← All topics

Tag

JSON

Every JSON story we've curated in Bowl of Data, newest issue first — part of our weekly digest across AI, security, blockchain, and engineering.

3 items · 3 issues

Week 33 · 2026

Read the issue →
  • QuoteBench: How Matched Scores Can Hide Command-Path Failures

    QuoteBench is a new benchmarking framework that exposes how the execution environment of LLM agents can corrupt Bash commands through parsing errors. It demonstrates that high 'matched' success scores often hide significant failures occurring at the boundary between model output and shell execution.

    AI & ML arXiv Source ↗

Week 32 · 2026

Read the issue →
  • The Bitter Lesson of Tool Calling

    This research evaluates whether replacing structured JSON tool calls with executable Python scripts improves LLM agent performance. The findings suggest that programmatic tool calling is a more robust and scalable alternative, particularly for complex, multi-step, and high-parallelism tasks.

    AI & ML arXiv Source ↗

Week 19 · 2026

Read the issue →