14 articles

📰 Dev.to · Wu Long

Articles from Dev.to · Wu Long · 14 articles · Updated every 3 hours · View all reads

All ⚡ AI Lessons (8976) ArXiv cs.AIDev.to · FORUM WEBForbes InnovationOpenAI NewsDev.to AIHugging Face Blog
The 429 That Poisoned Every Fallback
Dev.to · Wu Long 4d ago
The 429 That Poisoned Every Fallback
Your agent has a fallback chain: GPT-5.4 → DeepSeek → Gemini Flash. GPT-5.4 hits a 429 rate limit. No...
The One Parameter That Broke Every GPT-5 Call
Dev.to · Wu Long 4d ago
The One Parameter That Broke Every GPT-5 Call
You upgrade your model to GPT-5.2. Every single request returns a 400 error. Your agent retries, hits...
The Silent Freeze: When Your Model Runs Out of Credits Mid-Conversation
Dev.to · Wu Long 5d ago
The Silent Freeze: When Your Model Runs Out of Credits Mid-Conversation
You're chatting with your agent. It's been helpful all day. You send another message and... nothing....
Invisible Characters, Visible Damage
Dev.to · Wu Long 6d ago
Invisible Characters, Visible Damage
There's a special kind of bug that only exists because two pieces of code disagree about what a...
The Image Your Agent Made But Nobody Saw
Dev.to · Wu Long 6d ago
The Image Your Agent Made But Nobody Saw
Your agent generates a beautiful image. The tool returns success. The model writes a cheerful "Here's...
Your Agent Lied About Running the Code
Dev.to · Wu Long 1w ago
Your Agent Lied About Running the Code
A user ran a simple prompt: write a Python script that reads a CSV and outputs basic statistics. The...
When /pair approve Bypasses the Scope Guard
Dev.to · Wu Long 2w ago
When /pair approve Bypasses the Scope Guard
There's a particular class of security bug that I find endlessly fascinating: the one where two paths...
When setTimeout Overflows and Your Agent Melts
Dev.to · Wu Long 2w ago
When setTimeout Overflows and Your Agent Melts
A token expiry heuristic misidentifies seconds as milliseconds, producing a 360 billion ms...
When a Regex Eats Your Entire Process
Dev.to · Wu Long 2w ago
When a Regex Eats Your Entire Process
You upgrade your AI agent framework. You run gateway start. Seven seconds later, it's dead. No error...
When Your LLM Proxy Becomes the Attack Vector
Dev.to · Wu Long 2w ago
When Your LLM Proxy Becomes the Attack Vector
Yesterday, LiteLLM — the Python library that ~95 million monthly downloads use to route LLM API calls...