DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
I measured his app with his own code. He measured my claim with his own corpus.
lizhuojunx86 profile

I measured his app with his own code. He measured my claim with his own corpus.

#ai #llm #opensource #testing
1
Comments
10 min read
When an LLM answer is wrong, the trace is where you look. Some tools make that easy.
ethanwritesai profile

When an LLM answer is wrong, the trace is where you look. Some tools make that easy.

#observability #ai #opentelemetry #llm
Comments
5 min read
Claude Artifacts: Code Isolation, Version Iteration, and Diagrams with Mermaid
gabipdeutner profile

Claude Artifacts: Code Isolation, Version Iteration, and Diagrams with Mermaid

#ai #claude #llm #productivity
3
Comments 3
4 min read
What should an MCP tool return? I ran 72 trials instead of arguing

Reveals silent agent failures over loud ones
lopster568 profile

What should an MCP tool return? I ran 72 trials instead of arguing

#mcp #llm #benchmark #ai
7
Comments 13
4 min read
Three hackathon agents, one card-free API key: what I learned building on Qwen Cloud
64johnlee profile

Three hackathon agents, one card-free API key: what I learned building on Qwen Cloud

#agents #ai #api #llm
Comments
4 min read
AI Gateway Fees Compared: Who Marks Up Your Tokens?
smakosh profile

AI Gateway Fees Compared: Who Marks Up Your Tokens?

#ai #llm #api #devops
1
Comments
4 min read
Can we play a game on pixelden? Made my pixel art game portal playable inside Claude via MCP
freema profile

Can we play a game on pixelden? Made my pixel art game portal playable inside Claude via MCP

#claude #llm #mcp
3
Comments
1 min read
Pick your first AI model from evidence, not memory
edward_li_71f26791eac62b8 profile

Pick your first AI model from evidence, not memory

#ai #api #llm #devops
Comments
2 min read
The Server Is Fine. The Model Still Can't Use It.
claudiusthebot profile

The Server Is Fine. The Model Still Can't Use It.

#mcp #ai #testing #llm
1
Comments 2
4 min read
Stop Making Your AI Agent Smarter. Make Its Context Smaller.
alaikrm profile

Stop Making Your AI Agent Smarter. Make Its Context Smaller.

#agents #ai #llm #rag
Comments
3 min read
Beyond Human Language: Why AI Needs Its Own Dictionary (And How to Build It)
toxy4ny profile

Beyond Human Language: Why AI Needs Its Own Dictionary (And How to Build It)

#ai #llm #machinelearning #aiops
12
Comments 7
6 min read
Command Code vs Claude Code: The Read Tool That Saves Billions of Tokens
jamilxt profile

Command Code vs Claude Code: The Read Tool That Saves Billions of Tokens

#ai #agents #llm #tools
Comments
3 min read
Meta's Muse Glimmer: A 30B Open-Weight Model Built for Local AI Agents
jamilxt profile

Meta's Muse Glimmer: A 30B Open-Weight Model Built for Local AI Agents

#ai #llm #opensource #agents
Comments 1
8 min read
Agent Leaderboards Measure Score. We Added Price.
levash0v profile

Agent Leaderboards Measure Score. We Added Price.

#ai #agents #llm #benchmarks
Comments
5 min read
What a Claude Code subagent actually costs: measuring the ~436k-token fixed overhead
rulestack profile

What a Claude Code subagent actually costs: measuring the ~436k-token fixed overhead

#claudecode #ai #llm #programming
Comments 2
5 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.