Saturday, 4 October 2025

Keryn Headlines

Daily Retrospective

Covers 3 October 2025 00:00 to 4 October 2025 00:00 UTC

Daily, Saturday 4 October 2025

Reconstructed on 19 November 2026 from archived source metadata.

From the editor

The editor's note for this issue is not available. The developments below were selected and ranked automatically from the sources listed.

1 Certifiable Safe RLHF: Semantic Grounding and Fixed Penalty Constraint Optimization for Safer LLM AlignmentarXiv

Top developments

  1. 1

    Certifiable Safe RLHF: Semantic Grounding and Fixed Penalty Constraint Optimization for Safer LLM Alignment

    Ensuring safety is a foundational requirement for large language models (LLMs). Achieving an appropriate balance between enhancing the utility of model outputs and mitigating their potential for harm is a complex and persistent challenge. Contemporary approaches frequently…

    arXiv · Research · 3 October 2025 · Models

  2. 2

    AgentHub: A Registry for Discoverable, Verifiable, and Reproducible AI Agents

    LLM-based agents are rapidly proliferating, yet the infrastructure for discovering, evaluating, and governing them remains fragmented compared to mature ecosystems like software package registries (e.g., npm) and model hubs (e.g., Hugging Face). Existing efforts typically…

    arXiv · Research · 3 October 2025 · Trust

  3. 3

    LLM Agents for Automated Dependency Upgrades

    As a codebase expands over time, its library dependencies can become outdated and require updates to maintain innovation and security. However, updating a library can introduce breaking changes in the code, necessitating significant developer time for maintenance. To address…

    arXiv · Research · 3 October 2025 · Agentic SDLC

Further reading, by topic

SCA

  1. 4

DAST

  1. 5

AI-BOM

  1. 6

Models

  1. 7
  2. 8

    NonTextual Target Attack

    arXiv · Research · 3 October 2025

  3. 9

AI Security

  1. 10
  2. 11

    Sora 2 prompt injection

    Simon Willison · Analysis · 3 October 2025

Advisories in this window

  • 8 npm advisories4 critical · 1 high · 2 moderate · 1 low
  • 1 crates.io advisory1 low
  • 1 PyPI advisory1 moderate
  • 1 Packagist advisory1 high

All advisories

This edition

18 developments and 11 advisories in the window. Selection and order are automatic: how stories are placed and ranked.

Follow Keryn Headlines

Security news for teams building with AI. Choose an edition:

  • Daily: Every morning, 06:00 UTC. A short operational briefing: the few developments that matter, who is affected and what to watch. RSS feed
  • Weekly: Tuesdays, about 07:00 US Eastern. The week in order of importance. An editor’s essay accompanies the edition when it passes editorial checks. RSS feed
  • Monthly: The first Tuesday of the month, about 07:00 US Eastern. The month in review. A long read accompanies the edition when it passes editorial checks. RSS feed

Email is not open yet

Use RSS now: it works in any feed reader and needs no sign-up. Add the feed for the edition you want.

Daily feedWeekly feedMonthly feed All editions

When email opens, this box will let you choose editions and confirm by email. Nothing is collected before then.