Category Archive

AI & Automation

Agents, LLMs, on-device inference, tooling pipelines.

Two million canary prompts found three providers keeping what they said they deleted

Dragos planted fake credentials in two million AI prompts and watched where they surfaced: three provider breaches, resellers reading logs for free, and retenti…

Windows 11 Keeps a Bit for Every Coding Agent You Run

A Windows 11 component classifies the developer tools and coding agents you run, stores the bitmap locally, and uploads it through optional diagnostics that shi…

Capture CI Failure Evidence Before You Classify It

Deterministic evidence collection at failure time reclassifies most mystery CI failures without a model, leaving only judgment calls to the classifier.

Automated SAST with OpenAI Codex Security: Deterministic AST Analysis Meets LLM Remediation

Static analysis flags security bugs, but traditional SAST tools drown developers in false positives. OpenAI Codex Security combines AST parsing with automated c…

Silicon Trust Chains in Multi-Tenant GPU Clusters

Analyzing silicon trust chains, firmware attestation, and hardware security isolation in high-density AI data centers.

The Myth of Opaque AI Reasoning Tokens

Encrypted reasoning traces from proprietary AI APIs are not bound to individual sessions or users. Discover how cross-model trace replay exposes credentials, PI…

LightCraft: Rebuilding the RAW Photo Pipeline in Pure Rust

Raw photo development remains tied to bloated subscription software and legacy C libraries. LightCraft rebuilds the non-destructive image pipeline in pure Rust …

Liability Boundaries for Autonomous Agent Payments

Delegating execution authority to autonomous software without cryptographic parameter envelopes forces infrastructure operators to assume unlimited financial co…

Myth: SSH Agent Forwarding Is a Safe Bastion Pattern

Passing your local SSH keys through jump hosts with agent forwarding exposes your private identity to any compromised bastion. Here is the mechanical reality an…

AI Models Escaping Evaluation: Treating the Internet as a Security Boundary

Why researchers are calling for default-deny egress on AI eval environments—and how to implement it with iptables.

Press ⌘K to search & switch themes