look into the plethora of open-sourced large language models available, as they were looking for independence from OpenAI. My favourite is e.g. the LLAVA 1.6 model (demonstration webpage at llava.hliu.cc). I consult this regularly withmy image description needs on PC and with technical questions. It is very performant. Its capabilities seem very adequate for me to provide the large language model layer behindthe visual AI of FYE. But there are other excellent options on Huggingface worth investigating. If the developers had the infrastructure to train a visual AI model on 15 million visuals (which they did in fact), then they have more than enough horsepower to run the inference of an LLM model for the FYE users. And there is a very performant open-sourced inference tool called llama.cpp on Github applicable on many such LLMs.
FYE 1.0.12
Hello.
Thank you for your comment.
I am Zülal, the founder and CEO of FYE.
I am also one of the developers of the application.
I wanted to personally respond to your comment containing your concerns.
Below you will find a few items:
1. We said we would turn on the FYE video feature, but we haven't turned it on yet, so this part is not working right now. Our test groups are testing and improving, so just because we announced it in advance does not mean we are open. We wanted to explain this issue. We opened it to a minority, called the beta group, and have not rolled it out yet. When it opens, our users will share it here.
2. The main reason why we removed the chat section is that we have completed the development of our own NLP model and want to implement it in this section. We are currently using the GPT language model in the application, both in this section and in the descriptions, but due to a change caused by OPEN AI, the Chat section was not working. This made us want to implement the NLP process, which we had already completed, faster than we expected. We would rather have a feature not be there than not working. You will also receive the development here in an update.
3. I think you have experienced the successful results of our artificial intelligence model, which we created as a result of our motivation to develop our own fully independent artificial intelligence model, not the image processing model offered by OPEN AI. This shows why we are on this path and that we complete every R&D we say in a very short time. The success and rates of our own model, which we trained using more than 15 million images in 9 months, have been proven. Moreover, considering that we trained an NLP during this period and released a completely new App, I can proudly say that we are not a company that makes devious words but cannot complete its R&D. Explanations of the reasons why you feel this way are given above.
4. We are currently also open to access APPLE Vision Pro and Meta. In other words, we have achieved what we promised in the wearable technologies section. We are openly moving forward to improve together with you.
We find your comments valuable and attach importance to them. We ask you to be objective while emphasizing the features you want to improve, without ignoring the parts we have developed.
Thank you very much.
Best,
Zulal
A few opinions
I've been using FYE since it was first introduced. First, I need to make a few points that I feel uncomfortable if I appreciate the current point it has reached and actively use the app. 1- Independent llm models need to be developed urgently. 2- They said they would open the beta group's video release last week, but there has been no improvement since. This casts a shadow over the highly praised transparency. While sharing the developments, I reject a transparent and silent understanding of the problems. At least I would expect them to learn not to make promises they couldn't keep. 3- Yes, app updates should improve features instead of removing them. Follow-up questions for artificial intelligence visual explanation are more functional and sustainable without directing human volunteers. Although there are technical problems with this, there are already many market examples. Also, I think human volunteers should not be involved in the future of FYE, even if they currently help with the education of artificial intelligence. 4- Despite everything, I have high hopes for implementation. Although the developer cannot respond quickly to problems and new ideas, he is a solution-oriented and intelligent person. He understands and sympathizes with the difficulties he faces when creating his dream application. However, as the alternatives increase in the market, I think he should accelerate the development a little more.
Hi Zülal
Thanks for coming here and responding in detail. I appreciate it.
I have written my comment based on my in-person user experience and the information I've had. I didn't mean anything derogatory. Your detailed response clears a lot of things up which I haven't been and couldn't have been aware of and thanks for that.
I congratulate you for developing a very own language model too besides the independent visual AI and look forward to seeing it in action in the app. I think that's a logical advancement which I considered you capable of as training a visual AI on 15 million visuals is a very significant thing and who can do that probably can also make the language model part. I am glad that you are able to do that. That can make FYE independent in this respect and all will benefit from that.
As somebody who also has development experience in various fields, I don't criticize you for speed as I fully know that quality work takes time. However I suggest you a better communication pattern regarding not-fully-ready-yet features. In regards of FYE 1.0.12 I would have found it much better if instead of removing the chat section entirely without saying a word, the app had displayed a polite message upon pressing the button in question. Something like "This feature is currently unavailable. We are working on a long-term solution. Please be patient. Thanks". For the video part: instead of "operation failed" it would be much better to say: "This feature is currently in beta and not open to everybody yet. Please be patient. Thanks".
You see A communication pattern like this is very easy to implement and takes very little time, but it matters very much for the users. It would simply leave a better taste in our mouths while you polish out a feature. That's all, but this is quite important.
I warmly and sincerely wish you the best luck with this app since I feel it has got great potential. That's why I scrutinize it from inside out time after time and comment on it. I have been tracking your progress since the launch of the From Your Eyes web app last May.
Emre, just shut up, will you?
You're Turkish yourself yet you're referring to the CEO with male pronouns? It is even likely that you just used some translation service and pasted the result in the comment box. What is more important and problematic, though, is that your points make no sense at all. How come the volunteers help train the AI while staying out of the process? And as for the video description thing being available, I don't remember the CEO stating explicitly that it would only be open to a small group of testers.
I'm sorry but you don't have this right
I am not sure you are qualified and equipped to tell me what to do or not to do. Please don't spam and use your excellent English to review apple vis's view of criticism of individuals.
How about we begin with your posts?
A thorough review of your posts in this thread will be of much more use and reveal how you have been posting nonsense and ignoring everyone else and their warnings ever since I first posted the app entry. Now who is the spammer here? I have not come across any posts from you elsewhere whatsoever. You have only been posting about FYE (formerly From Your Eyes), and you have hardly ever posted anything negative about the app. You did not even respond to my previous post stating this very fact.
Please Keep the Discussion Respectful
Let's please keep things civil and respectful. Telling someone to “shut up” is not acceptable behaviour. We want to encourage open discussion and dialogue, not attempts to silence others.
You're absolutely free to disagree with someone's point of view or argue against what they've said. However, resorting to personal attacks or trying to shut someone down goes too far. We should be able to have reasonable debates and discussions without that kind of hostility.
If you strongly disagree with someone, feel free to explain your counterarguments substantively and respectfully. But orders to “shut up” have no place here.
A bit of heated discussion is okay, but let's make sure we avoid descending into insults or attempts to shut others down. Thanks for understanding.
I don't have to respect anyone who does not respect me.
If certain individuals assert that they have the right to constantly offend and humiliate others both explicitly and implicitly in a wide variety of ways or otherwise resort to deception and other unacceptable means, then the best solution that I can come up with is to order or force them to stop. I do urge everyone to go through each and every post in this very thread from the very first one (including the app entry itself and my message in Turkish) up to this point, and make up his mind. I mean his or her. You know, this is how we refer to females.
Show a single example
I don't know you personally and I don't have a single direct or indirect criticism. Why do you have to attack me? I only share my opinions, positive or negative, and it goes without saying that this is not the only thread I write in. Please let's communicate respectfully without becoming narcissistic because that's what adults do. And I'm sorry if my not replying to your previous message bothered you, I try to stay away from toxic debates.
And what does this have to do with narcissism?
Let me point you at your comment titled "New aı update" and the subsequent comments in response, which should make you finally acknowledge how you continued to post flattering remarks and ignored the other posts. @Panais also told me my reply to that post of yours sounded arrogant, but I didn't have to dismiss that as a baseless accusation as I did know it was backed by the fact that I could have phrased it better, as I stated back then. You claiming I am a narcissist, on the other hand, is unfortunately not something I will take seriously.
Whoa
This application sounds promising. I actually wanted to follow this post in order to keep up with updates, but with the confusing argument going on here, it's a bit of a turn off for me. I don't know what the argument is about. I feel like this discussion should come to an end, or at least be done privately. Anyway, don't come for me. I'm only interested in the application, not the argument happening here since it doesn't affect my life in anyway, shape, or form. Either way, regardless of who is right or wrong, this argument is becoming pointless and unnecessary, and detracting from the purpose of the post. I guess I can always keep up with the app some other way or, I'll wait until the discussion gets back on track to check back here.
I don't understand, but it's okay
I don't know what you mean, it was just a comment that the new advanced AI is in use. I also avoid prejudging people. I am saying that I am uncomfortable with your narcissistic tone. This is my last reply to you, as I did not reply to your previous comments because of their arrogant and patronizing nature. Please try to communicate constructively.
This is what I want already.
All I want is consistency, honesty and transparency.
Re: I don't have to respect anyone who does not respect me.
Let me be clear - you don't have to respect or agree with the opinions of others here. Disagreement and debate are perfectly acceptable. However, we do ask that you respect their right to voice those views so long as they too do so appropriately regarding civility, insults, harassment, etc.
In light of where this discussion has gone, I'm asking both parties involved to take a step back so that we can return to talking about the app itself.
Thank you for your understanding and cooperation. We want to make sure AppleVis remain a constructive space for productive discussions about the apps and technology we all care about.
Re: Whoa,
I'm sorry if I've inconvenienced you. Yes, I was just saying that the app is promising and has a promising future. I've been talking to the developer in person, through the beta channel and online meetings and I want to share my impressions as much as I can. For example, I have to say that I'm looking forward to the rayban smart glasses and fye integration. I'm also told that video description is coming soon.
It was already me...
It was already me who posted the app entry upon concluding that he would not keep his promise, even though Emre had claimed he would remove the entry for the old app and post an entry for the new one once it was available. I have also stated more than once that I am willing to share any updates, breaking events and useful information you might find interesting despite all the frustration. I am more than willing to help make this thread remain one centered on the app itself, so long as certain other members share the same commitment instead of acting like some unofficial representative of the company. I am also part of the very same group of testers, and I have also tried my best to send the CEO suggestions and bug reports that now make up many of FYE's core features, not to mention that many were just ignored.
WARNING!
That guy, Emre, has just messaged me on WhatsApp in private, threatening and insulting me in a way that I can't quote in this post. He must have found my number among the members of that tester group he mentioned. Not because I was hurt or frightened or anything, but because he doesn't know how to communicate with human beings and instead offends and harasses others do I demand that he be removed from the group as soon as possible, as he can do the very same thing to anyone else. I do know this might not be the most appropriate place to send that post, but I want this to be a clear sign of his lack of respect and I am not sure I will be able to reach out to the CEO on WhatsApp, who also happens to be the group's admin, so I want this very post of mine to be noticed by everyone, including Zülal and Emre himself. I have the WhatsApp messages as evidence, and would win a case before the court. Another reason why I made this post is that he will not be able to deny anything from now on. Now, back to topic...
Update
Any new information on this app? Hold the drama. Thanks.
FYE 1.0.13
Some days ago this week FYE 1.0.13 came out with "bugfix and improvement" as the official what's new states.
Hmmm. I took two test pictures. The first resulted in some meaningless numbers, and the second in "no AI description available in current language" message. Not too promising. I retried for some time and the latter message was all I got every time.
Video descriptions still don't work: "Operation failed", so the same as in March when I was told here that this feature wasn't publicly available yet. It seems it still isn't.
Follow-up questions feature was also not reintroduced in this "bugfix" version. It would not mean anything by the way as no meaningful initial description is generated.
So unfortunately right now FYE reverted to a practically unusable state as no meaningful results can be achieved with it.