DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Self-Hosting a Terminal AI Coding Assistant (Ollama + Tailscale + Qwen Code)
abhishek_raghuwanshi_2ae7 profile

Self-Hosting a Terminal AI Coding Assistant (Ollama + Tailscale + Qwen Code)

#ai #llm #devops #selfhosted
Comments
5 min read
Context Hydration: When Memory Becomes Voice
kenwalger profile

Context Hydration: When Memory Becomes Voice

#ai #agents #architecture #llm
9
Comments
4 min read
Claude Code Subagents: Setup, Config, and When to Use Them
rosgluk profile
Rost

Claude Code Subagents: Setup, Config, and When to Use Them

#llm #ai #aicoding #dev
Comments
11 min read
Building AI Skills: GitHub Copilot Extensions, Claude Tools, and Reusable Agent Capabilities
avaneeshyadav profile

Building AI Skills: GitHub Copilot Extensions, Claude Tools, and Reusable Agent Capabilities

#agents #ai #llm #tutorial
Comments
12 min read
Your AI Remembers Everything and Trusts All of It

Focuses on the economics of forgetting
marcosomma profile

Your AI Remembers Everything and Trusts All of It

#ai #architecture #llm #systemdesign
40
Comments 45
11 min read
When Your Judge Can't Decide
debashish_ghosal profile

When Your Judge Can't Decide

#ai #llm #testing #agents
11
Comments 4
10 min read
From Joint State-Transition Prediction to Language: A Minimal Predictive Hypothesis of Intelligence
ylemkairos profile

From Joint State-Transition Prediction to Language: A Minimal Predictive Hypothesis of Intelligence

#ai #llm #machinelearning
Comments 2
10 min read
Score Coding Models With a 60-Line Harness Before You Spend a Cent
hackgo_6978 profile

Score Coding Models With a 60-Line Harness Before You Spend a Cent

#ai #llm #python #tutorial
Comments
5 min read
My Tool-Calling Loop Worked Fine, Until Compliance Wanted a Second Model to Check It
deep-27 profile

My Tool-Calling Loop Worked Fine, Until Compliance Wanted a Second Model to Check It

#llm #node #typescript #agents
2
Comments 1
4 min read
What I learned trying to benchmark local LLMs honestly
davidg3654 profile

What I learned trying to benchmark local LLMs honestly

#llm #python #opensource #ai
Comments 2
4 min read
With Context Windows This Large, Why Do We Still Need Memory?
uchan135 profile
jj_uc

With Context Windows This Large, Why Do We Still Need Memory?

#discuss #ai #llm #architecture
4
Comments 12
5 min read
Skyl v1.0.0 Is Now Stable — A Go Library Connecting Developers to 400+ AI Models Through One Unified Interface
bagombeka_job profile

Skyl v1.0.0 Is Now Stable — A Go Library Connecting Developers to 400+ AI Models Through One Unified Interface

#ai #go #llm #software
1
Comments
2 min read
Claude Code Just Landed, A CLI Agent That Edits Through Your Terminal
unfiltered_anshul profile

Claude Code Just Landed, A CLI Agent That Edits Through Your Terminal

#agents #ai #cli #llm
1
Comments
3 min read
Should Perplexity Be My Seventh Deep-Research Agent?
cryptopunk_dz2_bd054446a6 profile

Should Perplexity Be My Seventh Deep-Research Agent?

#discuss #ai #perplexity #llm
Comments
2 min read
RAG vs MAG: Two Paths to Smarter AI Memory
saumya_ranjanmohapatra_3 profile

RAG vs MAG: Two Paths to Smarter AI Memory

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