DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Token Budgeting: The Engineering Skill Nobody Talks About

Token Budgeting: The Engineering Skill Nobody Talks About

Comments
10 min read
Agent frameworks create workflows. Production needs run receipts.

Agent frameworks create workflows. Production needs run receipts.

Comments
2 min read
I spent two weeks optimizing 96GB of VRAM for local LLMs. Paid APIs still won.

I spent two weeks optimizing 96GB of VRAM for local LLMs. Paid APIs still won.

Comments
2 min read
How I reduced AI coding context by 95%

How I reduced AI coding context by 95%

8
Comments 11
3 min read
Catch LLM multi-hop hallucinations with zero extra tokens

Catch LLM multi-hop hallucinations with zero extra tokens

Comments 1
5 min read
Put the LLM last: I replaced a 7B model with a tiny Go classifier

Put the LLM last: I replaced a 7B model with a tiny Go classifier

4
Comments 5
7 min read
Stop Wasting Tokens: How to structure Claude.md for complex codebases.

Stop Wasting Tokens: How to structure Claude.md for complex codebases.

Comments
10 min read
Orchestrating AI: LangChain Framework Abstraction vs. Pure Native Code

Orchestrating AI: LangChain Framework Abstraction vs. Pure Native Code

1
Comments
5 min read
Chạy LLM trên iGPU: Giới hạn VRAM của Intel Arc và Radeon 780M

Chạy LLM trên iGPU: Giới hạn VRAM của Intel Arc và Radeon 780M

Comments
3 min read
La biblioteca di Borges:digitale.

La biblioteca di Borges:digitale.

Comments
2 min read
Prompt Caching in Practice: The 5-Minute Cache and Workflow Design

Prompt Caching in Practice: The 5-Minute Cache and Workflow Design

1
Comments 1
11 min read
Anvil

Anvil

Comments
9 min read
LLM Context Window Management: Strategies and Patterns

LLM Context Window Management: Strategies and Patterns

Comments
5 min read
Investigating a Hybrid LLM-GNN Model to Enhance the Efficiency of ADAPT-QAOA for Quantum Circuit Optimization

Investigating a Hybrid LLM-GNN Model to Enhance the Efficiency of ADAPT-QAOA for Quantum Circuit Optimization

5
Comments
4 min read
minbpe vs turboBPE: Two ways to think about tokenizer training

minbpe vs turboBPE: Two ways to think about tokenizer training

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