DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
KV Cache Quantization: I Stretched Qwen 35B's Context 8 on 12GB VRAM
kenimo49 profile

KV Cache Quantization: I Stretched Qwen 35B's Context 8 on 12GB VRAM

#llm #ai #gpu #performance
1
Comments 1
3 min read
Is Agent Memory Just RAG With Extra Steps? We Opened the Source Code to Find Out

Vendor codebase audit settles the RAG debate
izgorodin profile

Is Agent Memory Just RAG With Extra Steps? We Opened the Source Code to Find Out

#ai #agents #rag #llm
6
Comments 16
6 min read
Catching the AI Agent Failure Mode Your Loop Guard Can't See
faizan_raza_8f0a1d3e9428e profile

Catching the AI Agent Failure Mode Your Loop Guard Can't See

#ai #opensource #llm #opentelemetry
Comments
4 min read
The End of the Algorithmic Overlord: Why AI's Future Belongs to Local-First, Open Source
hypernexus profile

The End of the Algorithmic Overlord: Why AI's Future Belongs to Local-First, Open Source

#ai #llm #opensource #mcp
1
Comments
5 min read
Claude vs ChatGPT vs Gemini: which AI is right for enterprise in 2026?
studiolabsai profile

Claude vs ChatGPT vs Gemini: which AI is right for enterprise in 2026?

#ai #llm #chatgpt #productivity
Comments
6 min read
Autoregressive vs Diffusion LLMs: How the Next Generation of Language Models Actually Writes Text
jamilxt profile

Autoregressive vs Diffusion LLMs: How the Next Generation of Language Models Actually Writes Text

#ai #llm #machinelearning #tutorial
Comments
8 min read
Stop Testing New AI Models in Production
ye_allen_ profile

Stop Testing New AI Models in Production

#ai #api #llm #devops
2
Comments 1
3 min read
My board never scored an outage as a regression. My evidence couldn't prove it.
agentdev9 profile

My board never scored an outage as a regression. My evidence couldn't prove it.

#evaluation #testing #llm #opensource
Comments
5 min read
How to change an LLM prompt in production without a code deploy
whydeepanshux profile

How to change an LLM prompt in production without a code deploy

#llm #ai #devops #promptengineering
6
Comments 5
8 min read
6 AI Gateways Compared for 2026: Routing, Governance, Caching, and Observability
ethan_5383afd058ff profile

6 AI Gateways Compared for 2026: Routing, Governance, Caching, and Observability

#ai #llm #monitoring #systemdesign
Comments
10 min read
The $3.2 Million Question: Calculating the True Cost of AI Vendor Lock-In
hypernexus profile

The $3.2 Million Question: Calculating the True Cost of AI Vendor Lock-In

#ai #llm #opensource #mcp
Comments
4 min read
I Told the AI "A Scanner Flagged This" — and It Agreed With Everything

Frontier models fall hard for confirmation bias
alimafana profile

I Told the AI "A Scanner Flagged This" — and It Agreed With Everything

#ai #security #llm #promptengineering
19
Comments 25
10 min read
I Tried to Prompt-Inject My Own Agent Engine. It Didn't Work. Here's Why.

Structural gates beat prompt safety
debashish_ghosal profile

I Tried to Prompt-Inject My Own Agent Engine. It Didn't Work. Here's Why.

#ai #agents #security #llm
41
Comments 11
12 min read
We benchmarked an AI agent with vs. without a semantic execution boundary. It cut token load ~63% — and that's before you count the electricity.
cristian_barragan_f2f519e profile

We benchmarked an AI agent with vs. without a semantic execution boundary. It cut token load ~63% — and that's before you count the electricity.

#agents #ai #llm #performance
Comments
6 min read
Three AI Agents Walk Into a Codebase, and Only One Walks Out
coridev profile

Three AI Agents Walk Into a Codebase, and Only One Walks Out

#ai #security #llm #cybersecurity
6
Comments 1
3 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.