Enterprises are shifting agents from experiments to production, with attention on useful outcomes, security, and independent safety evaluation.
Anthropic is giving METR employee-like access to evaluate the safety of its systems and has started early discussions with other organizations, including Hugging Face. This shifts trust from vendor self-assessment to independent, distributed auditing...
Enterprise AI is moving from experiments to production. The key metric is no longer cost per token or GPU-hour, but effective cost per useful outcome. Three models compete: bespoke stacks, on-demand consumption, and integrated private platforms. The ...
OpenCode, an open source coding agent popular as an alternative to Claude Code and Cursor, suffered a breach of its online platform: attackers stole some users' API keys and used them to inflate AI account charges. AI tools asked to inspect the malic...
A study on wake simulations and damped oscillators shows that physics-labeled LLM prompts improve initial calibration in 23 of 25 trials, but the advantage fades after 15 evaluations. Hybridizing with a classical optimizer cuts runs to 9, versus 17 f...
Researchers propose Structured Authority Injection, a protocol that routes human corrections through typed, schema-validated MCP tool calls and maintains a ranked authority context prepended to each LLM prompt. It defines three override classes with ...
Google has open-sourced Harness2, a system that lets an AI agent refine its own harness for each task and retain lessons learned, without touching model weights. Tested with Gemini 3.5 Flash and GLM-5 on legal, office, and professional benchmarks, it...
PRISM recovers per-query signal from execution-verified graph corpora that lack rankings. A teacher reads a sibling graph via a zero-initialized low-rank branch; the student aligns per-decision targets on self-sampled trajectories. Across six benchma...
The FastAPI platform described by DeepUnfolding Agent separates adaptive control from domain-specific execution. Executors register a schema, send round-level diagnostics, receive schema-bounded actions, and return feedback. SQLite persistence and Do...
