Hackernews posts about Cerebrum
- The 1979 Design Choice Breaking AI Workloads (www.cerebrium.ai)
- Why Kubernetes Serving Breaks Down for Real-Time AI (www.cerebrium.ai)
- The datacenter where the day starts with topping up cerebrospinal fluid (www.theregister.com)
- 100x Defect Tolerance: How Cerebras Solved the Yield Problem (2025) (www.cerebras.ai)
- The datacenter where the day starts with topping up cerebrospinal fluid (www.theregister.com)
- Amazon Will Use Cerebras' Giant Chips to Help Run AI Models (www.bloomberg.com)
- Breaking Down the Cerebras Wafer Scale Engine (wafer.substack.com)
- Show HN: AIRiskCalc – AI-Powered Health Risk Calculators (www.airiskcalc.com)
- Show HN: Axiom Refract – Full architectural record for any codebase (axiomrefract.com)
- Yates – Prisma with Postgres RLS (github.com)
- Yates – Use Prisma with Postgres RLS (github.com)
- Show HN: Voice bots with 500ms response times (fastvoiceagent.cerebrium.ai)
- Show HN: A personalised AI tutor with < 1s voice responses (educationbot.cerebrium.ai)
- Show HN: Building a Real-Time AI Avatar for Coaching and Training Simulations (coaching.cerebrium.ai)
- Show HN: Turning a Live Video into Instant Purchases Using AI (live-stream-shopper.cerebrium.ai)
- Show HN: Turning a Live Video Stream into Real-Time Purchases With AI (live-stream-shopper.cerebrium.ai)
- Open-source alternative to v0, Lovable, bolt (coding-agent.cerebrium.ai)
- An Alternative to OpenAI Realtime API for Voice Capabilities (www.cerebrium.ai)
- AI Companies need to partner with Serverless compute platforms vs. K8s (www.cerebrium.ai)
- Surfer: Personal Digital Footprint Exporter (github.com)
- Scaling your ComfyUI workflow behind a API endpoint (www.cerebrium.ai)
- AI chipmaker Cerebras files for IPO (www.cnbc.com)
- Cerebras Code now supports GLM 4.6 at 1000 tokens/sec (www.cerebras.ai)
- Cerebras systems raises $1.1B Series G (www.cerebras.ai)
- Cerebras achieves 2,500T/s on Llama 4 Maverick (400B) (www.cerebras.ai)
- WTH Is Cerebrolysin, Actually? (moreisdifferent.blog)
- GPT-OSS 120B Runs at 3000 tokens/sec on Cerebras (www.cerebras.ai)
- Qwen3 Coder 480B is Live on Cerebras (www.cerebras.ai)