DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
I pinged 55 LLMs every 8 hours for a week. What stayed up, what broke, what vanished (Sep 15–21)

I pinged 55 LLMs every 8 hours for a week. What stayed up, what broke, what vanished (Sep 15–21)

Comments
3 min read
AI voice agent for customer service: what stops callers hanging up?

AI voice agent for customer service: what stops callers hanging up?

Comments
6 min read
RAG Architecture in 2026: A Production Blueprint for Retrieval-Augmented Generation

RAG Architecture in 2026: A Production Blueprint for Retrieval-Augmented Generation

Comments
12 min read
27 recorded LLM-judge runs, published as JSON

27 recorded LLM-judge runs, published as JSON

Comments
2 min read
Jev vs a 310M encoder I trained myself: 750 rows, three tasks, two different winners

Jev vs a 310M encoder I trained myself: 750 rows, three tasks, two different winners

Comments
10 min read
TimesFM 3.0 is not an LLM, and the word 'foundation' is doing too much work

TimesFM 3.0 is not an LLM, and the word 'foundation' is doing too much work

Comments
1 min read
Four Levels of Using an LLM: From Chat to Agents

Four Levels of Using an LLM: From Chat to Agents

5
Comments
14 min read
Are there any free API alternatives to Gemini or Groq with higher rate limits for a FastAPI backend?

Are there any free API alternatives to Gemini or Groq with higher rate limits for a FastAPI backend?

Comments
1 min read
We Read 100+ JEV Repositories. The Best Part Was the Code Around the Model Call.

We Read 100+ JEV Repositories. The Best Part Was the Code Around the Model Call.

Comments
10 min read
Building and Training LLM from scratch (No GPU)

Building and Training LLM from scratch (No GPU)

1
Comments
4 min read
Your AI Agent Can Call APIs Now

Your AI Agent Can Call APIs Now

Comments
6 min read
When The Bot Has Three Tools Available And Confidently Picks The Wrong One

When The Bot Has Three Tools Available And Confidently Picks The Wrong One

Comments
5 min read
New Jev model doesn’t fail in the reply. It fails in the gate.

New Jev model doesn’t fail in the reply. It fails in the gate.

2
Comments
2 min read
LLM Pricing Digest: DeepSeek Quietly Drops a Free Flash Model

LLM Pricing Digest: DeepSeek Quietly Drops a Free Flash Model

1
Comments
3 min read
Engenharia de Prompts: de Zero-shot a Retrieval Augmented Generation

Engenharia de Prompts: de Zero-shot a Retrieval Augmented Generation

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