AI coding guides & resources
Engineering decisions, tutorials, and video guides from the OTF team.
The Hidden Dangers of Sharing Code with AI Assistants
A cautionary tale of how sharing proprietary code with AI assistants can lead to unintended data leaks and security breaches.
9 min read
Stay Ahead in AI: Cursor Acquisition, New Models, and Frontier Updates
AI deal reports point one way: the model is becoming the stack. What the reported moves mean for builders, with sourcing caveats.
7 min read
Why fast small models matter more than flagships for coding agent loops
Why fast lightweight models beat flagships inside coding agent loops, and how to split planning from execution.
7 min read
Secure Your CI/CD Pipeline: Prevent AI Agent Credential Leaks
Discover how pre-receive hooks can safeguard your systems from AI coding agents inadvertently exposing live credentials in git history.
7 min read
DeepSeek's Bold Shift: Quadrupling Prices While Launching Claude Rival
DeepSeek shocks from low-cost leader to premium AI provider with a 4x price hike and new Claude competitor
8 min read
Securing CI/CD: Preventing AI Agent Credential Leaks in Code Commits
AI coding agents leak credentials into git history at a higher rate than humans. Server-side pre-receive hooks reject bad pushes before they land.
7 min read
Why 75% of developers prefer Claude Code over Codex
Retrofit: 75% survey win is a workflow-fit question, with verified ZDNet citations
8 min read
Mindgard Secures $30M to Reinforce AI Security After Uncovering Critical Vulnerabilities
Mindgard's $30M Series A funding comes after discovering over 150 AI vulnerabilities, including zero-days in Cursor and ChatGPT.
8 min read
Anthropic's Claude Agents Learned to Cooperate with Mythos 5
How Anthropic's Mythos 5 model achieved peace between competing AI agents after experiments led to malware attacks.
7 min read
Grok Bot: how persistent cross-app agents change delegated work
Grok Bot gives agents their own cloud computer and lets them work across apps. Here is how to use the beta without skipping approvals.
8 min read
Anthropic launches self-hosted Claude Code beta for enhanced control
Retrofit: self-hosted Claude Code beta with verified data-split citations and sources
8 min read
change software development with AI-powered cloud agents
Retrofit: workspace-attached sandboxes end the split-brain workflow, scoped to verified claims
8 min read
Lovable achieves AI agent certification with Lloyd's insurance backing
Lovable is the first coding-agent platform certified under AIUC-1, pairing the standard with a Lloyd's insurance policy.
7 min read
AI lets non-programmers ship software with ease
A large share of people shipping AI-built software have no formal coding background — how they do it and what lasts.
8 min read
Slash AI costs: cut token usage by 45% with this simple Claude Code tweak
One Claude Code effort-setting change cut token burn 45% in one author's test.
7 min read
California's AI Transparency Act: what AI builders need to know now
California's SB 942 obliges covered AI providers to embed provenance, ship a free detection tool, and offer labels.
7 min read
Claude AI enables smooth multi-session coding collaboration on macOS
Claude Code v2.1.224 lets sessions share findings on macOS with auditable handoffs.
8 min read
AI Coding Assistants Face Critical Security Risks: RCE and Supply Chain Attacks
A reported vuln class in Claude Code, Gemini CLI, and Codex targets the agent harness — the trust-boundary bug and how to harden it.
8 min read
change Software Delivery with AI Agents and Automated Pipelines
Claude Code writes the fix; Harness decides if it ships — security agents, canary rollback, and AI browser verification in one loop.
6 min read
Critical one-click RCE flaw exposes VS Code and Cursor users to remote code execution
AISLE reported a commit-link RCE in Cursor, VS Code and Antigravity; current versions are fixed. What to check.
6 min read
Sumo Logic boosts security with new AI tools
Sumo Logic's SOC Analyst Agent feeds models normalized telemetry, not raw logs. Powell reports 64% faster response. The architecture lesson travels.
8 min read
AI models face growing threat: hackers exploit Claude, Codex, and more for malware
Guardrails fall to basic social engineering. Treat prompts, API keys, and model output as attack surface when shipping AI features.
8 min read
Lovable Accelerates AI Development with Cerebras Partnership
Lovable's Cerebras partnership bets on inference latency, not model smarts — faster round-trips to keep builders in flow.
7 min read
Microsoft Agent Framework advances to production-ready runtime
Microsoft's Agent Framework productizes the agent harness layer. What it ships and how to adopt it.
6 min read
