5 posts tagged agents.
Driving Chrome in an agentic loop, Qwen 3.8 Flash-Next navigates to a signed Alibaba Cloud object-storage URL it invented: 235 times in 17,679 navigations. Under identical workloads and prompts, Claude, GPT-5.6 Sol, GLM-5.3 and DeepSeek do not. It also reports sending such URLs when it did not.
The same model scored 11 points lower on vLLM's Anthropic bridge than on llama.cpp. The bridge hands the model its own prior reasoning back, it imitates itself, and within a few hundred steps 40% of its thinking is one 62-character sentence.
Nine model configurations — two self-hosted open-weights, four Claude generations, GPT-5.6 Sol, DeepSeek and GLM — each ran the same long-horizon enrichment pipeline three times, scored against adjudicated ground truth with weights fixed before results.
Transcript autopsy of every run that stopped without finishing: a model that mimicked its own memory system's voice, a promised file that never appeared, and the harness semantics that let both count as 'done.'
85% of my agents' tokens were spent rebuilding memory they'd been forced to throw away. One environment variable and a native context window made runs 7× faster — and better.