DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
On-Policy vs Off-Policy Training of LLMs: How Models Start Learning From Their Own Outputs

On-Policy vs Off-Policy Training of LLMs: How Models Start Learning From Their Own Outputs

1
Comments 1
11 min read
Six prompt-optimization frameworks: what matters when you run them on the same task

Six prompt-optimization frameworks: what matters when you run them on the same task

1
Comments
3 min read
CrowdGPT - Let's train the future of AI together :D

CrowdGPT - Let's train the future of AI together :D

6
Comments
1 min read
How a theory of leftover surprise changed a memory layer

How a theory of leftover surprise changed a memory layer

Comments
9 min read
I Open-Sourced a Codex Skill That Researches, Tests, and Judges Competing Solutions

I Open-Sourced a Codex Skill That Researches, Tests, and Judges Competing Solutions

Comments
5 min read
One MCP server, eight AI clients: Apple Health setup that works everywhere

One MCP server, eight AI clients: Apple Health setup that works everywhere

Comments
2 min read
GPT-4o API Costs Dropped 50% - How to Recalculate Your AI Budget

GPT-4o API Costs Dropped 50% - How to Recalculate Your AI Budget

Comments
2 min read
RAG Framework with the Infra Lens

RAG Framework with the Infra Lens

Comments
3 min read
Why Your Coding Agent Doesn't Need an Electron App: A Minimalist LLM Proxy in Go

Why Your Coding Agent Doesn't Need an Electron App: A Minimalist LLM Proxy in Go

Comments
6 min read
Why Your Architecture Now Matters More Than Your Model

Why Your Architecture Now Matters More Than Your Model

Comments
4 min read
My DSPy pipeline compiled beautifully and got worse in production

My DSPy pipeline compiled beautifully and got worse in production

3
Comments 1
3 min read
Readme

Readme

Comments
6 min read
Diff Every Tool Call: Replaying Agent Runs from a JSONL Trace

Diff Every Tool Call: Replaying Agent Runs from a JSONL Trace

5
Comments 3
4 min read
แกะความคิดของ AI — เมื่อ Proprietary Model ไม่สามารถซ่อน Reasoning Trace ได้อีกต่อไป

แกะความคิดของ AI — เมื่อ Proprietary Model ไม่สามารถซ่อน Reasoning Trace ได้อีกต่อไป

Comments
6 min read
Prompt Injection Isn't Just a Chatbot Problem — It's Coming for Your Internal Tools Too

Prompt Injection Isn't Just a Chatbot Problem — It's Coming for Your Internal Tools Too

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