Quesma
Related tags:
Posts about ai-agentsPosts about aiPosts about llama-cppPosts about machine-learningPosts about openrouterPosts about productivity
Gemini 3.7 Flash, Grok 4.6, GLM-5.3 and DeepSeek V4 Pro joined the frontierClaude Code pricing: same tokens, same model, up to 40x the priceI wired 4 models together in Claude Code. It backfired 4 ways on Terminal-BenchQuantization hurts knowledge nonlinearlyA lesson about retries, hidden in the DeepSeek-V4 paperBenchmarking Kimi K3, Opus 5, Grok 4.5, and Gemini 3.6 Flash on Baba Is YouDo Qwen 3.6 27B quantizations break the pelican?I burned all my tokens researching how to save tokensBaba Is Solved by Fable 5 and GPT-5.6 Sol, but at what cost?The true cost of saying "Hi" to an AI agent