DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
LLM Cost Management: From Monitoring Dashboards to Real-Time Enforcement

LLM Cost Management: From Monitoring Dashboards to Real-Time Enforcement

Comments
6 min read
Defluffer promete -45% en tokens. Yo medí el costo semántico del ahorro y es incómodo

Defluffer promete -45% en tokens. Yo medí el costo semántico del ahorro y es incómodo

Comments
9 min read
Agentes IA que pasan tus tests. Ese es el problema.

Agentes IA que pasan tus tests. Ese es el problema.

Comments
9 min read
Escribí un intérprete de Python en Python. Lo que aprendí no tiene nada que ver con Python

Escribí un intérprete de Python en Python. Lo que aprendí no tiene nada que ver con Python

Comments
8 min read
I Gave AI Agents a Telecom Job Interview. Most Failed Without a Cheat Sheet

I Gave AI Agents a Telecom Job Interview. Most Failed Without a Cheat Sheet

Comments
8 min read
LLM Evals on Real Traffic — Not Just Test Suites

LLM Evals on Real Traffic — Not Just Test Suites

1
Comments 1
4 min read
The Dual-Signal Governor: A Control-Plane Pattern for Drift-Aware Systems

The Dual-Signal Governor: A Control-Plane Pattern for Drift-Aware Systems

1
Comments
4 min read
Agents, Smart Contracts, and a Unified ML Engine

Agents, Smart Contracts, and a Unified ML Engine

Comments
2 min read
An unexplainable thing I saw: the agent didn't just comply with rules — it endorsed them

An unexplainable thing I saw: the agent didn't just comply with rules — it endorsed them

Comments
26 min read
Claude system prompt diff: lo que cambiĂł entre Opus 4.6 y 4.7 (y yo lo estaba viendo sin saberlo)

Claude system prompt diff: lo que cambiĂł entre Opus 4.6 y 4.7 (y yo lo estaba viendo sin saberlo)

Comments
8 min read
Stop Your AI Agent From Hallucinating Features

Stop Your AI Agent From Hallucinating Features

Comments
2 min read
How to Give Your AI Agent Memory Between Conversations

How to Give Your AI Agent Memory Between Conversations

Comments
2 min read
How to Govern Claude Code Usage Across Engineering Teams

How to Govern Claude Code Usage Across Engineering Teams

5
Comments 3
5 min read
What we found when an AI audited an AI (real findings, no sanitising)

What we found when an AI audited an AI (real findings, no sanitising)

Comments
4 min read
When "Slow Thinking" Is Just "Slow Talking"

When "Slow Thinking" Is Just "Slow Talking"

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