DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
I bootstrapped an API business on a single RTX 3060, from literally zero budget
joaopaulona profile

I bootstrapped an API business on a single RTX 3060, from literally zero budget

#api #buildinpublic #llm #selfhosted
Comments
3 min read
Mi primer intento con agentes de IA fracasĂł. El problema no era el modelo
saulemprendedor profile

Mi primer intento con agentes de IA fracasĂł. El problema no era el modelo

#agents #ai #llm #softwareengineering
Comments
3 min read
Your AI Agent Works in Dev. It Will Fail in Production. Here's the Math.
sasajib profile

Your AI Agent Works in Dev. It Will Fail in Production. Here's the Math.

#ai #llm #devops #agents
Comments
4 min read
tokeneff: An Open-Source LLM Cost Meter That Runs Locally
nio_zanghotmailcom_zang profile

tokeneff: An Open-Source LLM Cost Meter That Runs Locally

#ai #cli #llm #opensource
Comments 3
3 min read
My Zod Schema Was Valid. The Library Said It Wasn't.
yatindavra profile

My Zod Schema Was Valid. The Library Said It Wasn't.

#typescript #node #zod #llm
3
Comments 8
3 min read
7 Reasons Your RAG Chatbot Fails in Production (And How to Fix Them in TypeScript)
hussnain-shahid profile

7 Reasons Your RAG Chatbot Fails in Production (And How to Fix Them in TypeScript)

#architecture #llm #rag #typescript
Comments 1
9 min read
Prompt Caching: Why cache_control Writes But Never Reads
ji_ai profile

Prompt Caching: Why cache_control Writes But Never Reads

#llm #ai #performance #agents
1
Comments 7
6 min read
Your LLM judge gives a different answer on re-runs. How do you test with it?
ashwin_ugale_102f2abc9cec profile

Your LLM judge gives a different answer on re-runs. How do you test with it?

#ai #llm #testing #machinelearning
4
Comments 21
2 min read
ChatGPT Was the Interface. MCP Is the Infrastructure.
omi0 profile
Omi0

ChatGPT Was the Interface. MCP Is the Infrastructure.

#ai #llm #mcp #softwaredevelopment
Comments 3
4 min read
A New MiniMax Model Dropped: How to Evaluate It on Your Own Code Before Believing the Benchmarks
apppro_5726 profile

A New MiniMax Model Dropped: How to Evaluate It on Your Own Code Before Believing the Benchmarks

#ai #opensource #llm #programming
Comments
4 min read
I tested Claude Code's memory against mine. They are not doing the same job.

Cross-device testing reveals surprising boundaries
heinrichneb profile

I tested Claude Code's memory against mine. They are not doing the same job.

#ai #claudecode #productivity #llm
31
Comments 33
7 min read
I built a zero-backend, browser-only alternative to Open WebUI and heavy LLM stacks
talos1313 profile

I built a zero-backend, browser-only alternative to Open WebUI and heavy LLM stacks

#ai #opensource #webdev #llm
Comments 2
2 min read
Anthropic shipped an official eval runner for Claude Code. I made my tool run on it the same day. Field notes.
smartword_world_0b5b38003 profile

Anthropic shipped an official eval runner for Claude Code. I made my tool run on it the same day. Field notes.

#ai #claude #llm #testing
Comments 5
3 min read
A Developer's Checklist for Every RAG Lifecycle (Beyond Chunk-Embed-Search)
tanmay_bhurkunde profile

A Developer's Checklist for Every RAG Lifecycle (Beyond Chunk-Embed-Search)

#ai #architecture #llm #rag
Comments 1
2 min read
How I stop an LLM from hallucinating in production (RAG + entity-match + MCP)
jeemmo profile

How I stop an LLM from hallucinating in production (RAG + entity-match + MCP)

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