iPhone 17 Pro Demonstrated Running a 400B LLM(twitter.com)

689 points by anemll 7 months ago | 314 comments

An X post from @anemll showing a 400B-parameter MoE language model running locally on an iPhone at about 0.6 tokens per second via a Flash-MoE app.

Losing Trust in Google(twitter.com)

16 points by cheviethai123 2 years ago | 4 comments

Anthropic is burning more and more dev goodwill(twitter.com)

23 points by tosh 6 months ago | 8 comments

Stargazers intersections for most popular GitHub projects in Venn diagrams(twitter.com)

27 points by ashvardanian 3 years ago | 8 comments

Gemini won't return C++ coding help if you're under 18 "to preserve your safety"(twitter.com)

21 points by g42gregory 2 years ago | 13 comments

Curious about the training data of OpenAI's new GPT-OSS models? I was too(twitter.com)

220 points by flabber 1 year ago | 52 comments