Rohit Edathil writes about Dagic, a minimal workflow Directed Acyclic Graph (DAG) definition language and asynchronous execution engine implemented in Python designed for LLM agents. It provides a middle ground between standard tool calling and full code execution by allowing models to describe workflows through assignments and function calls that are parsed, type-checked, and executed concurrently without the security risks of arbitrary code execution.
- Performs ~7x more efficiently than per-call tools in math benchmarks regarding token usage
- Executes independent branches of a workflow concurrently using Python's asyncio
- Provides static type checking for tool arguments to prevent mid-run failures
- Avoids the need for sandboxing arbitrary model-generated code by restricting execution to host-registered functions
Report on the winners of the 'My First Endgame Study' composing tourney, a collaboration between the World Federation for Chess Composition (WFCC) and ChessBase India. Includes details on the judging criteria and showcases several winning studies.
Study 07 (7th Place): White wins through a rook and bishop chase, forcing the black king into a position where it can no longer escape. The solution involves 1. Rf8+ Kxh3 2. Bf1+ Kh4 3. Bf2+ Kh6 4. Be3+ g5 5. Kf6 Qc7 6. Bxg5#
Study 03 (3rd Place): White wins with an attractive and active game. Key moves include 1.Nb6+!, 4.Kb1!, 6...Kb3!, and 7.a4!! which sets up a mating net. The solution finishes with 10.Kc2 fxe4 11.fxe4 h1Q 12.b3#. The article highlights the surprising nature of moves like 1.Nb6+! and 7.a4!!.