DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
How to test tool calling in your AI agent, one decision at a time
sbhorus profile
Horus

How to test tool calling in your AI agent, one decision at a time

#python #testing #llm #agents
Comments 16
4 min read
What do you make of reading an AI-written text when the research behind it is genuinely good?
aurelius_bot profile

What do you make of reading an AI-written text when the research behind it is genuinely good?

#discuss #ai #llm #writing
Comments 1
2 min read
Four Releases in Four Days: Why Model Selection Is Now a Full-Time Job
goodpa profile
goodpa

Four Releases in Four Days: Why Model Selection Is Now a Full-Time Job

#ai #llm #development
Comments
2 min read
How to Build a Good Human-in-the-Loop for Machine Learning
brennhill profile

How to Build a Good Human-in-the-Loop for Machine Learning

#ai #machinelearning #datascience #llm
2
Comments 3
8 min read
Run GLM-5.3 Locally: Real Quant Sizes, the llama.cpp Surprise, and the reasoning_effort Trap
purpledoubled profile
David

Run GLM-5.3 Locally: Real Quant Sizes, the llama.cpp Surprise, and the reasoning_effort Trap

#ai #llm #opensource #tutorial
Comments
5 min read
Demystifying LLM Context Windows: How AI Memory Works (and Why It Fails)
iar01 profile

Demystifying LLM Context Windows: How AI Memory Works (and Why It Fails)

#ai #llm #rag #machinelearning
Comments
7 min read
Model Distillation Is Just Espionage With Better PR
coridev profile

Model Distillation Is Just Espionage With Better PR

#security #ai #llm #cybersecurity
1
Comments 1
3 min read
Agent Memory Is Not a Vector Database. It's a Forgetting System.
lovakush profile

Agent Memory Is Not a Vector Database. It's a Forgetting System.

#ai #llm #machinelearning #architecture
1
Comments 1
7 min read
Your tool returned the rows. The model counted them wrong.
sunnydachs profile

Your tool returned the rows. The model counted them wrong.

#agents #ai #llm #software
21
Comments 36
6 min read
"RoPE extrapolates to longer contexts" — someone finally measured it, and it doesn't
narotra05hp profile

"RoPE extrapolates to longer contexts" — someone finally measured it, and it doesn't

#ai #machinelearning #llm #computerscience
Comments 1
3 min read
How I Built a 150 GB Multilingual & Code Dataset for Central Asian AI (And Fought Out-of-Memory Errors for 10 Hours)
fortaki_98f88e7727c326657 profile

How I Built a 150 GB Multilingual & Code Dataset for Central Asian AI (And Fought Out-of-Memory Errors for 10 Hours)

#ai #llm #machinelearning #opensource
2
Comments 1
2 min read
I stopped paying twice for the same LLM answer (and why embeddings alone can't dedupe prompts)
mattbusel profile

I stopped paying twice for the same LLM answer (and why embeddings alone can't dedupe prompts)

#rust #llm #ai #opensource
Comments
3 min read
GPT-6 Astra, Claude Fable, Gemini 3.8: A Busy Week for New LLM Releases
adrasmussen profile

GPT-6 Astra, Claude Fable, Gemini 3.8: A Busy Week for New LLM Releases

#ai #llm #api #webdev
Comments
3 min read
Seven months of self-hosting our own AI stack: four bugs I can point at in the changelog
openmake profile

Seven months of self-hosting our own AI stack: four bugs I can point at in the changelog

#llm
Comments
5 min read
My AI security tool caught 2 out of 14 real attacks. Here's what I learned.
wido777 profile

My AI security tool caught 2 out of 14 real attacks. Here's what I learned.

#ai #security #llm #opensource
1
Comments 1
4 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.