DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Retrieval Is Not Memory

Retrieval Is Not Memory

Comments
1 min read
Jan Sahay: Transforming Healthcare Access with an AI Voice Agent

Jan Sahay: Transforming Healthcare Access with an AI Voice Agent

Comments
5 min read
Z.ai’s GLM-5.3 Closes the AI Cyber Gap

Z.ai’s GLM-5.3 Closes the AI Cyber Gap

Comments
6 min read
Building Vyapar AI: My 10-Day Journey Building an Indian Voice Agent with Murf Falcon

Building Vyapar AI: My 10-Day Journey Building an Indian Voice Agent with Murf Falcon

Comments
8 min read
Your LLM Trace Is Green. Why Is the RAG Answer Still Wrong?

Your LLM Trace Is Green. Why Is the RAG Answer Still Wrong?

6
Comments 5
6 min read
Stop Passing Strings Between AI Agents: Use In-Memory KV Cache Handoffs

Stop Passing Strings Between AI Agents: Use In-Memory KV Cache Handoffs

Comments
3 min read
Deploying Qwen3.8-2.4T-A95B with vLLM: Verified GPU Pods, Quants, and Serving Recipes

Deploying Qwen3.8-2.4T-A95B with vLLM: Verified GPU Pods, Quants, and Serving Recipes

5
Comments
7 min read
What actually breaks when you let an LLM execute real actions

What actually breaks when you let an LLM execute real actions

Comments 1
5 min read
Language is a routing problem, not a translation problem

Language is a routing problem, not a translation problem

6
Comments 6
3 min read
Semantic Caching: The LLM Cost-Killer Nobody's Talking About Enough

Semantic Caching: The LLM Cost-Killer Nobody's Talking About Enough

Comments
2 min read
Our Documentation Was Lying. The Model Believed It.

Our Documentation Was Lying. The Model Believed It.

Comments 2
8 min read
I Put `minimum` in My JSON Schema. ShapeCraft Ignored It. That Was By Design

I Put `minimum` in My JSON Schema. ShapeCraft Ignored It. That Was By Design

1
Comments
4 min read
Turning Qwen2.5-0.5B into a JSON API with SFT — 23% 100% on a Free T4

Turning Qwen2.5-0.5B into a JSON API with SFT — 23% 100% on a Free T4

1
Comments
13 min read
Boris Cherny's Steps of AI Adoption, Through the Eyes of Our Pipeline

Boris Cherny's Steps of AI Adoption, Through the Eyes of Our Pipeline

5
Comments 1
29 min read
I benchmarked 7 Python JSON parsers on 300 malformed LLM outputs — mine lost the column I cared about

I benchmarked 7 Python JSON parsers on 300 malformed LLM outputs — mine lost the column I cared about

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