Fable 5.1 Shows a Shift: More Tool Calls, Shorter Reasoning
Early Fable 5.1 usage data shows a stronger action-oriented shift: 78% of responses end in a tool call (vs 51% for Fable 5), and reasoning tokens appear more of…
Early Fable 5.1 usage data shows a stronger action-oriented shift: 78% of responses end in a tool call (vs 51% for Fable 5), and reasoning tokens appear more of…
Fable 5.1, released Sep 1 and available on Requesty, sharply reduces verbosity: median responses drop from 603 to 270 tokens, favoring action over explanation.
dax, who is building OpenCode, teases a new stealth AI model called Omen Alpha, available exclusively to OpenCode Go subscribers at a promotional rate of $100 u…
OpenCode has quietly introduced Omen Alpha, a new model available exclusively to OpenCode Go subscribers, with $100 of usage offered for just $10.
Anthropic is exploring Function Hooks as a way to extend and customize Claude Code. The feature has not shipped yet and already drew comments that it copies Com…
A builder behind OpenCode Go shares a candid take on the AI coding agent space: brutal competition, widespread fraud, and razor-thin odds of success.
Sam Altman expressed excitement that early customers are already using OpenAI's Astra on Microsoft Azure, signaling early traction for the AI offering.
Command Code announces its read tool can handle nearly any file format with high speed and token efficiency, claiming a Pareto-dominance position on the TEF Ben…
Ahmad Awais announces an updated read tool benchmark for CommandCode AI and explains how the rebuilt read_file was engineered for open models, claiming billions…
CommandCodeAI v1.47.0 now natively supports most file formats, with the maintainer saying it is faster and more token-efficient than custom skills. Update via `…