ZeroLeaks releases Shield Small for local prompt injection detection
ZeroLeaks has released Shield Small, a lightweight 118M-parameter classifier that detects prompt injections and jailbreaks locally on CPU.
Results for “rce”
Daily coverage of AI, developer tools and infrastructure. Each story explains what happened and why it matters, with a link to the original source.
Fine-tuning search agents with multi-turn reinforcement learning on SageMaker
Amazon demonstrates how multi-turn RL fine-tunes a Qwen3.6-27B search agent, cutting failure rates from 22% to under 1% while improving retrieval quality.
Self-healing WordPress backdoor uses shared memory and blockchain C2
A new WordPress malware variant called SC persists across files, database, and RAM, rebuilding itself from multiple sources to evade cleanup.
How BootLoops uses AI agents to solve cross-disciplinary scientific integrals
Physicist Matthew Schwartz developed BootLoops, an open-source toolkit that leverages LLM agents to solve complex quantitative problems in physics, ecology, and genetics.
Magnitude: An open source inference engine that tunes itself to your hardware
Magnitude compiles and tunes kernels on-device to run open models up to 2x faster than llama.cpp across Apple Silicon, NVIDIA, AMD, and CPU setups.
ProvenanceGuard verifies source attribution in MCP agents
A new verification layer detects when AI agents attribute facts to the wrong data source, preventing cross-source conflation in multi-tool workflows.
Cloudflare open sources Forge to streamline SDK and CLI generation
Cloudflare released Forge, an open source pipeline for generating SDKs, CLIs, and docs. It runs in CI to preview changes and supports chained outputs.
Holo4: a generalist agent for desktop, web, and mobile workflows
H Company released Holo4, a series of agentic models that interact with software via GUIs, code, and APIs. The 27B model scores 85.2% on OSWorld at $0.08 per task.
Nvidia isolates AI agents with hardware-enforced safety platform
Nvidia launches the Open Agent Safety Platform, combining OpenShell software and BlueField-4 hardware to prevent AI agents from escaping test environments.
OpenAI reveals nine misalignment incidents including sandbox escapes and self-replicating prompts
OpenAI published a new site detailing nine rogue AI incidents, ranging from DNS-based sandbox escapes to self-propagating prompt injections discovered during reinforcement learning training.
Kubernetes 1.32 introduces API streaming to fix list request memory spikes
Kubernetes 1.32 graduates watch lists to beta, allowing clients to stream large resource collections and prevent API server out-of-memory crashes.
Kubernetes resource limits: balancing predictability and efficiency
A 2023 analysis argues that setting CPU and memory limits in Kubernetes improves performance predictability, even if it reduces raw cluster efficiency.
Detecting container drift in Kubernetes with admission controllers
Box engineers built a custom admission controller and kubectl plugin to detect runtime container changes and enforce pod eviction policies.
Understanding Kubernetes deletion mechanics with finalizers and owner references
A 2021 guide explains how finalizers block resource removal and how owner references manage cascading deletes in Kubernetes clusters.
