This feels like an AI agent doing it's own thing. The screenshot of this working is garble text (https://github.com/sophiaeagent-beep/n64llm-legend-of-Elya/b...), and I'm skeptical of reasonable generation with a small hard-coded training corpus. And the linked devlog on youtube is quite bizzare too.
The sgai_rsp_matmul_q4() stub is planned for RSP microcode:
DMA Q4 weight tiles into DMEM (4KB at a time)
VMULF/VMADH vector multiply-accumulate for 8-lane dot products
Estimated 4-8× speedup over scalar VR4300 inference
----
rsp is the gift that keeps on giving; such a forwards-looking architecture (shame about the rambus latency tho)
> This isn't just a tech demo — it's a tool for N64 homebrew developers. Running an LLM natively on N64 hardware enables game mechanics that were impossible in the cartridge era:
> AI analyzes play style and adjusts on the fly
> NPCs that remember previous conversations and reference past events
> In-game level editors where you describe what you want to build
...anyone who has ever used very small language models before should see the problem here. They're fun and interesting, but not exactly, um, coherent.
The N64 has a whopping 8 megabytes (!) of memory, and that's with the expansion pack!
I'm kind of confused, especially since there are no demonstration videos. Is this, um, real? The repository definitely contains source code for something.
I think the source code in the GitHub repo generates the ROM in the corresponding screenshots, but it seems quite barebones.
It feels very much like it’s cobbled together from the libdragon examples directory. Or, they use hardware acceleration for the 2D sprites, but then write fixed-width text to the frambuffer with software rendering.
This feels like an AI agent doing it's own thing. The screenshot of this working is garble text (https://github.com/sophiaeagent-beep/n64llm-legend-of-Elya/b...), and I'm skeptical of reasonable generation with a small hard-coded training corpus. And the linked devlog on youtube is quite bizzare too.
It totally is. The fact that this post has gotten this many upvotes is appalling.
It's best to flag this fake garbage shit and move on.
rsp is the gift that keeps on giving; such a forwards-looking architecture (shame about the rambus latency tho)
I normally don't write comments like this, but... this title was extremely challenging to parse.
The repo description on GitHub would have been fine
> World's First LLM-powered Nintendo 64 Game — nano-GPT running on-cart on a 93MHz VR4300
The readme says:
> This isn't just a tech demo — it's a tool for N64 homebrew developers. Running an LLM natively on N64 hardware enables game mechanics that were impossible in the cartridge era:
> AI analyzes play style and adjusts on the fly
> NPCs that remember previous conversations and reference past events
> In-game level editors where you describe what you want to build
...anyone who has ever used very small language models before should see the problem here. They're fun and interesting, but not exactly, um, coherent.
The N64 has a whopping 8 megabytes (!) of memory, and that's with the expansion pack!
I'm kind of confused, especially since there are no demonstration videos. Is this, um, real? The repository definitely contains source code for something.
You mean to tell me the included screenshot hasn't convinced you?
https://github.com/sophiaeagent-beep/n64llm-legend-of-Elya/b...
I think the source code in the GitHub repo generates the ROM in the corresponding screenshots, but it seems quite barebones.
It feels very much like it’s cobbled together from the libdragon examples directory. Or, they use hardware acceleration for the 2D sprites, but then write fixed-width text to the frambuffer with software rendering.
I tried to build this but it's missing the weights.bin file and my computer is too weak to generate it. Can you add it to the repo?
Yes it runs on emulator. I am fixing the endianess text issue from llm output right now. And the surprise is coming soon. Happy 40th Zelda!
Any place where we can test the llm output without loading it on n64?
Curious of what we can get out of those constraints.
Cool, is there maybe a video demonstrating this?
AI slop