PREVIEW. This is how it will look in an inbox; it was not sent to you. Each real email carries its own unsubscribe link and Keryn's postal address.

Keryn Headlines

Daily, Sunday 14 June 2026 · Retrospective · Covers 13 June 2026 00:00 to 14 June 2026 00:00 UTC

Read on the web

Top developments

Defending against Adaptive Prompt Injection Attacks via Reasoning-enabled Task Alignment

arXiv · Research · AI Security, Models

ClayBuddy: A Framework, Evaluation, & Mitigation of Coding Agent Failures

arXiv · Research · Agentic SDLC

AI-driven Software Development: A Pragmatic Path to Agentic Development Processes

arXiv · Research · Agentic SDLC

Models

US Gov asks Anthropic to ban 'foreign national' access to Fable, Mythos

BleepingComputer · Analysis · Models

AI Security

Securing Multi-Agent GIS Systems: Risk Evaluation and Prompt Hardening Optimization

arXiv · Research · AI Security

AutoDojo: A Generative Benchmark for Evaluating Prompt Injection Defenses in LLM Agents

arXiv · Research · AI Security

Advisories in this window

  • 1 Go advisory · 1 critical

All advisories

Titles, links and short excerpts only; every item links to its source. Selection is automatic; the editor's note is AI-drafted and checked as described. Preview: the unsubscribe link and Keryn's postal address are added to each email when it is sent.