▶ Videos →

📰 Dev.to · plasma

13 articles · Updated every 3 hours · View all reads

All Articles 181,975 Blog Posts 166,034 Tech Tutorials 48,750 Research Papers 35,704 News 22,619 ⚡ AI Lessons

I Was Measuring LLM Latency Wrong

Dev.to · plasma 🧠 Large Language Models ⚡ AI Lesson 1mo ago

I Was Measuring LLM Latency Wrong

For a long time, I recorded one latency number for every LLM request: latency_ms =...

The Bug Only Happened After I Switched LLM Providers

Dev.to · plasma 🧠 Large Language Models ⚡ AI Lesson 1mo ago

The Bug Only Happened After I Switched LLM Providers

The request succeeded. The response was valid JSON. The SDK did not throw an exception. And the...

The LLM Response Looked Fine. My Parser Disagreed.

Dev.to · plasma 🧠 Large Language Models ⚡ AI Lesson 2mo ago

The LLM Response Looked Fine. My Parser Disagreed.

The response looked perfectly reasonable in the logs. It had the fields I asked for. The values made...

My LLM Provider Returned 200. The Workflow Still Failed.

Dev.to · plasma 🧠 Large Language Models ⚡ AI Lesson 2mo ago

My LLM Provider Returned 200. The Workflow Still Failed.

The request looked completely normal. The server returned 200 OK. The response body was valid JSON....

I Stopped Swapping LLM Providers Without a Smoke Test

Dev.to · plasma 🧠 Large Language Models ⚡ AI Lesson 2mo ago

I Stopped Swapping LLM Providers Without a Smoke Test

For a while, my LLM provider migration test was embarrassingly simple: Change the base URL Send one...

A Small Node.js Wrapper for LLM API Retries, Timeouts, and Logging

Dev.to · plasma 🧠 Large Language Models ⚡ AI Lesson 2mo ago

A Small Node.js Wrapper for LLM API Retries, Timeouts, and Logging

Most LLM API integrations start with a direct SDK call. That is fine for a demo. But once the call...

The LLM API Failure Policy I Wish I Had Before My First Production Incident

Dev.to · plasma 🧠 Large Language Models ⚡ AI Lesson 2mo ago

The LLM API Failure Policy I Wish I Had Before My First Production Incident

Most LLM API error handling starts out looking like normal HTTP error handling. If it is a 429,...

The Retry Setup I Use for LLM APIs Without Accidentally Duplicating User Actions

Dev.to · plasma 🧠 Large Language Models ⚡ AI Lesson 2mo ago

The Retry Setup I Use for LLM APIs Without Accidentally Duplicating User Actions

Retries look simple until an LLM call is allowed to do something. For a normal read-only API...

Stop Treating LLM API Errors Like Normal HTTP Errors

Dev.to · plasma 🧠 Large Language Models ⚡ AI Lesson 2mo ago

Stop Treating LLM API Errors Like Normal HTTP Errors

Most backend engineers already know how to handle HTTP errors. 400 means the request is bad. 401...

LLM API debugging checklist

Dev.to · plasma 🧠 Large Language Models ⚡ AI Lesson 2mo ago

LLM API debugging checklist

When an LLM feature breaks in production, my first instinct used to be: "the model got worse." That...

My LLM API Calls Were Failing Silently. Here's the Logging Setup I Wish I Had Earlier

Dev.to · plasma 🧠 Large Language Models ⚡ AI Lesson 2mo ago

My LLM API Calls Were Failing Silently. Here's the Logging Setup I Wish I Had Earlier

The first few LLM API bugs I hit in production were easy to notice. The request failed. The user saw...

GLM 5.2 Is Now Available on TokenBay: Testing It with the OpenAI SDK

Dev.to · plasma 🧠 Large Language Models ⚡ AI Lesson 2mo ago

GLM 5.2 Is Now Available on TokenBay: Testing It with the OpenAI SDK

GLM 5.2 is now available on TokenBay. If you're already using the OpenAI SDK, this means you can try...

One API Key for GPT, Claude, Gemini, and Qwen: A Practical Guide to OpenAI-Compatible Model Routing

Dev.to · plasma 🧠 Large Language Models ⚡ AI Lesson 2mo ago

One API Key for GPT, Claude, Gemini, and Qwen: A Practical Guide to OpenAI-Compatible Model Routing

If you've built anything serious with LLM APIs, you've probably hit this pattern: GPT is great for...