DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Stop hand-picking an LLM per request: a practical case for auto-routing

Stop hand-picking an LLM per request: a practical case for auto-routing

Comments
3 min read
OpenCode Tool Calling Internals

OpenCode Tool Calling Internals

2
Comments 3
13 min read
One base_url for GPT, Claude, and Gemini: cutting three SDKs down to one

One base_url for GPT, Claude, and Gemini: cutting three SDKs down to one

Comments
3 min read
Build the Reply Loop: Receive, Think, Respond

Build the Reply Loop: Receive, Think, Respond

Comments
5 min read
The On-Premise LLM Lottery

The On-Premise LLM Lottery

Comments
5 min read
Your AI Agent Folds When You Push Back: Measured Sycophancy and a Challenge-Triggered Verification Gate

Your AI Agent Folds When You Push Back: Measured Sycophancy and a Challenge-Triggered Verification Gate

Comments 25
8 min read
Our few-shot examples came from the eval set. The 0.94 was fiction.

Our few-shot examples came from the eval set. The 0.94 was fiction.

1
Comments 4
13 min read
Stop Blaming the Model. Your Latency Budget Is Probably Broken.

Stop Blaming the Model. Your Latency Budget Is Probably Broken.

Comments
3 min read
Retrieval-Augmented Self-Recall: The RAG Problem Nobody Talks About

Why similarity thresholds fail across models

Retrieval-Augmented Self-Recall: The RAG Problem Nobody Talks About

9
Comments 14
5 min read
AI Assistant Architecture: LLM, Memory, Tools, Routing, Observability

AI Assistant Architecture: LLM, Memory, Tools, Routing, Observability

Comments
14 min read
Memory Systems in AI Assistants

Memory Systems in AI Assistants

Comments
9 min read
AI Gateways: A Senior Engineer's Honest Take

AI Gateways: A Senior Engineer's Honest Take

5
Comments
16 min read
Nvidia Rubin's 10x Cheaper Tokens Hide a Footnote

Nvidia Rubin's 10x Cheaper Tokens Hide a Footnote

Comments
6 min read
Compact LLM chat history without LangChain (zero dependencies)

Compact LLM chat history without LangChain (zero dependencies)

1
Comments
2 min read
Building My Memory Layer - The Thinking Process Behind Every Layer

Building My Memory Layer - The Thinking Process Behind Every Layer

1
Comments
5 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.