Search
AI
OpenAI and Broadcom unveil Jalapeño, a chip built for LLM inference
The accelerator targets the work of producing model responses, with initial deployment planned for the end of 2026.
Google · Chips
Google launches two new AI chips to compete with Nvidia
The eighth-generation TPU splits into TPU 8t for training and TPU 8i for inference, with up to 3x faster training.
Google · AI
Google unveils TurboQuant, shrinking AI working memory by at least 6x
A new compression algorithm cuts the memory AI models use while running. The internet is already calling it "Pied Piper."
OpenAI · Cerebras
OpenAI signs a deal reportedly worth over $10 billion with Cerebras for faster responses
Cerebras will deliver 750 megawatts of compute to OpenAI through 2028, aimed at making ChatGPT answer faster.
Nvidia · CES 2026
Nvidia launches Vera Rubin: up to 5x faster than Blackwell for AI
Jensen Huang told CES 2026 that Vera Rubin is in full production, with OpenAI, Anthropic and AWS among its users.