DEV Community

# llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
What is Production-Grade Agentic AI?
sergey-shamov profile

What is Production-Grade Agentic AI?

#agents #ai #architecture #llm
Comments
3 min read
2026 Q1 is the year developers still build the agent harness. 2026 Q3 / 2027 is the year the LLM builds its own harness.
programming_withjackche profile

2026 Q1 is the year developers still build the agent harness. 2026 Q3 / 2027 is the year the LLM builds its own harness.

#agents #ai #llm #tooling
Comments
4 min read
How I Unified 14+ AI Models Behind One OpenAI-Compatible API
daniel_dong_sdwgw041 profile

How I Unified 14+ AI Models Behind One OpenAI-Compatible API

#ai #llm #python #opensource
Comments
2 min read
Why Enterprises Should Not Let LLMs Execute SQL Directly?
_706015150500ca0399b12 profile

Why Enterprises Should Not Let LLMs Execute SQL Directly?

#architecture #llm #security #sql
Comments
1 min read
Reasoning happens before the response
frank_brsrk profile

Reasoning happens before the response

#ai #mcp #llm #agents
Comments
5 min read
Qwen 3.6 27B and 35B MTP vs Standard on 16GB GPU
rosgluk profile
Rost

Qwen 3.6 27B and 35B MTP vs Standard on 16GB GPU

#selfhosting #llm #ai #llamacpp
Comments
8 min read
AI Weekly — 2026-05-22 to 2026-05-29 | Anthropic's $965B Moment and the Infrastructure Bet
yang_goufang_23c7ba674984 profile

AI Weekly — 2026-05-22 to 2026-05-29 | Anthropic's $965B Moment and the Infrastructure Bet

#ai #machinelearning #tech #llm
Comments
5 min read
One Open Source Project per Day #74: ai-engineering-from-scratch - Build AI Full-stack Skills from Ground Up
wonderlab profile

One Open Source Project per Day #74: ai-engineering-from-scratch - Build AI Full-stack Skills from Ground Up

#ai #opensource #llm #learning
Comments
2 min read
Stop letting LLMs hallucinate dates — a tool for AI agents
nazarf profile

Stop letting LLMs hallucinate dates — a tool for AI agents

#typescript #llm #opensource #ai
5
Comments 1
2 min read
NVIDIA's Nemotron Diffusion: One Model, Three Generation Modes, 6 Faster
thegatewayguy profile

NVIDIA's Nemotron Diffusion: One Model, Three Generation Modes, 6 Faster

#ai #machinelearning #llm #nvidia
Comments
3 min read
Continuous batching wrecked our p99 latency. Here's the trace.
marcuswwchen profile

Continuous batching wrecked our p99 latency. Here's the trace.

#machinelearning #llm #mlops #sre
Comments
4 min read
LangChain JsonOutputParser: Fix Malformed JSON from LLMs
aijsonmedic profile

LangChain JsonOutputParser: Fix Malformed JSON from LLMs

#python #langchain #llm #json
Comments
2 min read
Quantizing Gemma 4 on Mac with llama.cpp
0xkoji profile

Quantizing Gemma 4 on Mac with llama.cpp

#llm #gemma #quantization #ai
1
Comments
4 min read
Building a cost-efficient LLM caching layer in Python
ayinedjimi-consultants profile

Building a cost-efficient LLM caching layer in Python

#python #ai #llm #performance
Comments
5 min read
Why Claude Code Sessions Diverge: A Mechanism Catalog
vainamoinen profile

Why Claude Code Sessions Diverge: A Mechanism Catalog

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