Ege Beşe (@egebese) header
Ege Beşe (@egebese) profile picture

creative engineer @fal prev. ux designer :: building ai products

türkiye
Joined August 2017
Photo by Ege Beşe (@egebese)Photo by Ege Beşe (@egebese)Photo by Ege Beşe (@egebese)Photo by Ege Beşe (@egebese)Photo by Ege Beşe (@egebese)Photo by Ege Beşe (@egebese)Photo by Ege Beşe (@egebese)Photo by Ege Beşe (@egebese)Photo by Ege Beşe (@egebese)Photo by Ege Beşe (@egebese)
Ege Beşe retweeted
Video2Game Claude can't design very original little game on his own. So I let H3 Max on @fal generate the gameplay video first, and Claude turns it into a real game you can play in the browser: every image, 3D model and sound generated on fal, written in @threejs only.
56
146
28
1,610
210,249
Ege Beşe retweeted
VEED Dubbing is now live on fal. - Translates videos with cloned voices and lip-sync. - Pro supports 94 languages and 14 regional accents, preserves background audio, and handles multiple speakers. - Provides target accent and voice cloning strength controls.
21
13
5
166
14,770
probably due to gta 6
ALERT: Several countries including Japan, UK, Switzerland, and Germany, have recently urged citizens to stockpile emergency supplies amid war, disasters and cyber attack fears.
4
1,038
Ege Beşe retweeted
World to World I gave Claude Opus 5.5 a Gaussian splat of a garden and asked it to rebuild the scene in Blender Procedural objects, Geometry Nodes, Shader Nodes, then captured textures mapped onto selected surfaces
28
44
12
482
561,854
Ege Beşe retweeted
A little refresh for fal.ai. New look, new pages and a few fun Easter eggs. Made by fal Design Labs.
18
14
6
179
20,240
we were seeing a lot of tools made opensource with REA, cmon guys do opensource Arc for us
We've decided to sunset Arc on December 22, 2026. That's not an easy sentence to write. We spent years building Arc and celebrating each and every release along the way: we have so much pride and love for what we made alongside the Arc community. Our priority is to deliver best-in-class security for our members. Keeping a browser secure takes constant, dedicated work that is only increasing in the age of AI. Dia was built from the ground up to meet today’s security standards, so that's where our engineering and security teams will focus moving forward. We've worked to make switching to @diabrowser as easy as possible for Arc members. Here's how: · Your passwords, bookmarks, extensions and history come over to Dia seamlessly. · Spaces, Folders, and Tab Groups are in Dia and import over with your data intact. · Dia now surpasses Arc benchmarks in stability, speed, and security. · The browser features you use in Arc are free in Dia, and the AI is optional. Thank you for using Arc, for pushing us to make it better, and for building alongside us. The team that made Arc is the same team behind Dia, and some of our most ambitious work is just ahead. We'd love for you to be there with us when it lands.
13
1,622
today we saw the 🐐 (@gokayfem )
2
33
2,103
single image and outputs are crazy with flux 3 max
3
2
37
1,873
all game concepts names and logos are made with gpt image 2.5 so hopefully there are no similar names and logos out there lmao
397
after H3 Max, this feels like witchcraft. the quality and speed are unmatched. it's actually unreal. fal Research made video generation faster than image generation, twice.
Introducing FLUX 3 Max, the latest post-trained video model from fal Research in partnership with @bfl_ai. FLUX 3 Max is tied for #1 in image-to-video quality on independent third-party benchmarks, generating a 10-second, 720/768p video in ~12 seconds. For the next three weeks, FLUX 3 Max is 75% off, making it the most affordable frontier video model at its quality level.
10
1,073
Ege Beşe retweeted
Meet the fastest model in the West. Introducing FLUX 3 Max, the latest frontier video model post-trained by fal Research in partnership with @bfl_ai. Tied for #1 in image-to-video quality. Among the fastest frontier video models. Now on fal.
Introducing FLUX 3 Max, the latest post-trained video model from fal Research in partnership with @bfl_ai. FLUX 3 Max is tied for #1 in image-to-video quality on independent third-party benchmarks, generating a 10-second, 720/768p video in ~12 seconds. For the next three weeks, FLUX 3 Max is 75% off, making it the most affordable frontier video model at its quality level.
25
37
10
412
30,077
there is a new player in town and it's the best
Introducing FLUX 3 Max, the latest post-trained video model from fal Research in partnership with @bfl_ai. FLUX 3 Max is tied for #1 in image-to-video quality on independent third-party benchmarks, generating a 10-second, 720/768p video in ~12 seconds. For the next three weeks, FLUX 3 Max is 75% off, making it the most affordable frontier video model at its quality level.
3
25
1,603
something new is coming to @fal
13
1,036
me if I get my hands on a 2nd dgx spark
Çin'de bir düğünde 12 bin dolarlık ekran kartı hediye edilen damat ağladı.
4
1,223
ok, i decided i don't really like GPT-6. it's not the agentic workflow i need. so i switched back to my basics and now use @herdrdev for pretty much my entire daily workflow. my current setup: - i have a main space called task manager. it spawns smaller workspaces connected to related Linear and Slack issues. - i use the herdr board to visualize all my existing tasks. - it's connected to Linear, Slack, Google Calendar, Gmail, and Wispr Flow for meeting recordings. - i can just talk to it, spawn new task spaces, and continue working with all the context. - task manager also has scheduled tasks, so it can find things for me to work on, remind me about stuff, etc. it's basically a very basic Hermes + OpenClaw setup, i guess. and honestly, i like this much more. also, Opus 5.5 is crazy good compared to GPT-6 Astra and 6.1. it has the kind of taste i need for creative engineering. understands visuals better, makes better design decisions, and can actually design good stuff. that's a big deal for the kind of work i do.
i changed the way i work with Codex. i used to just create chats and work from the recent area. never really used the pinned area. now i built a small task manager for myself inside Codex. it's connected to Slack, Linear, email, and my calendar. i also set up a few scheduled tasks: ** scans different sources for possible tasks, picks up the ones i should work on, and if there's no Linear task yet, creates one and assigns it to me. ** every 30 minutes, checks the status of my chats, updates labels, and color codes them so i can see what's going on. it also has my writing style, so my colleagues probably can't tell when GPT wrote a message. but i usually label messages that GPT writes and sends. another thing i added is an Obsidian skill with a scheduled task. at the end of each day, it logs what it did and saves useful knowledge from the chats and the work i did. kind of like a small work memory that keeps growing. still figuring out the best setup, but it's already useful. any tips are appreciated.
4
1
17
3,044
Ege Beşe retweeted
Introducing fal Worlds. A new way to create and interact with AI-generated worlds in real time. Build characters, explore environments, direct scenes, and watch worlds respond to your actions as they unfold. Get hands-on with the latest frontier world models, including LingBot World, H3 Max Director and more.
13
68
24
498
39,584
Ege Beşe retweeted
Krea 3, the new image editing model from @krea_ai, is now on fal. High-quality edits in under 6 seconds. Change the setting while keeping your subject consistent, or combine multiple reference images with simple text instructions.
13
15
1
170
8,577
Ege Beşe retweeted
Introducing fal Reframe. Change any video's aspect ratio without cropping or reshooting. Powered by H3 Max, Reframe extends your scene beyond the original frame while preserving the footage, timing, and audio. Go from vertical to widescreen, 9:16 to 1:1, and more.
18
26
7
322
18,860
i changed the way i work with Codex. i used to just create chats and work from the recent area. never really used the pinned area. now i built a small task manager for myself inside Codex. it's connected to Slack, Linear, email, and my calendar. i also set up a few scheduled tasks: ** scans different sources for possible tasks, picks up the ones i should work on, and if there's no Linear task yet, creates one and assigns it to me. ** every 30 minutes, checks the status of my chats, updates labels, and color codes them so i can see what's going on. it also has my writing style, so my colleagues probably can't tell when GPT wrote a message. but i usually label messages that GPT writes and sends. another thing i added is an Obsidian skill with a scheduled task. at the end of each day, it logs what it did and saves useful knowledge from the chats and the work i did. kind of like a small work memory that keeps growing. still figuring out the best setup, but it's already useful. any tips are appreciated.
7
2
23
6,019
Ege Beşe retweeted
. @krea_ai has something new coming to fal. Stay tuned.
11
19
3
220
15,424