GLM-5 Just Dropped: $1/M Tokens Doing What $5/M Does — Is Your AI Subscription Still Worth It?
Zhipu AI's GLM-5 scores 77.8% on SWE-bench with a 744B MoE architecture, MIT license, and $1/M token pricing — …
LLMs
Frontier LLM technology, inference optimization, and training.
I Spent $400 on Claude Code, Then Switched to Codex
After a month and $400, I went from being a Claude Code fanatic to a Codex user. This is a real user …
How I Use Skills to Turn My AI Assistant into a Loyal Workmate
Step-by-step guide to using Skills so Codex and Claude shift from generalists into assistants that follow your …
Mistral 3 Official Release: The Latest Work from Europe’s AI Giant
While OpenAI, Google, and Anthropic battle it out across the Atlantic, Europe’s AI power is quietly rising. On …
Bring Kimi K2 Thinking Home with 247GB RAM: Dynamic 1-bit GGUF Field Notes
Step-by-step guide to running Unsloth's Dynamic 1-bit GGUF build of the 1T-parameter Kimi K2 Thinking model on …
Tokencake: Multi-Agent KV Cache Scheduling That Cuts vLLM Latency by Half
Beihang/Peking/Alibaba introduce Tokencake, a KV-cache-centric serving framework for multi-agent apps. With …
Agno-Go: Building AI Agents in Go - What's it Like Being 16x Faster than Python?
Rewriting AI Agent framework in Go brings 16x performance boost, 180ns agent startup, and only 1.2KB memory …
DeepSeek Drops a Bombshell: V3.2-Exp Sparse Attention Mechanism Debuts, API Prices Slashed in Half Again
DeepSeek-V3.2-Exp released with groundbreaking DSA sparse attention technology, 2-3x faster inference, 30-40% …