DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
A 3-step agent cost me $4.20. agenttrace showed me the O(n ) tool call hiding in plain sight.
mukundakatta profile

A 3-step agent cost me $4.20. agenttrace showed me the O(n ) tool call hiding in plain sight.

#hermesagent #ai #llm #observability
Comments
4 min read
The prompt your SDK sends is not the prompt you wrote
mukundakatta profile

The prompt your SDK sends is not the prompt you wrote

#hermesagent #ai #llm #python
Comments
3 min read
Why Logs Aren't Enough to Debug AI Agents
opswald profile

Why Logs Aren't Enough to Debug AI Agents

#ai #debugging #llm #agents
Comments
5 min read
LM Studio Adds MTP Speculative Decoding; Qwen 3.6 GGUF Quants, Ollama Insights
soytuber profile
soy

LM Studio Adds MTP Speculative Decoding; Qwen 3.6 GGUF Quants, Ollama Insights

#ai #llm #selfhosted
Comments
3 min read
AI Cost Attribution Evidence Anchors in 2026: How to Close Tenant Chargeback Disputes Without Re-running Allocation
argon_loop profile

AI Cost Attribution Evidence Anchors in 2026: How to Close Tenant Chargeback Disputes Without Re-running Allocation

#ai #cloud #infrastructure #llm
Comments
7 min read
[Open-Source LLM Agent #1] Running a LangGraph ReAct Agent in Production: OpenAI-Compatible API + Multi-Model Gateway + One-Line Tracing
javaking1129 profile
duke

[Open-Source LLM Agent #1] Running a LangGraph ReAct Agent in Production: OpenAI-Compatible API + Multi-Model Gateway + One-Line Tracing

#langchain #llm #python #kubernetes
Comments
5 min read
How I A/B test LLM prompts without fooling myself
kartik-nvjk profile

How I A/B test LLM prompts without fooling myself

#llm #ai #prompts #testing
2
Comments 1
5 min read
Prompt Caching Explained Like You're Talking to a Smart Human (Not an AI Researcher)
anandindia93 profile

Prompt Caching Explained Like You're Talking to a Smart Human (Not an AI Researcher)

#ai #llm #performance #tutorial
Comments
3 min read
A Tiny First-Call Checklist Before Trusting Any LLM Gateway
xuxu_8309f491756bc5701316 profile

A Tiny First-Call Checklist Before Trusting Any LLM Gateway

#ai #llm #api
Comments
1 min read
AI 2026AI
zny10289 profile
ZNY

AI 2026AI

#ai #llm #monitoring #tutorial
Comments
6 min read
Securing LangGraph Multi-Agent Workflows Against Memory Poisoning (ASI06)
vaishnavi_gudur profile

Securing LangGraph Multi-Agent Workflows Against Memory Poisoning (ASI06)

#security #python #llm #agents
Comments
3 min read
How Markus Builds AI Teams That Actually Ship — Not Just Chat
jsyqrt profile

How Markus Builds AI Teams That Actually Ship — Not Just Chat

#agents #ai #llm #softwareengineering
Comments
3 min read
Your RAG faithfulness check is measuring copy-paste, not faithfulness
iamhetpatel profile

Your RAG faithfulness check is measuring copy-paste, not faithfulness

#rag #llm #evaluation #machinelearning
2
Comments 6
5 min read
DeepSeek V4 on Huawei's Ascend 950: A Real Stress Test for China's AI Chip Ecosystem
lanternproton profile

DeepSeek V4 on Huawei's Ascend 950: A Real Stress Test for China's AI Chip Ecosystem

#ai #hardware #machinelearning #llm
Comments
6 min read
DevOps Meets Generative AI: Building, Testing, and Deploying LLM-Powered Apps
sciforce profile

DevOps Meets Generative AI: Building, Testing, and Deploying LLM-Powered Apps

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