Daily, Tuesday 26 May 2026
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.
Top developments
- 1
Curriculum Learning for Safety Alignment
Direct Preference Optimization (DPO) is a widely used approach for safety alignment that aims to reduce harmful behaviors in large language models. However, prior work shows that it can be brittle and exhibits poor out-of-distribution (OOD) generalization. In this paper we…
- 2
AgentSecBench: Measuring Prompt Injection, Privacy Leakage, and Tool-Use Integrity in LLM Agents
LLM agents process trusted instructions, retrieved records, and tool observations through a common generative channel. This conflates data flow with authority: an untrusted string can affect a secret-bearing response or an action proposal even when no application policy…
- 3
Anthropic’s restricted Claude Mythos model may be coming to Claude Code
Anthropic appears to be preparing for the public rollout of the Mythos model, which was announced in April as a restricted model that poses major security risks to private and public software.
Further reading, by topic
Advisories in this window
- 63 npm advisories63 critical
This edition
12 developments and 63 advisories in the window. Selection and order are automatic: how stories are placed and ranked.