DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Self-hosting a lite agent backend on one TPU: Gemma 4 E2B + vLLM on a v5e-1

Self-hosting a lite agent backend on one TPU: Gemma 4 E2B + vLLM on a v5e-1

15
Comments 1
21 min read
"Loop Engineering: How I Stopped My AI Agent From Reward-Hacking Its Own Quality Checks"

"Loop Engineering: How I Stopped My AI Agent From Reward-Hacking Its Own Quality Checks"

Comments
5 min read
The boring layer around your LLM call

The boring layer around your LLM call

Comments 5
6 min read
AMD drops $5B on Anthropic as Microsoft fine-tunes Alibaba baseline models

AMD drops $5B on Anthropic as Microsoft fine-tunes Alibaba baseline models

5
Comments
8 min read
Ditch Naive Chunking: Late Chunking RAG in Spring AI

Ditch Naive Chunking: Late Chunking RAG in Spring AI

Comments
2 min read
An AI Escaped Its Sandbox. What It Means for Your Agents

An AI Escaped Its Sandbox. What It Means for Your Agents

Comments
7 min read
Gemini's New Flash Models Change How You Control Outputs

Gemini's New Flash Models Change How You Control Outputs

1
Comments
3 min read
When the Picture Doesn't Match the Label — Part 2: Feature-Based Detection with OCR and VQA

When the Picture Doesn't Match the Label — Part 2: Feature-Based Detection with OCR and VQA

Comments
7 min read
Engineering Resilient AI Orchestration: Mitigating Compliance and Operational Risks in Generative Feature Deployment

Engineering Resilient AI Orchestration: Mitigating Compliance and Operational Risks in Generative Feature Deployment

Comments
5 min read
Stop Vibes-Testing AI Coding Models: A Repeatable Evaluation Suite You Can Run for Free

Stop Vibes-Testing AI Coding Models: A Repeatable Evaluation Suite You Can Run for Free

2
Comments 1
6 min read
Kimi K3 Explained: The 2.8T Open Model Breaking Leaderboards

Kimi K3 Explained: The 2.8T Open Model Breaking Leaderboards

Comments
6 min read
Bio-Tuning Glasses: Building an Invisible Biofeedback Interface with Edge AI and Adaptive Optics

Bio-Tuning Glasses: Building an Invisible Biofeedback Interface with Edge AI and Adaptive Optics

2
Comments 1
5 min read
Your LLM sends valid data in an invalid shape

Your LLM sends valid data in an invalid shape

1
Comments 7
6 min read
Lynkr vs LiteLLM's New `complexity_router`

Lynkr vs LiteLLM's New `complexity_router`

1
Comments
7 min read
I Tested Kimi K3 on a Real Astro Codebase: Strong Cross-File Analysis, Unsafe First Fix

I Tested Kimi K3 on a Real Astro Codebase: Strong Cross-File Analysis, Unsafe First Fix

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