AI Engineer · October 11, 2026

Evaluate whether coding agents use—and benefit from—a code context graph

video AI Engineering Model Evaluation Agent Security

Evaluate whether coding agents use—and benefit from—a code context graph video thumbnail

Why it matters

This workshop builds a code graph over selected Rust crates using syntax extraction, symbol resolution, and Neo4j, then compares graph-assisted agents with text search. Its public repository includes a cached evaluation and source fixtures. The useful distinction is between one correct answer, consistent answers across runs, and actual adoption of the graph tools. Results from this small corpus do not establish a general advantage for graph-based retrieval.

My takeaway: Inspect the cached evaluation first, then add questions from your own repository. Measure tool use, repeated-run correctness, token cost, and indexing freshness. Keep deterministic symbol relationships separate from model-generated interpretations.

Keep exploring

More curated notes connected through AI Engineering and Model Evaluation.

OpenAI News · framework

Pacing model development in an era of cyber-critical capabilities

OpenAI says preliminary evidence that Astra may meet its Critical cybersecurity threshold led it to pause frontier reinforcement-learning work for two weeks and keep its largest planned run on hold. New safeguards include stronger workload and network isolation, continuous boundary testing, token-level monitoring that escalates suspicious tool activity, and broader alignment checks for deception, reward hacking, and unauthorized access.

OWASP GenAI Security Project · guide

OWASP Top 10 for Agentic Applications for 2026

OWASP's community guide organizes agentic-system risk into ten categories, including goal hijacking, tool misuse, identity and privilege abuse, memory poisoning, insecure inter-agent communication, cascading failures, and rogue-agent behavior. It provides a shared taxonomy and mitigation starting point rather than a certification checklist or evidence that a deployed system is secure.

OpenAI News · framework

A blueprint for democratic governance of frontier AI

OpenAI proposes a three-part U.S. frontier-AI governance model: harmonize emerging state safety laws into a federal baseline, strengthen CAISI as an evaluation and standards institution, and coordinate a broader resilience program. Proposed controls include severe-risk evaluations, transparency reports, independent audits, safety-incident reporting, model-weight security, whistleblower protection, and periodic technical assessments.