DEV Community

Artificial Intelligence

Artificial intelligence leverages computers and machines to mimic the problem-solving and decision-making capabilities found in humans and in nature.

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
OpenAI's model escaped its sandbox and hacked Hugging Face to cheat on a test

OpenAI's model escaped its sandbox and hacked Hugging Face to cheat on a test

Comments
3 min read
Stop Just Learning. Start Shipping: Welcome to SHEinnov8

Stop Just Learning. Start Shipping: Welcome to SHEinnov8

10
Comments
2 min read
Introducing Ayeixa Sentience Eval: Catching Raw JSON Leaks & Robotic Clichés in Agent Dialogue

Introducing Ayeixa Sentience Eval: Catching Raw JSON Leaks & Robotic Clichés in Agent Dialogue

1
Comments 1
2 min read
I Gave GitHub Copilot CLI a Memory I Own

I Gave GitHub Copilot CLI a Memory I Own

Comments 2
3 min read
Agentic Coding and the Design Space You Don't See

Agentic Coding and the Design Space You Don't See

1
Comments
7 min read
Self-Hosting vLLM on Cloud GPUs in 2026: Sub-180ms LLM Inference for Autonomous AI Agents (Full Production Guide)

Self-Hosting vLLM on Cloud GPUs in 2026: Sub-180ms LLM Inference for Autonomous AI Agents (Full Production Guide)

1
Comments 3
5 min read
Building Bulletproof Credit & Compute Billing Systems for GPU-Heavy Workflows

Building Bulletproof Credit & Compute Billing Systems for GPU-Heavy Workflows

1
Comments 2
11 min read
The Age of AI Requires Standard Ten: One Unified Code for All Software

The Age of AI Requires Standard Ten: One Unified Code for All Software

Comments
4 min read
Why Your AI Agent Drowns in 50,000 Tokens of Tool Definitions

Why Your AI Agent Drowns in 50,000 Tokens of Tool Definitions

1
Comments
2 min read
We Taught Our Code Search to Think — Here's What Broke (and What Fixed It)

We Taught Our Code Search to Think — Here's What Broke (and What Fixed It)

1
Comments
3 min read
Our LLM Judges Called Human Writing "AI-Flavored" 88% of the Time

Our LLM Judges Called Human Writing "AI-Flavored" 88% of the Time

Comments
3 min read
CrossSessionMemoryGuard: vigilando la exfiltraciĂłn de memoria cross-session en agentes multi-tenant

CrossSessionMemoryGuard: vigilando la exfiltraciĂłn de memoria cross-session en agentes multi-tenant

2
Comments
5 min read
I Ditched Cloud Vector Databases for SQLite FTS5 — and My RAG Pipeline Got 10x Better

I Ditched Cloud Vector Databases for SQLite FTS5 — and My RAG Pipeline Got 10x Better

1
Comments 4
6 min read
Meta Muse Spark 1.2 Honest Review: Loses the Benchmarks, Wins as an Agent

Meta Muse Spark 1.2 Honest Review: Loses the Benchmarks, Wins as an Agent

1
Comments
2 min read
MCP versus API: what assistants need that your REST endpoints do not spell out

MCP versus API: what assistants need that your REST endpoints do not spell out

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