QuEra Automates Quantum Laser Maintenance with Anthropic AI

Measure Before You Manage: Evaluating Agent Working Memory in Coding Agents

Agent working memory is heterogeneous. Objects such as instructions, artifacts, tool outputs, and agent-generated state play different semantic roles and exhibit different size, retention, and…

2026-08-31 ·arxiv.org

Fourteen Speaker Encoders Heard the Same Voice. Their Error Rates Differed Five-Fold.

A speaker encoder turns a few seconds of speech into a vector, and the distance between two vectors is treated as an answer to "are these the same person." That number gets used for authentication…

• Fourteen encoder models evaluated identical voice samples with varying error rates.
• Error rates ranged from 0.047 to 0.233, indicating a five-fold discrepancy.
• Emotional speech exacerbates error differences, with expressive speech showing higher error rates.

2026-08-31 ·dev.to

Wrong Prediction, Right Answer: Recovering Evidence from Collapsed LLM Sequence Scores

When a large language model fails a reasoning task, it is often assumed to lack the underlying capability. However, this conflates a genuine absence of reasoning with a late-stage output bottleneck.

2026-08-31 ·arxiv.org

Testing Google ADK TypeScript Agents Without Chasing Sentences

The fastest way to make an AI-agent test flaky is to assert the final sentence. You expect: I'll help you find hotels in Paris. The agent returns: Sure — I can look for hotel options in Paris.

2026-08-31 ·dev.to