DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Brazilian Lawyers Fined R$84,000 for Prompt Injection in Court — Here's What Caught Them (and What Didn't)
coridev profile

Brazilian Lawyers Fined R$84,000 for Prompt Injection in Court — Here's What Caught Them (and What Didn't)

#security #ai #appsec #llm
Comments
5 min read
Your AI speed benchmark is measuring the one workload you don't run
thousand_miles_ai profile

Your AI speed benchmark is measuring the one workload you don't run

#discuss #ai #llm #inference
Comments
3 min read
How the itrstats tax assistant works: one query, every layer
kartikeyraj profile

How the itrstats tax assistant works: one query, every layer

#python #llm #agents #rag
Comments
10 min read
The Shai-Hulud Worm Is Now Open Source — Here's How to Stop Self-Replicating Prompts Before They Reach Your LLM
coridev profile

The Shai-Hulud Worm Is Now Open Source — Here's How to Stop Self-Replicating Prompts Before They Reach Your LLM

#security #llm #appsec #cybersecurity
1
Comments
5 min read
Three Months of Speed-Up Experiments on a 3090 Ti: Autoregressive DFlash MTP for Qwen3.6-27B
ianlpaterson profile

Three Months of Speed-Up Experiments on a 3090 Ti: Autoregressive DFlash MTP for Qwen3.6-27B

#ai #llm #gpu #performance
Comments
18 min read
Building llama.cpp from source on a Dell Precision T5820 with an RTX 3090 Ti (after seven power cycles)
ianlpaterson profile

Building llama.cpp from source on a Dell Precision T5820 with an RTX 3090 Ti (after seven power cycles)

#ai #llm #gpu #linux
Comments
16 min read
Inference Arbitrage: How I Route 200+ Daily LLM Calls Across Five Models
ianlpaterson profile

Inference Arbitrage: How I Route 200+ Daily LLM Calls Across Five Models

#ai #llm #devops #python
Comments
10 min read
LLM Benchmark Rankings 2026: 15 Models Tested on 38 Real Coding Tasks
ianlpaterson profile

LLM Benchmark Rankings 2026: 15 Models Tested on 38 Real Coding Tasks

#ai #llm #programming #benchmarking
Comments
28 min read
How I Track Claude, Codex, and Gemini Quotas from One Script
ianlpaterson profile

How I Track Claude, Codex, and Gemini Quotas from One Script

#ai #llm #productivity #bash
Comments
6 min read
The LLM Kept Saying “Fixed.” For Three Months, It Wasn’t.
ianlpaterson profile

The LLM Kept Saying “Fixed.” For Three Months, It Wasn’t.

#ai #llm #testing #programming
Comments
7 min read
Why MTP doesn't speed up your llama.cpp inference (and how to actually fix it)
alanwest profile

Why MTP doesn't speed up your llama.cpp inference (and how to actually fix it)

#llm #performance #machinelearning #gpu
Comments
5 min read
Designing a Multi-Agent AI System for Content Analysis and Recommendations
nagashreebhat profile

Designing a Multi-Agent AI System for Content Analysis and Recommendations

#systemdesign #llm #backend #ai
Comments
7 min read
I Cut My LLM API Bill by 73% — Here's the Exact Optimization Playbook
kollittle profile

I Cut My LLM API Bill by 73% — Here's the Exact Optimization Playbook

#ai #llm #devops #costoptimization
Comments
5 min read
What Production ML Systems Taught Me About AI Hallucinations
mansisomayajula03 profile

What Production ML Systems Taught Me About AI Hallucinations

#ai #machinelearning #llm #softwareengineering
Comments
4 min read
How LLMs Actually Work (And What That Means for Your Architecture Decisions)
coderslab profile

How LLMs Actually Work (And What That Means for Your Architecture Decisions)

#ai #machinelearning #llm #webdev
Comments
6 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.