DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
I tried to make an AI agent answer more. It answered less.
ankushchadha profile

I tried to make an AI agent answer more. It answered less.

#ai #llm #eval #agents
1
Comments 1
5 min read
When You Swap Your AI Agent's Brain — Everything Breaks
hammermei profile

When You Swap Your AI Agent's Brain — Everything Breaks

#ai #agents #llm #infrastructure
Comments 1
6 min read
Why DeepSeek V3.2 Tool Calls Can Drift from Ordered System Instructions
bnobody47 profile

Why DeepSeek V3.2 Tool Calls Can Drift from Ordered System Instructions

#agents #ai #llm #opensource
Comments
4 min read
Claude Fable 5 can run for days. When does a solo dev actually want that?
rapls profile

Claude Fable 5 can run for days. When does a solo dev actually want that?

#ai #claude #llm #productivity
2
Comments
5 min read
My server pushes hints to agents — and the 3 iterations that led there
raymondnl profile
Ray

My server pushes hints to agents — and the 3 iterations that led there

#ai #llm #mcp #agentskills
2
Comments
6 min read
Who pays for the tokens? Designing an AI plugin that doesn't break your users' wallets
rapls profile
Rapls

Who pays for the tokens? Designing an AI plugin that doesn't break your users' wallets

#ai #llm #webdev #productivity
3
Comments 2
7 min read
Building a Skills Updater Pipeline for AI Platforms
niclydon profile

Building a Skills Updater Pipeline for AI Platforms

#showdev #ai #automation #llm
Comments
2 min read
GraphRAG Explained: How Knowledge Graphs Are Transforming Modern RAG Systems
itprepvn profile
ITPrep

GraphRAG Explained: How Knowledge Graphs Are Transforming Modern RAG Systems

#ai #llm #rag #machinelearning
Comments
3 min read
Your AI Agent Isn't Failing Because It Hallucinates — It's Failing Because of Rate Limits

Correctness trade-offs in capacity engineering
p0rt profile

Your AI Agent Isn't Failing Because It Hallucinates — It's Failing Because of Rate Limits

#ai #llm #devops #machinelearning
32
Comments 24
6 min read
How fast is LlamaStash? Overhead, throughput, and a fair comparison with Ollama and LM Studio

TTFT and RAG efficiency insights
deepu105 profile

How fast is LlamaStash? Overhead, throughput, and a fair comparison with Ollama and LM Studio

#ai #llamacpp #benchmark #llm
12
Comments 9
24 min read
Coverage decay: when style prompts forget themselves
niclab profile

Coverage decay: when style prompts forget themselves

#ai #llm #python #opensource
Comments 1
15 min read
DeepSeek/Qwen/Kimi via OpenAI-compatible APIs: a compatibility checklist
li_xu_4939deee356af27ede5 profile

DeepSeek/Qwen/Kimi via OpenAI-compatible APIs: a compatibility checklist

#ai #api #deepseek #llm
Comments 2
2 min read
The AI Is a Mirror: What a Year of Naming My Agents Taught Me
masroor_ahmad_68f272bb2ce profile

The AI Is a Mirror: What a Year of Naming My Agents Taught Me

#ai #claude #coding #llm
Comments 2
5 min read
# Scaffolding-Driven vs Model-Driven Planning: Where Agent Systems Actually Break *By Eyoel Nebiyu*
eyorata profile

# Scaffolding-Driven vs Model-Driven Planning: Where Agent Systems Actually Break *By Eyoel Nebiyu*

#agents #ai #architecture #llm
Comments
4 min read
How I Fixed the Infinite Feedback Loop When Auditing Project Plans with Claude
quolu profile
Quo

How I Fixed the Infinite Feedback Loop When Auditing Project Plans with Claude

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