DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
I Made an MCP Server Stop Calling Any AI API, and It Got More Useful
spranab profile

I Made an MCP Server Stop Calling Any AI API, and It Got More Useful

#mcp #ai #opensource #llm
1
Comments
5 min read
Building a Robust Market Research Assistant: Clean Architecture and LLM Tool Routing in Python
amals367 profile
Ama

Building a Robust Market Research Assistant: Clean Architecture and LLM Tool Routing in Python

#ai #programming #python #llm
Comments
2 min read
Runtime Intervention for LLMs: How Mentat Steers Agent Reasoning Without Fine-Tuning
mech_app_ai profile

Runtime Intervention for LLMs: How Mentat Steers Agent Reasoning Without Fine-Tuning

#agents #ai #api #llm
1
Comments
4 min read
Voorbij het taalmodel: de architectuur van betrouwbare AI-agents
percevalhasselman profile

Voorbij het taalmodel: de architectuur van betrouwbare AI-agents

#agents #ai #architecture #llm
Comments
9 min read
I Stopped Trusting YouTube Captions After an AI Agent Built the Wrong Thing
_68b6fbae5b434e30f3860e profile

I Stopped Trusting YouTube Captions After an AI Agent Built the Wrong Thing

#ai #opensource #llm
Comments
2 min read
Soul in Motion — 3:06 PM | 2026-08-27
dev_rajput_2d46f92f8a3418 profile

Soul in Motion — 3:06 PM | 2026-08-27

#ai #llm #devops #webdev
Comments
4 min read
Qwen3.8-Flash-Next Intelligence, Performance and Price Analysis!
mgobea profile

Qwen3.8-Flash-Next Intelligence, Performance and Price Analysis!

#qwen #llm #aibenchmarks #costanalysis
Comments
5 min read
I Replaced All My Cloud AI With Local Models — Here's What Actually Broke
samhartley_dev profile

I Replaced All My Cloud AI With Local Models — Here's What Actually Broke

#ai #llm #selfhosted #ollama
Comments
6 min read
GLM-5.3-Flash vs Qwen3.8-Flash: Two Labs Made Frontier AI 10x Cheaper This Week
jamilxt profile

GLM-5.3-Flash vs Qwen3.8-Flash: Two Labs Made Frontier AI 10x Cheaper This Week

#ai #llm #programming #devtools
1
Comments
7 min read
Qwen3 Embedding on Cloud TPU: Production Long-Context Retrieval with vLLM
cheng_zhang_45ee857b979b0 profile

Qwen3 Embedding on Cloud TPU: Production Long-Context Retrieval with vLLM

#ai #embeddings #qwen #llm
Comments
4 min read
Past the README Demo: Conversations, Healthcare Data, Agents, and CI Checks
yatindavra profile

Past the README Demo: Conversations, Healthcare Data, Agents, and CI Checks

#typescript #node #llm #opensource
1
Comments
3 min read
Local LLM vs Cloud API: My Mac Mini Cost Crossover
devlog profile

Local LLM vs Cloud API: My Mac Mini Cost Crossover

#ai #llm #macos
Comments
2 min read
AX-RAY: VIDRAFT's Causal Leakage Auditing Framework for Hybrid Sequence Models
ai_openfree_b23025ef075cf profile

AX-RAY: VIDRAFT's Causal Leakage Auditing Framework for Hybrid Sequence Models

#ai #machinelearning #opensource #llm
Comments
4 min read
I told my agent not to work around a refusal. It obeyed forever.
m_laazizi_a12c96ae8166ca0 profile

I told my agent not to work around a refusal. It obeyed forever.

#agents #ia #llm
Comments
3 min read
How to Give Local AI Agents Reliable Web Search
cloudsway profile

How to Give Local AI Agents Reliable Web Search

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