OpenAI News · September 22, 2026

Diagnose prompt-cache misses without widening an agent’s tool access

Why it matters

OpenAI’s prompt-caching guidance explains how to compare requests for changes that invalidate shared prefixes, place explicit breakpoints, and preserve tool definitions while changing which tools are callable. GPT-6 can also receive appended reasoning-effort updates without rewriting the earlier prefix. Workload savings still need measurement.

My takeaway: Keep stable instructions and tool schemas before changing context, and use cache-miss diagnostics to test edits. Restrict callable tools with allowed_tools rather than retaining unnecessary permissions for cache reuse. Measure cached tokens and latency, and check retention settings against your data-handling requirements.
Keep exploring

More curated notes connected through AI Engineering and Prompt Engineering.

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.

Microsoft Security Blog · guide

AI vulnerability research: measure reproducible findings and completed fixes

Microsoft’s FORGE account describes the work between a model’s vulnerability claim and a useful repair: reusable builds, duplicate removal, reachability checks, project-specific verification, reproducible triggers and regression tests. Structured rejection reasons help improve later searches. The useful operational measure is the flow of findings that survive verification and reach a fix, rather than the number of candidates generated. Reported successful-case costs exclude parts of screening, failed attempts and human work, so they are not the total cost of operating this pipeline.

OpenAI News · framework

Frontier training safety cases: connect evidence to enforced pause and rollback controls

OpenAI proposes training-run safety cases combining alignment evaluations, containment and monitoring with explicit operational ownership. Concrete measures include immutable transcripts, held-out incident tests, checks for evaluation gaming, response deadlines and fail-closed monitoring. Independent internal challenge, leadership vetoes and tracking downstream uses support stopping a run and reversing affected work. The article describes recommendations still being implemented, rather than audited proof that every safeguard already operates or that residual risk has been eliminated.