DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
SGLang v0.5.14: LPLB Expert-Parallel Load Balancing

SGLang v0.5.14: LPLB Expert-Parallel Load Balancing

Comments
7 min read
Faster PRs, Weaker Instincts: The Judgment Problem in AI-Assisted Engineering

Metrics mask silent logic gaps

Faster PRs, Weaker Instincts: The Judgment Problem in AI-Assisted Engineering

8
Comments 3
4 min read
Prompt Injection + Missing Authentication: How I Turned an AI Translation API into a Free LLM Abuse Vector (Denial of Wallet)

Prompt Injection + Missing Authentication: How I Turned an AI Translation API into a Free LLM Abuse Vector (Denial of Wallet)

Comments
2 min read
LangChain Alternatives: The Principle for Choosing a RAG Framework by Workload, Not Hype

LangChain Alternatives: The Principle for Choosing a RAG Framework by Workload, Not Hype

Comments 2
6 min read
My Pipeline Needed Three Different Models to Hand Off to Each Other Without Losing Validation Along the Way

My Pipeline Needed Three Different Models to Hand Off to Each Other Without Losing Validation Along the Way

1
Comments
4 min read
Bitmask-Based LLM Security Firewall with reskSecure — Block Jailbreaks at Token Level

Bitmask-Based LLM Security Firewall with reskSecure — Block Jailbreaks at Token Level

Comments
2 min read
I tracked which AI models people actually use for a month. The top 5 are all Chinese or open-weight.

I tracked which AI models people actually use for a month. The top 5 are all Chinese or open-weight.

Comments
2 min read
"From Chatbot to Teammate: What Claude Tag Signals for How We Work"

"From Chatbot to Teammate: What Claude Tag Signals for How We Work"

1
Comments
2 min read
Beyond the Chatbot: Why 2026 is the Year of the Agentic Orchestrator

Beyond the Chatbot: Why 2026 is the Year of the Agentic Orchestrator

1
Comments
3 min read
AI-Assisted Engineering: Faster to Build Isn't Cheaper to Own

QA and exception handling get denser

AI-Assisted Engineering: Faster to Build Isn't Cheaper to Own

13
Comments 8
6 min read
Inside the Quiet Rise of Autonomous AI Agents

Inside the Quiet Rise of Autonomous AI Agents

Comments 1
17 min read
Lesson 4 - Validation: A must-have cornerstone

Lesson 4 - Validation: A must-have cornerstone

2
Comments 3
5 min read
Part 2 - Agentic AI

Part 2 - Agentic AI

Comments
3 min read
Part 1 - Functional AI

Part 1 - Functional AI

Comments
4 min read
GLM 5.2 Has a 1M Token Context Window. Here's What That Does to Your API Bill.

GLM 5.2 Has a 1M Token Context Window. Here's What That Does to Your API Bill.

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