Taelin's banner

Taelin

@VictorTaelin • 79,550 subscribers

₍^. .^₎⟆

Shorts

first ray tracing demo on Bend2! looks unimpressive til you realize there's no shader nor opengl buffers on EVERY frame, it: - allocates a "quadtree JSON" with 1 million objects (??) - ray-traces over it, using a Python-ish marcher - renders every pixel to the screen - collects the entire structure and it still renders at ~80 FPS on 1024x1024 with no leaks and no stop-the-world garbage collection. it just keeps going again this is not optimized in any sensible way. this is rendering 3d graphics by allocating a massive JSON on every frame and then ray tracing and consuming it whole inside the Apple M4 GPU. and somehow it works I'm soo happy I finally have time to play with my creation 🥺

first ray tracing demo on Bend2! looks unimpressive til you realize there's no shader nor opengl buffers on EVERY frame, it: - allocates a "quadtree JSON" with 1 million objects (??) - ray-traces over it, using a Python-ish marcher - renders every pixel to the screen - collects the entire structure and it still renders at ~80 FPS on 1024x1024 with no leaks and no stop-the-world garbage collection. it just keeps going again this is not optimized in any sensible way. this is rendering 3d graphics by allocating a massive JSON on every frame and then ray tracing and consuming it whole inside the Apple M4 GPU. and somehow it works I'm soo happy I finally have time to play with my creation 🥺

40,638 views

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

Pokémon Red gameplay

Pokémon Red gameplay

3,635,010 views • 2 years ago

RELEASE DAY After almost 10 years of hard work, tireless research, and a dive deep into the kernels of computer science, I finally realized a dream: running a high-level language on GPUs. And I'm giving it to the world! Bend compiles modern programming features, including: - Lambdas with full closure support - Unrestricted recursion and loops - Fast object allocations of all kinds - Folds, ADTs, continuations and much more To HVM2, a new runtime capable of spreading that workload across 1000's of cores, in a thread-safe, low-overhead fashion. As a result, we finally have a true high-level language that runs natively on GPUs! Here's a quick demo:

RELEASE DAY After almost 10 years of hard work, tireless research, and a dive deep into the kernels of computer science, I finally realized a dream: running a high-level language on GPUs. And I'm giving it to the world! Bend compiles modern programming features, including: - Lambdas with full closure support - Unrestricted recursion and loops - Fast object allocations of all kinds - Folds, ADTs, continuations and much more To HVM2, a new runtime capable of spreading that workload across 1000's of cores, in a thread-safe, low-overhead fashion. As a result, we finally have a true high-level language that runs natively on GPUs! Here's a quick demo:

2,972,605 views • 2 years ago

8 hours of work with Fable: - Implemented this game prototype from scratch. Fable built the demo with fluid movements, robust rollback netcode, and US/BR servers it deployed itself. Try it (links below). - Investigated and solved a paradox in Bend2. This led us to a new, elegant consistency proof based on QTT. Extremely hard work. It implemented the full solution and regression tests. - One-shot Bend2's compiler. This is a 26k-loc file that converts a a program to C/Metal, based on the new runtime I've finished recently. A few months ago, I was impressed Sonnet one shot a parser. Seems like we're one-shotting compilers now... With this, all the hard parts of Bend2 are completed. (Sorry for the repost, last video had leaks. I'm sleepy now)

8 hours of work with Fable: - Implemented this game prototype from scratch. Fable built the demo with fluid movements, robust rollback netcode, and US/BR servers it deployed itself. Try it (links below). - Investigated and solved a paradox in Bend2. This led us to a new, elegant consistency proof based on QTT. Extremely hard work. It implemented the full solution and regression tests. - One-shot Bend2's compiler. This is a 26k-loc file that converts a a program to C/Metal, based on the new runtime I've finished recently. A few months ago, I was impressed Sonnet one shot a parser. Seems like we're one-shotting compilers now... With this, all the hard parts of Bend2 are completed. (Sorry for the repost, last video had leaks. I'm sleepy now)

92,553 views • 2 months ago

IT WORKS! Demo time 🥳 (next 10x productivity bump is here?) Suppose you must refactor a large codebase, e.g.: > "use I32 instead of U32 as the native number type" That task, by itself, is simple enough to be automated by Sonnet alone, right? Problem is: what if the codebase is too large to fit on the AI's context, and RAG solutions / editors like Cursor can't precisely isolate which parts require edit (because it needs some semantic reasoning)? What now? Do we fallback to human coding, as did the old Mayans? Of course not! We just split the codebase in chunks, and send each chunk to ~500 DeepSeek instances in parallel (!). Each instance then decides if given block should be edited or not. This is viable because DeepSeek is smart, fast and really cheap. Finally, we send the blocks that need edit to Sonnet, in a single prompt, and let it work normally. The entire process takes less than a minute, is cheap enough, and very effective. We conclude with a 'git diff' for manual review. In short, AI has came to grep search & replace. Since this script feels like dropping a bomb in your codebase, I'm calling it AoE, and it is available on VictorTaelin/AI-Scripts. Enjoy! Here's the demo:

IT WORKS! Demo time 🥳 (next 10x productivity bump is here?) Suppose you must refactor a large codebase, e.g.: > "use I32 instead of U32 as the native number type" That task, by itself, is simple enough to be automated by Sonnet alone, right? Problem is: what if the codebase is too large to fit on the AI's context, and RAG solutions / editors like Cursor can't precisely isolate which parts require edit (because it needs some semantic reasoning)? What now? Do we fallback to human coding, as did the old Mayans? Of course not! We just split the codebase in chunks, and send each chunk to ~500 DeepSeek instances in parallel (!). Each instance then decides if given block should be edited or not. This is viable because DeepSeek is smart, fast and really cheap. Finally, we send the blocks that need edit to Sonnet, in a single prompt, and let it work normally. The entire process takes less than a minute, is cheap enough, and very effective. We conclude with a 'git diff' for manual review. In short, AI has came to grep search & replace. Since this script feels like dropping a bomb in your codebase, I'm calling it AoE, and it is available on VictorTaelin/AI-Scripts. Enjoy! Here's the demo:

631,272 views • 1 year ago

faster mobile version Room → Macbook → Apple M4 → Atoms → Quarks also deployed for you to play! (link below)

faster mobile version Room → Macbook → Apple M4 → Atoms → Quarks also deployed for you to play! (link below)

63,303 views • 2 months ago

opus 5 test

opus 5 test

37,722 views • 1 month ago

programming in 2025 is pathetic typical 1h refactor done in 4m20s

programming in 2025 is pathetic typical 1h refactor done in 4m20s

345,769 views • 1 year ago

a quick demo of this workflow I really recommend it, way faster than CLI agents

a quick demo of this workflow I really recommend it, way faster than CLI agents

176,288 views • 9 months ago

Deleted again because misinformation 🥲 Gemini 3.5 Flash *is* available on the API. Yet, both the API and the CLI versions are 3x slower than on the IDE! See the video below. → Antigravity IDE: 4 seconds (smooth) → Antigravity CLI: 15 seconds (buggy) So the point holds: they want you to use the visual IDE. Problem is: it is 2026. NOBODY should be using IDEs anymore. Get over it. Let it GO. I’m certainly not launching a VSCode fork to use a model, no matter how great it is. They invent a portal gun, only to lock it behind a taxi subscription, because they completely fail to realize their very product deprecates that other thing they think will make them money? Cursor is a great example of a company that (sadly) is very likely fail because of that mindset. Composer is actually surprisingly good model. They should put all efforts in serving it. Yet, they keep locking it under an old school product that nobody wants to use. And even these who DO use IDEs probably won’t necessarily pick YOUR IDE. And they shouldn’t. You do NOT need them to, to make money. Your model is the product. You keep chasing old business models. Completely out of touch. Meanwhile Anthropic is all charging at full speed to sooner or later surpass Google by just serving great models under an API /ctrlv

Deleted again because misinformation 🥲 Gemini 3.5 Flash is available on the API. Yet, both the API and the CLI versions are 3x slower than on the IDE! See the video below. → Antigravity IDE: 4 seconds (smooth) → Antigravity CLI: 15 seconds (buggy) So the point holds: they want you to use the visual IDE. Problem is: it is 2026. NOBODY should be using IDEs anymore. Get over it. Let it GO. I’m certainly not launching a VSCode fork to use a model, no matter how great it is. They invent a portal gun, only to lock it behind a taxi subscription, because they completely fail to realize their very product deprecates that other thing they think will make them money? Cursor is a great example of a company that (sadly) is very likely fail because of that mindset. Composer is actually surprisingly good model. They should put all efforts in serving it. Yet, they keep locking it under an old school product that nobody wants to use. And even these who DO use IDEs probably won’t necessarily pick YOUR IDE. And they shouldn’t. You do NOT need them to, to make money. Your model is the product. You keep chasing old business models. Completely out of touch. Meanwhile Anthropic is all charging at full speed to sooner or later surpass Google by just serving great models under an API /ctrlv

68,347 views • 3 months ago

so I slept on my Macbook and bricked its screen 🤦‍♂️ worst part I didnt push yesterday's work and I dont have any HDMI cable. thankfully, OSX comes with a TTS command built in, so I managed to log in blindly, launch iTerm and turn SSH on

so I slept on my Macbook and bricked its screen 🤦‍♂️ worst part I didnt push yesterday's work and I dont have any HDMI cable. thankfully, OSX comes with a TTS command built in, so I managed to log in blindly, launch iTerm and turn SSH on

217,683 views • 1 year ago

to elaborate, what surprised me is that we can just upload a melody, some lyrics to match, and it... just works? for example: → uploaded Tetris melody → wrote some crappy lyrics → 15s later, I got this it fits perfectly, matching notes to syllables! I had no idea this worked

to elaborate, what surprised me is that we can just upload a melody, some lyrics to match, and it... just works? for example: → uploaded Tetris melody → wrote some crappy lyrics → 15s later, I got this it fits perfectly, matching notes to syllables! I had no idea this worked

60,398 views • 6 months ago

Code editing has been deprecated I still need to be there to feed insights, but the actual editing is fully automated. I now program by just talking to Sonnet on terminal. This complex refactor should take days, and it was done by lunchtime. How long til it is fully autonomous?

Code editing has been deprecated I still need to be there to feed insights, but the actual editing is fully automated. I now program by just talking to Sonnet on terminal. This complex refactor should take days, and it was done by lunchtime. How long til it is fully autonomous?

163,330 views • 2 years ago

GPT-5 basically one-shot this

GPT-5 basically one-shot this

82,695 views • 1 year ago

I asked it not to use any Pokémon copyright 😐

I asked it not to use any Pokémon copyright 😐

52,838 views • 9 months ago

ok im pretty sure this wasn't supposed to find factors so fast

ok im pretty sure this wasn't supposed to find factors so fast

99,916 views • 1 year ago

DEMO TIME SupGen is a generative coding AI... except it isn't an AI. There is no model, there is no pre-training. You just give it some examples, and it gives you a program. It runs locally, in a single-core CPU. Oh, and it can also prove theorems. Here's a demo, including a brief TT intro. (The synth examples start at the 6 min mark.)

DEMO TIME SupGen is a generative coding AI... except it isn't an AI. There is no model, there is no pre-training. You just give it some examples, and it gives you a program. It runs locally, in a single-core CPU. Oh, and it can also prove theorems. Here's a demo, including a brief TT intro. (The synth examples start at the 6 min mark.)

87,898 views • 1 year ago

Another day of AI's optimizing the Bend-to-JS compiler Results: → consistent improvements in most tests → regressions are quickly corrected → some sus results (0.3s → 0.01s) - bug or legit? → compiler capped at 2k-LOC to avoid code explosion I'll review it next Monday

Another day of AI's optimizing the Bend-to-JS compiler Results: → consistent improvements in most tests → regressions are quickly corrected → some sus results (0.3s → 0.01s) - bug or legit? → compiler capped at 2k-LOC to avoid code explosion I'll review it next Monday

13,749 views • 6 months ago

No more content to load