DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Why Apple Is Pivoting Hard Toward On-Device AI in 2026

Why Apple Is Pivoting Hard Toward On-Device AI in 2026

Comments
7 min read
OpenAI Outage Postmortem: What Status Pages Don't Tell You

OpenAI Outage Postmortem: What Status Pages Don't Tell You

Comments
7 min read
The 6-Line Postgres Migration That Halved a Team's LLM Bill

The 6-Line Postgres Migration That Halved a Team's LLM Bill

Comments
7 min read
Vibe Coding Just Failed Its First Real Audit

Vibe Coding Just Failed Its First Real Audit

Comments
8 min read
The 2-Line Defense That Stops 90% of Real-World Prompt Injection

The 2-Line Defense That Stops 90% of Real-World Prompt Injection

Comments
7 min read
The Single Unit Test Every LLM Prompt Should Have

The Single Unit Test Every LLM Prompt Should Have

Comments
7 min read
Observability 2.0: Tracing AI "Thought Chains" with OpenTelemetry

Observability 2.0: Tracing AI "Thought Chains" with OpenTelemetry

Comments 2
3 min read
My AI Agent Kept Lying to Me. Then It Tried to Trick Me.

My AI Agent Kept Lying to Me. Then It Tried to Trick Me.

Comments 2
5 min read
Why I Stopped Counting Tokens: Building a Zero‑Token Cognition Engine

Why I Stopped Counting Tokens: Building a Zero‑Token Cognition Engine

Comments
1 min read
Local-first: a Model on Your Own Machine, Zero Cloud

Local-first: a Model on Your Own Machine, Zero Cloud

3
Comments 1
4 min read
Qwen3.6 Performance Boost with vLLM, New Ollama Management Tool & 35B Model

Qwen3.6 Performance Boost with vLLM, New Ollama Management Tool & 35B Model

Comments
3 min read
Prompt Injection in AI Coding Agents: 3 Attack Vectors, 4 Defenses

Prompt Injection in AI Coding Agents: 3 Attack Vectors, 4 Defenses

Comments
12 min read
How I Caught My LLM Fabricating Its Own Evidence

How I Caught My LLM Fabricating Its Own Evidence

Comments 3
3 min read
Trained, Not Prompted: Why Fine-Tuned Models Beat LLM Wrappers for Offensive Security

Trained, Not Prompted: Why Fine-Tuned Models Beat LLM Wrappers for Offensive Security

Comments
2 min read
Building AI Resume Tailor — v0 build notes

Building AI Resume Tailor — v0 build notes

Comments 1
7 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.