DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Inside vLLM's CPU backend: a new contributor's notes

Inside vLLM's CPU backend: a new contributor's notes

Comments
7 min read
Why Coding Agents Need Two Halves of Infrastructure: Control Plane + Fast Data Plane

Why Coding Agents Need Two Halves of Infrastructure: Control Plane + Fast Data Plane

Comments 1
7 min read
When Your AI Agent Goes Silent: The Failure Patterns Most Developers Miss

When Your AI Agent Goes Silent: The Failure Patterns Most Developers Miss

1
Comments 1
5 min read
When AI Agents Go Rogue: Preventing Destructive Automation

When AI Agents Go Rogue: Preventing Destructive Automation

Comments
5 min read
Stop trusting the agent: bind tool-call approvals to the exact call

Stop trusting the agent: bind tool-call approvals to the exact call

1
Comments
4 min read
When Prompt Batching Made My LLM App More Expensive

Retry overhead from single-item failures

When Prompt Batching Made My LLM App More Expensive

21
Comments 12
4 min read
LLM Token Costs: Why Your Prompt Might Cost 10x More Than You Think

LLM Token Costs: Why Your Prompt Might Cost 10x More Than You Think

Comments 1
1 min read
GLM 5.2: Zhipu's Open-Weight Frontier Model With 1M Context

GLM 5.2: Zhipu's Open-Weight Frontier Model With 1M Context

Comments
5 min read
Microsoft Says 50% AI Code. Here's What That Actually Means for Engineers

Microsoft Says 50% AI Code. Here's What That Actually Means for Engineers

Comments
3 min read
The knowledge-authority layer: what your agents can't get from the outside

The knowledge-authority layer: what your agents can't get from the outside

4
Comments 1
3 min read
Stop Passing Entire Chat Histories to AI Agents

Stop Passing Entire Chat Histories to AI Agents

Comments
4 min read
How LumiClip Finds the Best Moments in Your Video and Reframes Them for Mobile

How LumiClip Finds the Best Moments in Your Video and Reframes Them for Mobile

Comments
5 min read
How Does Your Team Decide Which LLM-Based Tools to Use for Software Development Tasks?

How Does Your Team Decide Which LLM-Based Tools to Use for Software Development Tasks?

Comments
1 min read
Nobody keeps the receipts for AI pricing, so I built the changelog

Nobody keeps the receipts for AI pricing, so I built the changelog

3
Comments
2 min read
Compass v1.1.0 · we shipped a memory plugin that catches its own consumption drift

Compass v1.1.0 · we shipped a memory plugin that catches its own consumption drift

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