Llm Page 76 - DEV Community

Skip to content

DEV Community

👋 Sign in for the ability to sort posts by relevant, latest, or top.

Prabhakar Chaudhary

Oct 23

MiniMax M3.1 Flash: How a 428B MoE Model Cuts Agentic AI Costs by 70% Without Sacrificing Performance

#ai #machinelearning #llm #opensource

5 min read

Oct 23

How to Summarize Large Logistics Documents with an LLM API Batch or Streaming

#ai #llm #logistics #summarization

7 min read

ColeMitchell4991

Oct 23

Summarize Large Documents with an LLM API — Batch vs Streaming Best Approach

#python #llm #documentprocessing

6 min read

Oct 23

The harness is not the model: what you pick with an agentic CLI

#ai #agents #claude #llm

13 min read

VoltageGPU

Oct 23

Calling open models inside a TEE with the OpenAI Python SDK

#ai #llm #privacy #python

2 min read

skvrtyk

Oct 23

LLMOps Is Supply Chain Work: Pinning the Inputs You Don't Control

#ai #llm #devops #python

5 min read

Abdullah

Oct 23

Local AI in 2026: What One 24 GB GPU Can Actually Run

#ai #llm #opensource #programming

3 min read

Oct 27

Coverage Is Not Capability: What Whisper Taught Me About African Speech

#ai #llm #machinelearning #openai

5 min read

Oct 23

The hidden prompt tokens in cheap LLM APIs

#ai #llm #api #testing

3 min read

Oct 23

The case for on-prem LLMs in security scanning

#security #llm #ai #devops

1 min read

Kulissa

Oct 27

How we built an AI buyer that pushes back (instead of agreeing with you)

#ai #voice #llm #startup

6 min read

Adrian M. Peticila

Oct 23

We audited 134,522 posts to see why AI writing still sounds fake (and open-sourced a deterministic syntactic gate)

#ai #llm #opensource #writing

3 min read

Oct 23

The real cost of "just add RAG"

#rag #ai #architecture #llm

4 min read

Runcrate

Oct 27

vLLM prefix caching on vs off: 7.5x the throughput with a 4,000-token system prompt on one L40S

#vllm #llm #gpu #performance

6 min read

Rost

Oct 23

Tiered Context: A Knowledge Hierarchy for AI Agents

#knowledgemanagement #ai #llm #architecture

15 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.