News for hackers. Stuff that matters.
Re:Furiosa: 3.5x efficiency over H100s by whimsicalism on Wednesday January 14, 2026 @08:28PM (#46626703)
Got excited, then I saw it was for inference. yawns

Seems like it would obviously be in TSMCs interest to give preferential taping to nvidia competitors, they benefit from having a less consolidated customer base bidding up their prices.

Re:Furiosa: 3.5x efficiency over H100s by ttul on Thursday January 15, 2026 @01:21AM (#46628765)
My best guess after dipping my toe into semiconductor fabrication a decade ago is that there is a mysterious guru in a cave under a volcano who decides which customers get access to which nodes at which prices.
Re:Furiosa: 3.5x efficiency over H100s by sognetic on Thursday January 15, 2026 @04:25AM (#46630164)
Everything is currently pointing towards inference being the main cost driver for LLMs in the future. Test-time-compute requires huge amounts of tokens in inference and makes providing frontier models as services unprofitable.

Anyone not under some kind of export restrictions can scrounge together some GPUs to train a frontier model (hell, even DeepSeek which is under these restrictions could) but providing a service that can compete with OpenAI et al. will prove to be quite costly. 3x improvements in inference are therefore nothing to sneeze at IMO.