DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Three AI Labs Admit Their Agents Cheat and Break Into Things. Nobody Blinked.
coridev profile
Cor E

Three AI Labs Admit Their Agents Cheat and Break Into Things. Nobody Blinked.

#security #ai #llm #cybersecurity
1
Comments 3
3 min read
LLMs on Consumer Hardware — Part 2: Prefill and the Failure of the AI PC
sven_welack profile

LLMs on Consumer Hardware — Part 2: Prefill and the Failure of the AI PC

#localllama #ai #llm #homelab
Comments 3
4 min read
Small language models (1B–3B): what they're good for after fine-tuning
pranjulrathour profile

Small language models (1B–3B): what they're good for after fine-tuning

#smallmodels #finetuning #llm #deployment
Comments
3 min read
Instruction tuning vs domain adaptation: two different fine-tuning goals
pranjulrathour profile

Instruction tuning vs domain adaptation: two different fine-tuning goals

#finetuning #instructiontuning #domainadaptation #llm
Comments
3 min read
QLoRA hyperparameters that actually matter (rank, alpha, learning rate, epochs)
pranjulrathour profile

QLoRA hyperparameters that actually matter (rank, alpha, learning rate, epochs)

#qlora #hyperparameters #finetuning #llm
Comments
3 min read
LoRA vs QLoRA vs full fine-tuning: cost, quality and when each makes sense
pranjulrathour profile

LoRA vs QLoRA vs full fine-tuning: cost, quality and when each makes sense

#finetuning #lora #qlora #llm
Comments
3 min read
MCP Tool Descriptions Are Instructions, Not Metadata -- and That Is the Exploit
rxkov profile
Rxkov

MCP Tool Descriptions Are Instructions, Not Metadata -- and That Is the Exploit

#ai #llm #mcp #security
1
Comments 3
5 min read
OPSEC for Agents: Scope, Caps, Monitoring, and Kill Switches
rxkov profile
Rxkov

OPSEC for Agents: Scope, Caps, Monitoring, and Kill Switches

#agentic #llm #opsec #security
Comments 1
4 min read
The Orchestrator's Deputy Has No Scope: Ambient Authority Is the Root Bug in Multi-Agent AI
rxkov profile
Rxkov

The Orchestrator's Deputy Has No Scope: Ambient Authority Is the Root Bug in Multi-Agent AI

#agents #cybersecurity #llm #security
Comments 2
5 min read
Qwen3.8-Max Is Huge. The Agent Harness Still Decides
zira125 profile
Zira

Qwen3.8-Max Is Huge. The Agent Harness Still Decides

#devops #ai #agents #llm
5
Comments 1
3 min read
LLM Agent Sandboxes Have Two Escape Surfaces. Only One Gets CVEs.
rxkov profile
Rxkov

LLM Agent Sandboxes Have Two Escape Surfaces. Only One Gets CVEs.

#agents #llm #mcp #security
Comments 2
5 min read
5 Things That Make an AI Agent Actually Useful (Not Just Cool)
aninmukhe profile

5 Things That Make an AI Agent Actually Useful (Not Just Cool)

#ai #llm #programming #productivity
Comments
4 min read
Giving AI Agents the Same RBAC Rules as Your Users: Building a Laravel Permission Layer LLMs Actually Respect
hosseinhezami profile

Giving AI Agents the Same RBAC Rules as Your Users: Building a Laravel Permission Layer LLMs Actually Respect

#ai #laravel #permission #llm
5
Comments
11 min read
RAG Poisoning Is a Supply Chain Attack, Not a Prompt Injection Variant
rxkov profile
Rxkov

RAG Poisoning Is a Supply Chain Attack, Not a Prompt Injection Variant

#ai #llm #rag #security
Comments
4 min read
Open-Source LLMs Are Unverified Dependencies: The Model Backdoor Gap npm Already Solved
rxkov profile
Rxkov

Open-Source LLMs Are Unverified Dependencies: The Model Backdoor Gap npm Already Solved

#cybersecurity #llm #opensource #security
Comments
5 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.