GoodBarber engineering lead J. explains that agent memory is a liability and recommends tracking state rather than history, citing a Google and Purdue preprint (SKILL.state) that reports up to 94 perc…
A new arXiv preprint (2608.14639v1) reports that per-field selective risk control for document extraction silently fails on real documents, diagnosing three failure modes across 13,859 genuine claude-…
Agentgateway and vLLM Semantic Router (vSR) integrate via external processing (ExtProc) to enable semantic routing of prompts to the most cost-effective LLM model, reducing workload costs by approxima…
A new permutation diagnostic reveals that position bias in multiple-choice LLM benchmarks is only detectable within a 60-95% base-accuracy Goldilocks zone, with frontier-tier models operating above th…
A developer built The AI Crash Test, a browser-based tool for adversarial LLM testing that uses deterministic predicate grading instead of an LLM judge. The tool allows users to audit results via the …