Gemini CLI and Codex Level Up MCP Safety and Setup: Trust Prompts vs Auto-Install Skills
Two CLI assistants walk into the same tooling bar. One checks IDs at the door; the other quietly installs the band’s gear before the show starts. Gemini’s new “trust, but verify” moment Gemi...
Edition File
All editions ›Recent Editions
Full history ›Pydantic Updates Agent Instructions Without Rewriting the Opening
An agent’s task state can change without changing the start of its next model request. Pydantic AI’s new append mode puts the update at the end of the conversation, preserving the earlier prefix for possible cache reuse.
OpenAI Gives 20 Languages the Same Database Exam
MultiLangBench asks a model to build a database engine in a chosen language. The revealing part is the examiner: reference SQLite reads the file that implementation leaves behind.
Unsloth Can Reject a New Model to Keep Another Loaded
New Studio code gives chat, image and video models a choice: share GPU memory when possible, make room, or refuse a disruptive load. When media does displace chat, it can also save the primary GGUF model’s cached work.
Pi Can Park Agent Tasks Until the Host Wakes Them
Pi’s experimental durable harness now stores a sleeping task’s deadline and next step, letting a host alarm bring execution back later. The change separates continuing work from a continuously running process.
How AI Agents Work
The long-form map behind the daily paper: context, tools, loops, memory, delegation, safety, interface, and trust.