Skip to content

The Edge of the Cyber World See the latest

ai

AI

OpenAI discloses six new cases of ‘concerning’ AI model behavior outside Hugging Face incident

OpenAI has disclosed six new cases of unexpected or “concerning” behavior from its AI models, including instances in which models tried to hide mistakes, used an exposed API key without permission, uploaded files to the public internet, and found unauthorized […] The post OpenAI discloses six new cases of ‘concerning’ AI model behavior outside Hugging…

Read summary

Technology

BIND 9 Update Fixes 14 Flaws, Including an Unauthenticated Crash Over DNS-over-HTTPS

The Internet Systems Consortium (ISC) has released BIND 9.20.29 and 9.21.26 to fix fourteen security flaws it disclosed on 16 September in BIND 9, its open-source DNS server software. One of them affects any BIND server that answers DNS-over-HTTPS (DoH). A sender with no credentials can crash the server process, named, with a single request that carries an invalid SIG

Read summary

AI

How Value Induction Reshapes LLM Behaviour

Conversational Large Language Models are post-trained on language that expresses specific behavioural traits, such as curiosity, open-mindedness, and empathy, and values, such as helpfulness, harmlessness, and honesty. This is done to increase utility, ensure safety, and improve the experience of the people interacting with the model. However, values are complex and inter-related – inducing one…

Read summary

Apps

Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation

Discrete flow matching generates text by iteratively transforming noise tokens into coherent language, but may require hundreds of forward passes. Distillation uses the multi-step trajectory to train a student to reproduce the process in a few steps. When the student underperforms, the usual explanation is insufficient capacity. We argue the opposite: the trajectory is the…

Read summary