Hacker News
- 100x defect tolerance: How we solved the yield problem https://cerebras.ai/blog/100x-defect-tolerance-how-cerebras-solved-the-yield-problem 179 comments
- AIBI: Revolutionizing Interviews with AI https://cerebras.ai/blog/aibi-revolutionizing-ai-interviewing 2 comments
- Llama 3.1 405B now runs at 969 tokens/s on Cerebras Inference https://cerebras.ai/blog/llama-405b-inference 156 comments
- Cerebras Inference now 3x faster: Llama3.1-70B breaks 2,100 tokens/s https://cerebras.ai/blog/cerebras-inference-3x-faster 84 comments
- Cerebras Inference: AI at Instant Speed https://cerebras.ai/blog/introducing-cerebras-inference-ai-at-instant-speed 72 comments