Llm - DEV Community

Skip to content

DEV Community

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

Real-world data from 51,000 game API calls

Aliaksei Zelianouski

Nov 8

How much does it cost to run a text game with LLMs

#ai #llm #gamedev #machinelearning

18 min read

Jayant Chaudhary for eProxim

Nov 10

Guardrails for AI Agent Tool Calls That Write to Your ERP, in Python

#ai #python #llm #security

12 min read

WeekendAiProjects

Nov 10

Prompt injection by email: we attacked our local AI inbox assistant. It reads everything and can send nothing

#ai #security #python #llm

8 min read

Pin Xiong

Nov 10

Testing async side effects in an LLM agent harness: tickets, retries, and exactly-once

#testing #ai #python #llm

6 min read

Valen

Nov 10

35 days running as an agent: $4.30 in costs, one cent earned

#agents #ai #buildinpublic #llm

2 min read

Nov 10

The verified agent pattern: building outbound agents for a web that blocks them by default

#ai #agents #llm #security

7 min read

Bhargav

Nov 10

What Does It Take to Run a 30B Model Without a GPU?

#c #llm #ai #opensource

13 min read

Vladimir Sobolev

Nov 10

Which model, settings and prompt? Testing an LLM step one change at a time

#testing #llm #ai #automation

13 min read

Yoseph Eikelman

Nov 10

A therapy scribe where a model may add the commas, but code decides whether it may change a word

#llm #healthcare #speech #hebrew

7 min read

ZedIoT

Nov 10

Can an 8 GB Edge Device Run a 2 GB Model? Budget Memory at Peak Concurrency

#ai #llm #performance #edgecomputing

10 min read

Victor Machiavelli

Nov 10

How I stopped an AI astrologer from making things up: ephemeris facts, book grounding and a fact-checker

#llm #ai #python #nextjs

4 min read

Nov 10

0/55 three nights in a row: product bug or test bug?

#testing #saas #llm #devops

3 min read

Alex Chen

Nov 10

Your Routing Dashboard Lies Until the Attribution Window Closes

#llm #ai #gpu #routing

6 min read

Calabonga

Nov 10

Разработчик-инженер или промпт вместо кода

#ai #career #llm #programming

1 min read

Muhammad Hussnain Jamil

Nov 10

LLM Inference Cost in 2026: Why Cost per Finished Task Beats Cost per Token

#llm #machinelearning #python #devops

22 min read

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