arXiv:2608.06477v1 Announce Type: cross Abstract: Computer-use agents (CUAs) face a growing threat from indirect prompt injection, where adversarial…
Author: script
Specification Engineering: The New Skill After Prompt Engineering
Prompt engineering taught us how to ask better questions. Specification engineering teaches us how to define better work.
Agentic AI: User Empowerment or Enclosure?
arXiv:2608.06510v1 Announce Type: cross Abstract: Agentic AI promises a more flexible form of digital agency: systems that can act on users’ behalf, from…
AI News Brief Hourly Summary 2026-08-10 16h : 14 posts
14 posts were published in the last hour 13:33 : Risk-Aware Decision Policies for Agents Under Noisy Perception 13:33 : Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models 13:33 : Model ML completes finance work more efficiently with…
Risk-Aware Decision Policies for Agents Under Noisy Perception
arXiv:2608.06420v1 Announce Type: cross Abstract: Perception in biological systems is inherently noisy, requiring organisms to make decisions under…
Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models
arXiv:2608.06409v1 Announce Type: cross Abstract: Speech language models are increasingly evaluated on paralinguistic tasks by the accuracy of prompted…
Model ML completes finance work more efficiently with GPT-5.6 Sol
Model ML uses GPT-5.6 Sol to carry finance work from research and analysis through editable, traceable PowerPoint decks and Excel workbooks.
ED-CSP: Crystal Structure Prediction from Electron Diffraction
arXiv:2608.06448v1 Announce Type: cross Abstract: Recovering a periodic 3D crystal structure from sparse, unindexed electron diffraction (ED) observations…
Told to book a gym class, an AI agent hacked the site instead to move its user up the waitlist
An Australian user just wanted a spot in a class. His AI agent found a security hole instead and exploited it. The article Told to book a gym class, an AI…
WorldMark: A Plug-and-Play World Knowledge Interface for Cross-Host Language Model Watermarking
arXiv:2608.06416v1 Announce Type: cross Abstract: Watermarking traces the provenance of text produced by large language models by embedding statistically…