DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
We logged every rejected tool call for a month. A third were our validation being wrong, not the model.
james_oconnor_dev profile

We logged every rejected tool call for a month. A third were our validation being wrong, not the model.

#llm #python #devops
1
Comments
2 min read
LLM Cost Optimization: How We Cut Reply Generation from $0.011 to $0.0009
helperx profile

LLM Cost Optimization: How We Cut Reply Generation from $0.011 to $0.0009

#ai #llm #javascript #node
1
Comments
9 min read
The Model Context Protocol (MCP): what it is and how to build a server
tech_nuggets profile

The Model Context Protocol (MCP): what it is and how to build a server

#mcp #llm #ai #opensource
Comments
7 min read
Designing Your Own AI Harness: A Deep Dive Into the Architecture of Agent Loops, Tools, Context, and Control
alexmercedcoder profile

Designing Your Own AI Harness: A Deep Dive Into the Architecture of Agent Loops, Tools, Context, and Control

#agents #ai #architecture #llm
1
Comments 2
20 min read
Local MCP Development with Python and Kiro
xbill profile

Local MCP Development with Python and Kiro

#mcpserver #kiro #llm #kirocli
Comments
8 min read
Beyond the Single Model: Why we Built an LLM Orchestrator with Consensus Engine?
anthropic profile

Beyond the Single Model: Why we Built an LLM Orchestrator with Consensus Engine?

#showdev #ai #architecture #llm
1
Comments
1 min read
Show HN: I replaced database deadlock victim selection with an LLM — here's the data
shunhewang profile

Show HN: I replaced database deadlock victim selection with an LLM — here's the data

#ai #database #llm #opensource
Comments
4 min read
Kronos Financial LLM, Local AI Health Checks & Code-RAG Benchmarking Insights
soytuber profile
soy

Kronos Financial LLM, Local AI Health Checks & Code-RAG Benchmarking Insights

#ai #llm #selfhosted
Comments
3 min read
Top 5 Open Source MCP Gateways in 2026, Compared
amazinglitter26 profile

Top 5 Open Source MCP Gateways in 2026, Compared

#ai #llm #mcp #opensource
15
Comments
5 min read
Does Quantization Break Tool-Calling? I Measured It on a 4GB Laptop GPU (BFCL, 3 Seeds, Bootstrap 95% CI)

Model family outperforms size as a predictor
happynood profile
Alexey

Does Quantization Break Tool-Calling? I Measured It on a 4GB Laptop GPU (BFCL, 3 Seeds, Bootstrap 95% CI)

#llm #machinelearning #python #opensource
3
Comments 10
4 min read
Deterministic Data Engineering With AI Harnesses: Using Claude Code, Codex, Antigravity, and OpenCode for Data Work You Can Actually Trust
alexmercedcoder profile

Deterministic Data Engineering With AI Harnesses: Using Claude Code, Codex, Antigravity, and OpenCode for Data Work You Can Actually Trust

#agents #ai #dataengineering #llm
Comments
19 min read
Gates Earned From Failure: a cost test for agent guardrails
vasyltretiakov profile

Gates Earned From Failure: a cost test for agent guardrails

#ai #llm #programming #architecture
Comments
16 min read
Why most AI apps fail in production (not in demos)
14babarali profile

Why most AI apps fail in production (not in demos)

#ai #llm #performance #softwareengineering
Comments
1 min read
The --schema-only flag that makes enterprise customers comfortable with AI
solasamuel profile

The --schema-only flag that makes enterprise customers comfortable with AI

#ai #llm #typescript #database
Comments
4 min read
Shipping 100,000 construction PDFs a month: what actually breaks
arif profile
arif

Shipping 100,000 construction PDFs a month: what actually breaks

#python #architecture #pdf #llm
1
Comments
17 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.