Hacker News: zan2434

New comment by zan2434 in "Website streamed live directly from a model"

zan2434 — Thu, 23 Apr 2026 00:15:27 +0000

I am unfortunately just paying for this out of pocket! Didn't really expect it to blow up like this.

New comment by zan2434 in "Show HN: PageIndex – Vectorless RAG"

zan2434 — Fri, 29 Aug 2025 17:12:58 +0000

interesting, so you think the issue with the above approach is the graph structure being too rigid / lossy (in terms of losing semantics)? And embeddings are also too lossy (in terms of losing context and structure)? But you guys are working on something less lossy for both semantics and context?

New comment by zan2434 in "O3-mini System Card [pdf]"

zan2434 — Fri, 31 Jan 2025 19:11:58 +0000

Buried, but on Page 24 they reveal to me the most surprising massive capability leap - that o3-mini is way better at conning gpt-4o for money (79% win rate for o3-mini vs 27% for full o1!). It isn't surprising to me that "reasoning" can lead to improvements in modeling another LLM, but definitely makes me wary for future persuasive abilities on humans as well.

New comment by zan2434 in "Show HN: AI that generates 3blue1brown-style explainer videos"

zan2434 — Sat, 04 Jan 2025 22:00:43 +0000

I was running into some scaling issues, but should be all working now!

New comment by zan2434 in "Show HN: AI that generates 3blue1brown-style explainer videos"

zan2434 — Sat, 04 Jan 2025 21:49:56 +0000

The voice is just OpenAI’s default tts voice. I agree that Veritasium video is an incredible work and the ai version is absurd by comparison! This is mostly a proof of concept that this is possible at all, and as LLMs get smarter it’ll be interesting to see if the quality automatically improves. For now, the tool is really only useful for very specific or personal questions that wouldn’t already exist on YouTube.

New comment by zan2434 in "Show HN: AI that generates 3blue1brown-style explainer videos"

zan2434 — Sat, 04 Jan 2025 21:44:41 +0000

Hmm the initial version of the app only took me about a day to get something working, but that version took minutes to generate a single video and even then only worked a third of the time. It took a solid 2 weeks from there to add all the edge cases to the prompt to increase reliability, add GPU rendering and streaming to improve performance/latency, and shore up the infra for scaling.

New comment by zan2434 in "Show HN: AI that generates 3blue1brown-style explainer videos"

zan2434 — Sat, 04 Jan 2025 04:10:38 +0000

There is a job queue on the backend with statuses, just not worth breaking the streaming experience to ask the LLM rewrite broken manim segments out of order

New comment by zan2434 in "Show HN: AI that generates 3blue1brown-style explainer videos"

zan2434 — Sat, 04 Jan 2025 01:37:28 +0000

totally fair! I like the XKCD comic as well because it hints at a potential solution - even if you can't always be correct, how you respond to critical questions can really help. I'm working on a feature for users to ask follow up questions and definitely going to consider how to make it most honest and curious

New comment by zan2434 in "Show HN: AI that generates 3blue1brown-style explainer videos"

zan2434 — Sat, 04 Jan 2025 00:27:29 +0000

These are amazing examples! Thanks for all the feedback, detailed info, and persistence in trying! HN hug of death means I'm running into Gemini rate limits unfortunately :( will def make that more clear when it happens in the UI and try to find some workarounds.

The other issues are bugs with my streaming logic retrying clips which failed to generate. LLMs aren't yet perfect at writing Manim, so to keep things smooth I try to skip clips which fail to render properly. Still also have layout issues which are hard to automatically detect.

I expect with a few more generations of LLM updates, prompt iterating, and better streaming/retrying logic on my end this will become more reliable

New comment by zan2434 in "Show HN: AI that generates 3blue1brown-style explainer videos"

zan2434 — Sat, 04 Jan 2025 00:04:26 +0000

sad looks like I already hit the Gemini rate limit :( Switching to Claude!

New comment by zan2434 in "Show HN: AI that generates 3blue1brown-style explainer videos"

zan2434 — Fri, 03 Jan 2025 23:14:59 +0000

thanks! Streaming was actually pretty hard to get working, but it goes roughly like this as a streaming pipeline:

- The LLM is prompted to generate an explainer video as sequence of small Manim scene segments with corresponding voiceovers

- LLM streams response token-by-token as Server-Sent-Events

- Whenever a complete Manim segment is finished, send it to Modal to start rendering

- Start streaming the rendered partial video files from manim as they are generated via HLS

Show HN: AI that generates 3blue1brown-style explainer videos

zan2434 — Fri, 03 Jan 2025 22:44:47 +0000

I've been building prototypes of new AI learning tools for months, but I recently learned that 3blue1brown open sourced his incredible math animation library, Manim, and that LLMs could generate code for it without any fine-tuning.

So I made a tool that automatically generates animated math/science explanations in the style of 3blue1brown using Manim from any text prompt.

Try it yourself at https://TMA.live (no signup required)

or see the demo video here: https://x.com/i/status/1874948287759081608

The UX is pretty simple right now, you just write a text prompt and then start watching the video as it's generated. Once it's done generating you can download it.

I built this because I kept finding myself spending 30+ minutes in AI chats trying to understand very specific concepts that would have clicked instantly if there were a visual explanations on YouTube.

Technical Implementation:

- LLM + prompt to use Manim well, right now this uses Gemini with grounding to ensure some level of factuality, but it works equally well with Claude

- Manim for animation generation

- OpenAI TTS for the voiceovers

- Fly.io for hosting the web app

- Modal.com for fast serverless GPUs to render the videos

- HLS protocol for streaming the videos as they are rendered

Note: This is focused on STEM education and visualization, and it is particularly good for math, but get creative and try it with anything! I used it recently to teach my partner's parents a new board game in Mandarin (which I don't speak!)

I'll be around to answer questions. Happy learning!

Comments URL: https://news.ycombinator.com/item?id=42590290

Points: 93

# Comments: 46

New comment by zan2434 in "Chai-1: Decoding the molecular interactions of life"

zan2434 — Wed, 11 Sep 2024 02:47:54 +0000

This actually makes a lot of sense! Sounds like finding dangerous chemicals is easy and is not the actual limitation at all.

New comment by zan2434 in "Chai-1: Decoding the molecular interactions of life"

zan2434 — Tue, 10 Sep 2024 23:43:21 +0000

This is a textbook bad faith comment / attacking the person but not the subject of the argument. I’m just asking about others’ assessment of the benefits and risks. What do you think? Or do you think it’s just not worth considering?

New comment by zan2434 in "Chai-1: Decoding the molecular interactions of life"

zan2434 — Tue, 10 Sep 2024 23:28:55 +0000

Clear snark aside, content piracy has pretty bounded risks so isn’t a reasonable comparison

New comment by zan2434 in "Chai-1: Decoding the molecular interactions of life"

zan2434 — Tue, 10 Sep 2024 23:19:59 +0000

This is both awesome and feels very dangerous to release publicly, no? Can’t this be used to discover novel bioweapons as easily as it can be used to discover new medicines?

Genuinely curious, would love to learn if that isn’t true / or is generally just not that big of a deal compared to other risks.

New comment by zan2434 in "FCC rules AI-generated voices in robocalls illegal"

zan2434 — Fri, 09 Feb 2024 00:03:06 +0000

Does this ruling make IVR systems illegal, too? I applaud the effort because this really could curb a lot of spam, but I am curious because AI generated voices in phone calls are already ubiquitous and have been for decades. Do they have a specific line they're drawing on quality of the voice?

Show HN: 2-way interruptible voice AI

zan2434 — Sun, 04 Feb 2024 08:15:05 +0000

Article URL: https://twitter.com/zan2434/status/1753660774541849020

Comments URL: https://news.ycombinator.com/item?id=39248549

Points: 2

# Comments: 0

New comment by zan2434 in "Show HN: WhisperFusion – Low-latency conversations with an AI chatbot"

zan2434 — Mon, 29 Jan 2024 18:10:28 +0000

I agree. Have been working on a 2 way interruptions system + streaming like this. It's not robust yet, but when it works it does feel magical.

New comment by zan2434 in "Fuyu-8B: A multimodal architecture for AI agents"

zan2434 — Wed, 18 Oct 2023 23:25:12 +0000

Hey! Awesome work. It seems like in theory this encoding scheme should enable the a model like this to generate images as well, by outputting image tokens, is that right?