DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
A 9-point eval gain vanished when we deduped train against test

A 9-point eval gain vanished when we deduped train against test

Comments
4 min read
I built an AI tool that saves 80% LLM costs & catches hallucinations (Open Source)

I built an AI tool that saves 80% LLM costs & catches hallucinations (Open Source)

Comments
2 min read
How We Built an AI CRM That Actually Remembers Customers Using Hindsight

How We Built an AI CRM That Actually Remembers Customers Using Hindsight

Comments
3 min read
AI Agents Explained: the Thought-Action-Observation Loop

AI Agents Explained: the Thought-Action-Observation Loop

1
Comments 1
1 min read
Emergence AI 的疯狂实验——涌现世界

Emergence AI 的疯狂实验——涌现世界

Comments
2 min read
Email Tools for Claude: Tool Use With an Agent Mailbox

Email Tools for Claude: Tool Use With an Agent Mailbox

Comments 1
5 min read
Three AI providers went down on the same day. Here's the architecture that didn't care.

Three AI providers went down on the same day. Here's the architecture that didn't care.

Comments
5 min read
How to Fine-Tune LLMs on Your Own Data: Open-Source Models, RL Environments, and Evals

How to Fine-Tune LLMs on Your Own Data: Open-Source Models, RL Environments, and Evals

Comments
7 min read
I tracked every GitHub traffic spike for my open source LLM proxy for 7 weeks. Then I did the exact same thing again, and it worked again.

I tracked every GitHub traffic spike for my open source LLM proxy for 7 weeks. Then I did the exact same thing again, and it worked again.

Comments
5 min read
caveman 真的能幫我省下 Token 帳單嗎?

caveman 真的能幫我省下 Token 帳單嗎?

Comments
2 min read
FinOps X 2026 recap: the great token panic

FinOps X 2026 recap: the great token panic

Comments
2 min read
I Stopped Tweaking Prompts. Here's How I Cut LLM Hallucinations to 6%.

I Stopped Tweaking Prompts. Here's How I Cut LLM Hallucinations to 6%.

Comments
3 min read
Moving From Chatbots to Agents: Testing OpenAI Operator

Moving From Chatbots to Agents: Testing OpenAI Operator

Comments
2 min read
Graphify on macOS, to shorten the LLM consumption

Graphify on macOS, to shorten the LLM consumption

Comments
1 min read
We version our tool schemas like an API contract, because the agent is a consumer

We version our tool schemas like an API contract, because the agent is a consumer

Comments
2 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.