General Compute's $400M Loan Bypasses Nvidia GPUs
General Compute borrowed $400 million from Upper90 against a fleet of SambaNova SN50 inference chips, the first major AI infrastructure loan not collateralized by Nvidia hardware.
Articles Tagged "Inference"
Cerebras Pushes GPT-5.6 Sol to 750 Tokens Per Second
GPT-5.6 Sol is now live on Cerebras wafer-scale hardware at 750 tokens per second - roughly 10x faster than any GPU-based frontier model deployment in production.
AI Research: Smarter Evals, Token Cuts, Agent Gates
Three papers tackle benchmark saturation, orchestration waste, and silent policy violations in tool-using agents.
SambaNova Banks $1B as Firms Move AI Off the Cloud
SambaNova closes a $1B Series F at $11B valuation with JPMorgan Chase as its flagship on-premises inference partner and SN50 chips due in H2 2026.
ZML Ships a Free LLM Server That Runs on Any Chip
ZML's LLMD inference server runs Llama, Qwen, and Mistral on Nvidia, AMD, TPU, Apple Metal, and Intel Arc from a single binary - for free.
Grok 4.1 Fast
Grok 4.1 Fast is xAI's agent-optimized model with a 2M-token context window, #1 ranking on tau-bench Telecom, and one of the lowest input prices among frontier-adjacent APIs at $0.20/M tokens.
Agent Safety Gaps, Memory Learning, and Leaner Inference
Three new papers expose how production agent frameworks fail under attack, why RLVR training discards useful cross-episode signals, and how calibrated confidence cuts inference compute by 12x.
d-Matrix Corsair - In-Memory Inference Accelerator
d-Matrix Corsair is an SRAM-based in-memory compute ASIC in production since June 2026, targeting 10x faster and 5x more power-efficient LLM inference vs GPU baselines.
OpenAI Jalapeño - Custom LLM Inference ASIC
OpenAI's first custom AI chip, co-designed with Broadcom on TSMC 3nm, targeting 50% lower inference cost than GPU alternatives.
Agent Languages, Sampling Ceilings, and Abstention
Three new papers on agents inventing symbolic languages to cut reasoning tokens by 3-6x, sampling ceilings that waste inference compute, and context-engineering to double agentic abstention rates.
Claude Sonnet 5 Is Anthropic's New Agentic Default
Anthropic's Claude Sonnet 5 becomes the default model across all plans, promising near-Opus agentic performance at a third less than Sonnet 4.6's standard price.
Cline's $10 Plan Bundles Ten Open-Weight Coders
ClinePass gives developers access to ten curated open-weight coding models for $9.99 a month, betting the agent harness matters more than the model.
