DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Open Source Project of the Day (Part 27): Awesome AI Coding - A One-Stop AI Programming Resource Navigator

Open Source Project of the Day (Part 27): Awesome AI Coding - A One-Stop AI Programming Resource Navigator

Comments
8 min read
When the Scraper Breaks Itself: Building a Self-Healing CSS Selector Repair System

When the Scraper Breaks Itself: Building a Self-Healing CSS Selector Repair System

Comments
8 min read
The Missing Link Between AI Agents and the Code They Modify

The Missing Link Between AI Agents and the Code They Modify

27
Comments 11
10 min read
Next-Gen LLMs: Deep Dive into Compact, High-Speed Models and Temporal Reasoning – Gemini 3.1 Flash-Lite, GPT-5.4 mini/nano

Next-Gen LLMs: Deep Dive into Compact, High-Speed Models and Temporal Reasoning – Gemini 3.1 Flash-Lite, GPT-5.4 mini/nano

Comments
7 min read
The hidden cost of GPT-4o: what every SaaS founder should know about per-user LLM spend it

The hidden cost of GPT-4o: what every SaaS founder should know about per-user LLM spend it

Comments 1
4 min read
What Happens When Your Request Enters the Inference Queue

What Happens When Your Request Enters the Inference Queue

1
Comments
3 min read
87.4% of My Agent's Decisions Run on a 0.8B Model

87.4% of My Agent's Decisions Run on a 0.8B Model

1
Comments 3
4 min read
Recognition Is All You Need: Human–AI Dynamics as Cognitive Amplification with Enforced Participation

Recognition Is All You Need: Human–AI Dynamics as Cognitive Amplification with Enforced Participation

1
Comments
6 min read
How I built an AI that reads bank contracts the way bankers do (not the way customers do)

How I built an AI that reads bank contracts the way bankers do (not the way customers do)

Comments
3 min read
Making AI "Boring": An Engineering Audit of RamaLama on Fedora Linux

Making AI "Boring": An Engineering Audit of RamaLama on Fedora Linux

Comments
3 min read
AI Agent Safety and Operations: Frontline Measures Against Prompt Injection and Monitoring

AI Agent Safety and Operations: Frontline Measures Against Prompt Injection and Monitoring

Comments
6 min read
How to Connect Non-Anthropic Models to Claude Code with Bifrost AI Gateway

How to Connect Non-Anthropic Models to Claude Code with Bifrost AI Gateway

6
Comments 2
5 min read
Escaping API Quotas: How I Built a Local 14B Multi-Agent Squad for 16GB VRAM (Qwen3.5 & DeepSeek-R1)

Escaping API Quotas: How I Built a Local 14B Multi-Agent Squad for 16GB VRAM (Qwen3.5 & DeepSeek-R1)

1
Comments 1
3 min read
How Poor Tool Calling Behavior Increases LLM Cost and Latency

How Poor Tool Calling Behavior Increases LLM Cost and Latency

1
Comments
6 min read
Why we built a programming language for AI prompts instead of another GUI

Why we built a programming language for AI prompts instead of another GUI

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