Skip to content

DEV Community

# llm

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

Cor E

Jun 12

Claude Fable 5 Was Jailbroken in 48 Hours. Here's What Actually Stopped Nothing.

#security #llm #appsec #cybersecurity

5 min read

Helgard

Jun 11

We create a way to unload Qwen2.5 KV cache to RAM.

#showdev #ai #llm #performance

3 min read

Baran Özdemir for Eidentic

Jun 11

Why agents need memory that improves itself

#ai #typescript #llm #programming

2 min read

Jun 12

AI Observability: Logs, Prompts, Tool Calls, And Cost

#observability #ai #llm #opentelemetry

15 min read

Ken

Jun 11

A Fluent LLM Answer Is Not the Same as an Inspected Answer

#devtools #python #ai #llm

4 min read

Jun 11

Introducing Duplex: A Zero-Backend, Multiplexed LLM Inference Engine for True Client-Side Parallel AI

#ai #webdev #llm #mcp

4 min read

AttestDojo

Jun 11

We Built the Loops Both Anthropic and OpenAI Are Now Telling Engineers to Write. Here's the Architecture.

#ai #agents #loopengineering #llm

5 min read

soy

Jun 11

PyTorch MLP Fusion, NVIDIA Agent Skill Security, & AI Tool Prompts Collection

#ai #llm #selfhosted

3 min read

leokwon68

Jun 11

I built an AI board of directors that debates a decision, then scores itself

#showdev #ai #llm #node

2 min read

Jun 11

From Pilots to Production: A Practical AI Playbook for Credit Unions

#ai #leadership #llm #machinelearning

7 min read

Jun 12

How to Humanize AI Text Without Sounding Robotic

#ai #llm #tutorial #writing

11 min read

Vainamoinen | Pulsed Media

Jun 11

Rent the Platform, Rent the Terms

#ai #programming #devops #llm

6 min read

Rob

Jun 11

Homelab Bakeoff: OpenClaw Outperforms Hermes… With Hermes Models

#agents #llm #homelab #buildinginpublic

11 min read

Alexandre Caramaschi

Jun 11

Por que n=50.000 mentiu para mim: a armadilha estatística por trás de uma falsa vantagem setorial

#datascience #llm #machinelearning #statistics

5 min read

Cor E

Jun 12

AI Email Agents Are Phishable: How OpenClaw Spilled User Data to Social Engineering Attacks

#security #ai #llm #appsec

4 min read

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