DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Your LLM Gets Dumber Every Time You Compact Context — And Nobody Is Measuring It

Your LLM Gets Dumber Every Time You Compact Context — And Nobody Is Measuring It

Comments
3 min read
AI Coding Agents Need Runtime Telemetry Before Commit Telemetry

AI Coding Agents Need Runtime Telemetry Before Commit Telemetry

2
Comments 5
4 min read
LuisCore curated Q&A for LLMs — daily syndication · 2026-05-28

LuisCore curated Q&A for LLMs — daily syndication · 2026-05-28

Comments
3 min read
Camouflage Injection Paper: Camouflage Detection Gap

Camouflage Injection Paper: Camouflage Detection Gap

Comments
7 min read
The Decision Machine

The Decision Machine

Comments
2 min read
Deepseek V4 Pro Price Drop Again on May 23, 2026

Deepseek V4 Pro Price Drop Again on May 23, 2026

Comments
2 min read
I Added a /recovery Endpoint to My LLM Proxy So Agents Never Lose Progress Mid-Task

I Added a /recovery Endpoint to My LLM Proxy So Agents Never Lose Progress Mid-Task

Comments
3 min read
A IA nĂŁo vai pensar por vocĂŞ. E isso Ă© uma coisa boa.

A IA nĂŁo vai pensar por vocĂŞ. E isso Ă© uma coisa boa.

8
Comments
3 min read
The tokens-per-byte trap: character-level 'compression' adds tokens

The tokens-per-byte trap: character-level 'compression' adds tokens

Comments
6 min read
Multi-Head Latent Attention (MLA)

Multi-Head Latent Attention (MLA)

Comments
9 min read
My LLM API Calls Were Failing Silently. Here's the Logging Setup I Wish I Had Earlier

My LLM API Calls Were Failing Silently. Here's the Logging Setup I Wish I Had Earlier

3
Comments 4
8 min read
# I built a tool that found my LangGraph email agent could be hijacked to forward the entire inbox to an attacker

# I built a tool that found my LangGraph email agent could be hijacked to forward the entire inbox to an attacker

4
Comments
4 min read
AI-Generated Replies at Scale: Lessons from 100K+ Automated Responses

AI-Generated Replies at Scale: Lessons from 100K+ Automated Responses

Comments
6 min read
Distributed Tracing for LLM Agents: When MCP Makes Tool Calls Observable

Distributed Tracing for LLM Agents: When MCP Makes Tool Calls Observable

Comments 1
5 min read
The Game Genie for LLMs: Persistent Cognitive State for Your Agents

The Game Genie for LLMs: Persistent Cognitive State for Your Agents

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