DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
How Context Window Degradation Breaks Long-Running Agents in Production—and How to Engineer Your Way Out
priyeshdave6 profile

How Context Window Degradation Breaks Long-Running Agents in Production—and How to Engineer Your Way Out

#ai #agenticai #machinelearning #llm
Comments 2
6 min read
Catch Tool Calls That Invent Missing Arguments
byteio_3726 profile

Catch Tool Calls That Invent Missing Arguments

#python #testing #ai #llm
Comments 1
7 min read
What Nobody Tells You About Deploying LLMs at Scale
aibughunter profile

What Nobody Tells You About Deploying LLMs at Scale

#aiagents #ai #llm #webdev
Comments 1
4 min read
Agentic Security Testing Automation: From Vulnerability Discovery to Remediation-in-Loop
sanyaduan profile
Sanya

Agentic Security Testing Automation: From Vulnerability Discovery to Remediation-in-Loop

#ai #security #llm #agents
Comments
6 min read
Agent Self-Evolution: A Comprehensive Survey (2023-2025)
sanyaduan profile
Sanya

Agent Self-Evolution: A Comprehensive Survey (2023-2025)

#ai #llm #agents #machinelearning
Comments
8 min read
Give your coding agent a second brain
bagofnarcissism profile
JB

Give your coding agent a second brain

#ai #llm #python #mcp
Comments
4 min read
How I Built Maya: A Real-Time Voice AI Clinic Receptionist
cosmostechy profile

How I Built Maya: A Real-Time Voice AI Clinic Receptionist

#ai #llm #agents #buildinpublic
1
Comments
5 min read
🌿 TouchGrass AI: Turning Screen Time Into Outdoor Time with Local Gemma

Hacktoberfest: Maintainer Spotlight
ch_thriveni_d38962a48b783 profile

🌿 TouchGrass AI: Turning Screen Time Into Outdoor Time with Local Gemma

#showdev #ai #hacktoberfest #llm
2
Comments 1
2 min read
Has anyone actually noticed a difference in Opus 5.5 lately?
suryacreatx profile

Has anyone actually noticed a difference in Opus 5.5 lately?

#discuss #ai #claude #llm
1
Comments 4
1 min read
A 10M-Token Budget Is a Test Plan: C++ Patch Trials on MonkeyCode's Free Tier
devcpp_268 profile

A 10M-Token Budget Is a Test Plan: C++ Patch Trials on MonkeyCode's Free Tier

#ai #cpp #testing #llm
Comments
5 min read
3 A.M. Token Leak: An Autopsy of an Agent Loop
hackrs_3352 profile

3 A.M. Token Leak: An Autopsy of an Agent Loop

#ai #agents #debugging #llm
Comments
5 min read
Measuring the Multi-Agent Fork Tax
sadeghizad profile

Measuring the Multi-Agent Fork Tax

#ai #agents #llm #engineering
Comments 1
8 min read
Context Arithmetic: A 5-Stage Retrieval Pipeline for Voice Agents (500K docs to 400 tokens in <200ms)
phoenix031 profile

Context Arithmetic: A 5-Stage Retrieval Pipeline for Voice Agents (500K docs to 400 tokens in <200ms)

#ai #rag #architecture #llm
2
Comments 2
5 min read
Four Frontier Models in Four Days: Your Single-Provider Setup Is Now a Liability
goodpa profile
goodpa

Four Frontier Models in Four Days: Your Single-Provider Setup Is Now a Liability

#ai #llm #development
1
Comments 2
2 min read
A Cost-Aware Shadow Test for Trending Model Claims
devio_3007 profile

A Cost-Aware Shadow Test for Trending Model Claims

#ai #llm #testing #python
Comments
4 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.