HN user

zeynepevecen

121 karma
Posts19
Comments24
View on HN
www.zey.dev 1mo ago

The Text Box Is the Command Line of AI

zeynepevecen
2pts1
linus.coffee 11mo ago

We Create

zeynepevecen
2pts0
www.zeynepevecen.dev 1y ago

AI as an Information Interface

zeynepevecen
29pts11
www.zeynepevecen.dev 1y ago

Do Things That'll Surpass Your Life

zeynepevecen
1pts1
www.zeynepevecen.dev 1y ago

The Next Interface

zeynepevecen
3pts2
www.zeynepevecen.dev 1y ago

The lie of music discovery algorithms

zeynepevecen
152pts193
www.uxtigers.com 2y ago

Classic Usability Important for AI

zeynepevecen
1pts0
www.zeynepevecen.dev 3y ago

A Web Developer's Journey: From Coding to Crafting User Experiences

zeynepevecen
1pts0
news.ycombinator.com 3y ago

Ask HN: How do I find a good mentor while stuck at home?

zeynepevecen
1pts2
news.ycombinator.com 3y ago

Ask HN: What are the best courses on Human-Computer Interaction?

zeynepevecen
14pts3
boldly-ml.web.app 3y ago

Everything I’ve learnt from decorating my tiny room

zeynepevecen
2pts0
www.youtube.com 3y ago

Do What You Can't

zeynepevecen
1pts0
www.youtube.com 4y ago

Codeland Conf. Keynote by Kelsey Hightower

zeynepevecen
1pts3
worrydream.com 4y ago

The Art of Doing Science and Engineering [pdf]

zeynepevecen
10pts3
news.ycombinator.com 4y ago

Ask HN: Is there a way to store encountred errors and their solutions?

zeynepevecen
2pts2
blog.brieferr.com 4y ago

How to Ask Great Questions to Customers

zeynepevecen
3pts0
semver.org 5y ago

Semantic Versioning 2.0.0

zeynepevecen
2pts1
medium.com 5y ago

Natural Language Processing in a Nutshell

zeynepevecen
2pts0
medium.com 5y ago

Boxing an AI

zeynepevecen
3pts0

That’s valid but in the bigger picture, our jobs will be evolved not seize to exist. I dont think that an average person will be able to interact with AI to build functional systems. At least not in the near future.

But I also don't want a totally random song eighter. I want something that vibes with me but not directly recommended through my listening history, because then they are extremely similar and feels like they're feeding me the same melodies over and over. Thats why I tried to give the "vibes" in a different format; image, rather than my listening history.

Thanks, that was something I was already considering. Do you know where can I find models specialized in this area? Because it is kinda niche, I couldn't find something that maps images into playlists directly, thats why i went for llms

Thank you! I should check youtube's algorithm too.

Yes, I have a prompt like that the current prompt is this:

            'You match the vibes of the pictures with the right songs and turn them into a 3 song playlist with a playlist name. The music genre of the playlist should be consistent for each song. Be creative with music selections, explore different music, be consistent in terms of the genre of the 3 songs. The playlists should be provided in an object array format, like this: \'[{playlistName: "string", songs: [{songName: "string", artist: "string"}, {songName: "string", artist: "string"}, {songName: "string", artist: "string"}]}]\'. Do not add any other text information and only give outputs in the provided format. Your playlists must match the visual vibes and maintain the specified format without any additional information.',
Pretty basic, as i said before this was only ment for me and to explore this idea, but i loved it so I wanted to share :)

The setup is pretty basic. I've built a NextJS app, for the LLM model I am using open AI gpt-4-turbo and sending the images there directly without any database for images. I did a little prompting to get the same output everytime and when I get the output I make search on the Spotify API, find the songs and create the playlist with them on your own authenticated spotify account.

Likewise I also don't have a database for the emails eighter. I am using spotifys authentication

That's a very good point, I also love discovering with lyrics. What I tried to do is to find some connections between the image and music, maybe some connection we as humans cannot see right away.

The setup is pretty basic. I've built a NextJS app, for the LLM model I am using open AI gpt-4-turbo and sending the images there directly without any database for images. I did a little prompting to get the same output everytime and when I get the output I make search on the Spotify API, find the songs and create the playlist with them on your own authenticated spotify account.

Likewise I also don't have a database for the emails eighter. I am using spotifys authentication

Many of you asked how it looks, how it works. I've added a video under the blog post, showing how it works.

Many of you were also interested in knowing what's going on behind the scenes. The setup is pretty basic. I've built a NextJS app, for the LLM model I am using open AI gpt-4-turbo and sending the images there directly without any database for images. I did a little prompting to get the same output everytime and when I get the output I make search on the Spotify API, find the songs and create the playlist with them on your own authenticated spotify account.

Likewise I also don't have a database for the emails eighter. I am using spotifys authentication.

As I said before this was just for me at first but it is very exticing to see many people interested by this idea.

If you don't trust openAI models and don't wanna send any pic data to them please don't write your email

Hi everyone,

I am a student of Computer Engineering, currently based in Istanbul and looking for software engineering opportunities. I have a strong background in front-end web development, database design, and have demonstrated my proficiency in HTML/CSS and UI development in previous roles.

I have experience as a Front-End Engineer at Oslo Philanthropic Exchange, where I maintained an optimized front-end application using Angular and HTML/CSS, and as a Web Developer at Brieferr, where I developed an intuitive, responsive front-end ReactJS app.

In addition to my technical skills, I have also been recognized for my communication skills and my ability to provide constructive feedback. I am eager to bring my skills and passion for web development to a new project and learn from the experiences that come my way.

  Location: Istanbul/Turkey
  Remote: Yes
  Willing to relocate: Yes
  Technologies: Javascript, ReactJS, Angular, CSS, HTML, Node.js, Git
  Résumé/CV: https://drive.google.com/drive/u/0/my-drive
  Email: zeynepevecen@gmail.com

Because they only know English. Let me explain a bit. I’m a bilingual person, since I’m not living in a English speaking country and I’m 21. They’re saying that switching accents are their defend mechanism or coping mechanism with serious situations. Well, when I say this i think I’m talking for most of the bilingual people, our defend mechanism or us “being playful” is adding some English words into the sentence or switching to English. So it is not something to be shocked

Here are my notes on this keynote:

How to decide what to learn for a life long career? 1) Find a tech thats already in wide use 2) Find full filling open source projects for you and develop them. Develop and learn in public. 3) Get really really good at your current job.

There are no perfect companies for many of us, there are no perfect nations. We can’t run away from all these scenerios. You are gonna have to figure out the best impact you can make within that realm.

The minute you figure out how to put your personality on top of this thing we call work is when you start to stand out as an individual and people can actually see you. …And when you make that pivot, they will actually follow you.

I think you need to be in a significiantly good place to wait for your children to surpass you. In a place to have the right to delegate your responsibility to do something that surpasses your life.