DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Token-level eval harness for tool-calling agents: what we wired up

Token-level eval harness for tool-calling agents: what we wired up

Comments 1
4 min read
Agent as a Tool Call: Claude Code's Fork-Exec Pattern

Agent as a Tool Call: Claude Code's Fork-Exec Pattern

2
Comments 2
2 min read
I built a free LLM pricing tool that updates itself daily. here's how

I built a free LLM pricing tool that updates itself daily. here's how

3
Comments
3 min read
LLM Cost Optimization for Agent Workflows: A Practical Guide

LLM Cost Optimization for Agent Workflows: A Practical Guide

Comments 2
13 min read
Evaluating Open-Weight LLMs for Phishing Simulation and Red Teaming

Evaluating Open-Weight LLMs for Phishing Simulation and Red Teaming

Comments
3 min read
Per-customer budget caps on our caption pipeline: 3 weeks with virtual keys

Per-customer budget caps on our caption pipeline: 3 weeks with virtual keys

Comments 1
4 min read
Serving a Fleet of SLMs on One RTX 5080: Multi-Model on a Single Consumer GPU

Serving a Fleet of SLMs on One RTX 5080: Multi-Model on a Single Consumer GPU

1
Comments 1
4 min read
I'm writing this down before I lose the thread

I'm writing this down before I lose the thread

Comments
7 min read
Your LLM Forgets Everything. Give It a Wiki!

Your LLM Forgets Everything. Give It a Wiki!

Comments 2
4 min read
CKP LLM: The Missing Layer Between Your AI Agent and Its Knowledge Base

CKP LLM: The Missing Layer Between Your AI Agent and Its Knowledge Base

Comments 2
5 min read
Voice agent latency is a lie. The number you care about is barge-in interrupt rate.

Voice agent latency is a lie. The number you care about is barge-in interrupt rate.

1
Comments 2
4 min read
The Pomodoro Timer Isn’t About Time, It’s About Engineering

The Pomodoro Timer Isn’t About Time, It’s About Engineering

4
Comments
5 min read
Why Signatures Make Automatic Optimization Easier Than Writing Prompts Directly

Why Signatures Make Automatic Optimization Easier Than Writing Prompts Directly

Comments
7 min read
Running a 70B LLM on Pure RISC-V: The MilkV Pioneer Deployment Journey

Running a 70B LLM on Pure RISC-V: The MilkV Pioneer Deployment Journey

Comments
17 min read
Self-healing LLM routing: 13 providers, one fallback chain

Self-healing LLM routing: 13 providers, one fallback chain

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