DEV Community

# llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
When the Fallback Model Killed the Personality — A DeepSeek Personality Drift Incident

When the Fallback Model Killed the Personality — A DeepSeek Personality Drift Incident

Comments
3 min read
The Developer's Guide to Running LLMs Locally: Ollama, Gemma 4, and Why Your Side Projects Don't Need an API Key

The Developer's Guide to Running LLMs Locally: Ollama, Gemma 4, and Why Your Side Projects Don't Need an API Key

8
Comments 5
4 min read
Why MCP tool calling doesn't work well for AI agents — and what Cloudflare, Anthropic, and Pydantic are doing instead

Why MCP tool calling doesn't work well for AI agents — and what Cloudflare, Anthropic, and Pydantic are doing instead

1
Comments
3 min read
How to Set Up Weighted Load Balancing Across LLM Providers

How to Set Up Weighted Load Balancing Across LLM Providers

6
Comments 1
6 min read
GPT-5.1 Was Retired on March 11 — Here's What Broke in Your LLM App

GPT-5.1 Was Retired on March 11 — Here's What Broke in Your LLM App

1
Comments
4 min read
Spec-Driven Development Based on DSPI: Design-Specify-Plan-Implement

Spec-Driven Development Based on DSPI: Design-Specify-Plan-Implement

1
Comments 1
9 min read
How LLMs Are Transforming Code Review in 2026

How LLMs Are Transforming Code Review in 2026

Comments
2 min read
Claude Status: Why Your Claude API Keeps Returning 529 `overloaded_error` — A Production Debugging Playbook

Claude Status: Why Your Claude API Keeps Returning 529 `overloaded_error` — A Production Debugging Playbook

2
Comments
4 min read
Modernizing Legacy Code with Konveyor AI: From EJB to Kubernetes

Modernizing Legacy Code with Konveyor AI: From EJB to Kubernetes

Comments
3 min read
Agent-first CLIs are about reducing turns, not JSON

Agent-first CLIs are about reducing turns, not JSON

Comments
4 min read
Should You Be Using RAG in 2026?

Should You Be Using RAG in 2026?

3
Comments
12 min read
How Much VRAM Do You Actually Need to Run LLMs Locally?

How Much VRAM Do You Actually Need to Run LLMs Locally?

Comments
3 min read
Running Gemma 4 Locally on an iPhone 13 Pro with Swift

Running Gemma 4 Locally on an iPhone 13 Pro with Swift

1
Comments 1
2 min read
CodeSpeak: When English Isn't Precise Enough for AI

CodeSpeak: When English Isn't Precise Enough for AI

1
Comments
5 min read
I Tested 50 AI App Prompts for Injection Attacks. 90% Scored CRITICAL.

I Tested 50 AI App Prompts for Injection Attacks. 90% Scored CRITICAL.

2
Comments
6 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.