Here's your daily roundup of the most relevant AI and ML news for September 03, 2026. Today's digest includes 2 security-focused stories. We're also covering 3 research developments. Click through to read the full articles from our curated sources.
Security & Safety
1. Malicious .git Configs Can Make Claude, Codex, Cursor, and Other AI Agents Run Attacker Code
Manifold Security has disclosed eight security flaws across seven command-line AI coding agents in which a repository's own Git configuration names a command that the agent runs on the developer's machine, four of them still unpatched at publication.
The command executes as the user, outside the...
Source: The Hacker News (Security) | 23 hours ago
2. Researchers Use Claude to Port Pre-Auth RCE Exploit From One PLC Model to Another
Forescout Research - Vedere Labs said it used Anthropic's Claude to port a working pre-authentication remote code execution (RCE) exploit from one WAGO programmable logic controller (PLC) to another, executing attacker-supplied ARM shellcode on live hardware.
The exploit targets CVE-2021-31...
Source: The Hacker News (Security) | 1 day ago
HuggingFace & Models
3. Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps
Source: HuggingFace Blog | 14 hours ago
4. BenchMIRT: What are LLM benchmarks actually measuring?
Source: HuggingFace Blog | 1 day ago
Research & Papers
5. Breadth Beats Depth: Improving GCG-Based Jailbreak Optimization with Breadth-Oriented Suffix Search
arXiv:2609.02172v1 Announce Type: cross Abstract: Optimization-based jailbreak attacks such as Greedy Coordinate Gradient (GCG) achieve strong effectiveness and transferability by optimizing adversarial suffixes on white-box source models. However, existing GCG-based methods rely on averaged adv...
Source: arXiv - Machine Learning | 10 hours ago
6. The Implications of Linguistic Illegibility for LLM Security
arXiv:2609.02852v1 Announce Type: new Abstract: LLMs are trained to generate natural language. However, various strands of evidence indicate that an LLM's externalized linguistic outputs and mechanistically-extracted linguistic features can be an unreliable lens for understanding internal model ...
Source: arXiv - Machine Learning | 10 hours ago
7. The Illusion of Replacement: Rethinking Specialized Machine Learning Models in the Foundation Model Era
arXiv:2608.28980v2 Announce Type: replace-cross Abstract: Can the specialized architectures that machine learning has traditionally built for structured data be replaced by language-based models? This question is examined through a review of 159 papers (2016--2026) across nine modalities, with p...
Source: arXiv - Machine Learning | 10 hours ago
Tech & Development
8. Show HN: Pangolin – SSO and WireGuard instead of API keys for LLM access
You have seen Pangolin (https://github.com/fosrl/pangolin) on here before for our open-source zero-trust network access suite of tools. We are launching a new AI gateway that takes a different approach to auth. Rather than authenticating requests to AI providers with API keys, it authenticates th...
Source: Hacker News - AI | just now
About This Digest
This digest is automatically curated from leading AI and tech news sources, filtered for relevance to AI security and the ML ecosystem. Stories are scored and ranked based on their relevance to model security, supply chain safety, and the broader AI landscape.
Want to see how your favorite models score on security? Check our model dashboard for trust scores on the top 500 HuggingFace models.