bruce @_bmacd

ø¤º° @ollama °º¤ø bmacd.xyz 🏴‍☠️ Joined January 2012

Tweets

557
Followers

800
Following

817
Likes

2K

anandmaj @Almondgodd

3 days ago

I spent the past month reimplementing DeepMind’s Genie 3 world model from scratch Ended up making TinyWorlds, a 3M parameter world model capable of generating playable game environments demo below + everything I learned in thread (full repo at the end)👇🏼

94 255 2K 174K 2K

Download Video

bruce @_bmacd

3 days ago

Generative video models are developing emergent zero-shot abilities across perception, physics, reasoning, and even tool use. video-zero-shot.github.io

0 0 2 155 0

Download Image

bruce @_bmacd

4 days ago

Fancy badge unlocked

2 0 11 2K 0

bruce @_bmacd

a week ago

Now is the time to visit foreign countries with AirPod translation while people still find it exciting to see

0 0 3 121 0

bruce @_bmacd

2 weeks ago

I need a better way to review code than just looking at git diffs

0 0 4 117 0

bruce @_bmacd

2 weeks ago

Few understand peak VST plugin design

0 0 1 127 0

Download Image

bruce @_bmacd

a month ago

This dentist has root privileges

0 0 10 732 0

Download Image

ravens @_R4V3N5_

a month ago

do yall remember this paper lol. how come we're not forcing models to be little guys anymore

87 89 2K 123K 624

Download Image

bruce @_bmacd

a month ago

0 0 4 311 0

Download Image

bruce @_bmacd

a month ago

It’s crazy how hostile the Hetzner sign‑up process is, but once you get through the console dashboard is amazing

1 0 2 190 0

bruce @_bmacd

a month ago

If you’ve never been dunked on, you set your bar too low

0 0 0 106 0

bruce @_bmacd

2 months ago

Small LLMs are fun. Run on any laptop, and you can fine‑tune them easily. Fast, cheap, and efficient.

ollama @ollama

2 months ago

Small LLMs are fun. Run on any laptop, and you can fine‑tune them easily. Fast, cheap, and efficient.

29 149 1K 110K 323

1 0 5 173 0

bruce @_bmacd

2 months ago

People always judge new models before the implementation is fully correct, then move on before it’s actually fixed

0 0 1 99 0

ollama @ollama

2 months ago

Ollama's new app is here for macOS and Windows! Ollama 0.10! 🧵

213 424 4K 789K 1K

Download Image

Qwen @Alibaba_Qwen

2 months ago

🚀 Qwen3-30B-A3B-Thinking-2507, a medium-size model that can think! • Nice performance on reasoning tasks, including math, science, code & beyond • Good at tool use, competitive with larger models • Native support of 256K-token context, extendable to 1M Qwen Chat: Go to…