Fetching from the wire…
01
02
03
04
05
06
07
08
Research2026-08-28 · source-backed
Services generated from BaxBench scenarios in JavaScript, Python and Rust were validated with BaxBench-derived tests, then run under 48-hour workloads with Mann-Kendall trend analysis (arXiv 2608.26391). Memory usage shows significant upward trends in most application-language combinations, while response time and throughput behave inconsistently. Human-written implementations aged too, so this isn't an AI-specific defect. It's a reminder that passing functional tests says nothing about surviving continuous operation, and that agent-generated services need soak testing that agent-generated test suites won't provide.
Each link below shares sources, entities, or timing with this story.
Simon Willison released LLM / Shared entities / Earlier coverage
Linked by a graph relationship (Simon Willison released LLM); both cover JavaScript, Python, Rust; earlier JavaScript coverage from 2026-03-27.
Simon Willison released LLM / Shared entities / Earlier coverage / Tension
Linked by a graph relationship (Simon Willison released LLM); both cover JavaScript, Python; earlier JavaScript coverage from 2026-03-28.
Simon Willison released LLM / Shared entities / Earlier coverage
Linked by a graph relationship (Simon Willison released LLM); both cover LLM, Python; earlier LLM coverage from 2026-08-27.
Linked by a graph relationship (Simon Willison released LLM); both cover JavaScript, Python; earlier JavaScript coverage from 2026-08-20.
Linked by a graph relationship (Simon Willison released LLM); both cover LLM, Python; earlier LLM coverage from 2026-06-22.
Linked by a graph relationship (Simon Willison released LLM); both cover Python, Rust; earlier Python coverage from 2026-05-15.
Linked by a graph relationship (Simon Willison released LLM); both cover JavaScript, Python; earlier JavaScript coverage from 2026-03-25.
Zerostack uses Rust / Shared entities / Earlier coverage
Linked by a graph relationship (Zerostack uses Rust); both cover JavaScript, Rust; earlier JavaScript coverage from 2026-05-17.