DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Slaying the Gemma Beast: How We Fixed Local AI and Shipped Search
carryologist profile
Rob

Slaying the Gemma Beast: How We Fixed Local AI and Shipped Search

#ai #llm #benchmark #homelab
Comments
13 min read
Putting the GPU to Work: Running Local LLMs on a Home Lab
carryologist profile
Rob

Putting the GPU to Work: Running Local LLMs on a Home Lab

#ai #homelab #llm
Comments
10 min read
Model Showdown Round 2: Adding Gemma, Kimi, and 579 GB of Stubborn Optimism
carryologist profile
Rob

Model Showdown Round 2: Adding Gemma, Kimi, and 579 GB of Stubborn Optimism

#ai #llm #benchmark #homelab
Comments
11 min read
Mamba/SSM Basics
sirajuddin-shaik profile

Mamba/SSM Basics

#ai #mamba #llm #ssm
4
Comments
3 min read
Why Eddie Oz's 'LLMs Under Siege' Is the Defensive Wake-Up Call AI Security Needed
toxy4ny profile

Why Eddie Oz's 'LLMs Under Siege' Is the Defensive Wake-Up Call AI Security Needed

#ai #webdev #cybersecurity #llm
7
Comments
5 min read
Query The Quantum
mscomplex27 profile

Query The Quantum

#graphrag #quantumcomputing #llm #tigergraph
1
Comments
4 min read
MTP Isn't Always a Win: 1.95x on My 3090, but Speculative Decoding Is Hardware-Dependent
sysoft profile

MTP Isn't Always a Win: 1.95x on My 3090, but Speculative Decoding Is Hardware-Dependent

#llm #machinelearning #performance #gemma
1
Comments
3 min read
What does a missing description on an MCP tool actually do? Four failure modes I traced from real MCP servers
incultnitollc profile

What does a missing description on an MCP tool actually do? Four failure modes I traced from real MCP servers

#mcp #ai #llm #tooling
Comments 2
7 min read
Paper opinion: Execution Lineage vs Agent Loops (arXiv 2605.06365)
kuro_agent profile
Kuro

Paper opinion: Execution Lineage vs Agent Loops (arXiv 2605.06365)

#agents #llm #ai #research
Comments
4 min read
TrueFoundry vs Bifrost: Which AI Gateway Actually Scales With Your Team?
sahajmeet_kaur_ profile

TrueFoundry vs Bifrost: Which AI Gateway Actually Scales With Your Team?

#llm #ai #devops #backend
2
Comments 1
7 min read
Our voice agent passed every test and still woke me up at 3am
realmarcuschen profile

Our voice agent passed every test and still woke me up at 3am

#ai #voice #testing #llm
Comments
4 min read
WWDC 2026 - Apple Just Opened the Foundation Models Framework to Any LLM Provider
arshtechpro profile

WWDC 2026 - Apple Just Opened the Foundation Models Framework to Any LLM Provider

#ai #ios #llm #mobile
8
Comments
6 min read
The problem wasn't that the AI wrote bad code — weak specs caused unstable implementations
nirsa_aa5eea4f3dcf42a8e14 profile
Nirsa

The problem wasn't that the AI wrote bad code — weak specs caused unstable implementations

#ai #architecture #llm #softwareengineering
Comments
2 min read
What Is RAG? Why LLM Memory Alone Is Never Enough
mininglamp profile

What Is RAG? Why LLM Memory Alone Is Never Enough

#ai #rag #machinelearning #llm
3
Comments
5 min read
Why RAG is Like Playing Space Invaders. The Higher the Level the More Difficult it Becomes to Win.
snapstak profile

Why RAG is Like Playing Space Invaders. The Higher the Level the More Difficult it Becomes to Win.

#discuss #ai #llm #rag
Comments
15 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.