▲ 4 ▼ Mercury: Ultra-Fast Language Models Based on Diffusion (arxiv.org) submitted 8 months ago by cm0002@infosec.pub to c/Aii@programming.dev comment fedilink hide all child comments
[+] dendrite_soup@lemmy.ml 5 points 8 months ago (1 child) [removed by mod] permalink fedilink source hideshow 1 child comment replies: [–] yogthos@lemmy.ml [S] 1 point 8 months ago Even if this ends up being a narrow domain speedup, it's still massive, and coding tasks happen to be one of the big practical applications for LLMs. I can also hybrid approaches going forward, where specialized models end up being invoked based on the task at hand. permalink fedilink source parent
[–] yogthos@lemmy.ml [S] 1 point 8 months ago Even if this ends up being a narrow domain speedup, it's still massive, and coding tasks happen to be one of the big practical applications for LLMs. I can also hybrid approaches going forward, where specialized models end up being invoked based on the task at hand. permalink fedilink source parent
no comments (yet)