Дания захотела отказать в убежище украинцам призывного возраста09:44
One more trend worth calling out: it's becoming common for LLMs to use CLI tools instead of MCPs (and it seems like every company is shipping one: Google Workspace CLI, Braintrust is launching one soon). The reason is token efficiency. MCP servers inject full tool schemas into context on every turn whether the agent uses them or not. CLIs flip this: the agent runs a targeted command, and only the relevant output enters the context window. I use agent-browser heavily for exactly this reason versus using the Playwright MCP.
，更多细节参见whatsapp
With the closure of the HuggingFace LLM leaderboard, and no access to powerful GPUs, I stopped running experiments. But with the flood of new Open Source models (Qwen, MiniMax, GLM, and more), and finally having just enough compute at home, I have started working on the current batch of LLMs. The heatmaps keep coming back with the same general story, but every architecture has its own neuroanatomy. The brains are different. The principle is the same. And some models are looking really interesting (Qwen3.5 27B in particular). I will release the code along with uploading new RYS models and a blog post once my Hopper-system finishes grinding on MiniMax M2.5.，更多细节参见手游
palomar-sync -- sync follower counts and PageRank to OpenSearch
10 additional monthly gift articles to share