close

DEV Community

# llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Claude Code retries rate-limit errors for API keys, not for your Max plan

Claude Code retries rate-limit errors for API keys, not for your Max plan

Comments
4 min read
Designing a Synthetic Data Pipeline for Persian LLM Fine Tuning: From Topic Graphs to QLoRA Evaluation

Designing a Synthetic Data Pipeline for Persian LLM Fine Tuning: From Topic Graphs to QLoRA Evaluation

Comments
4 min read
The LLM is an ALU

The LLM is an ALU

Comments 1
14 min read
I gave myself an AI advisory board — three models argue, I decide

I gave myself an AI advisory board — three models argue, I decide

Comments
3 min read
Semantic caching our flaky-test summariser: 58% fewer LLM calls

Semantic caching our flaky-test summariser: 58% fewer LLM calls

Comments
4 min read
Route Every Prompt to the Cheapest Model: Building a Multi-LLM Cost Optimizer with Pydantic AI

Route Every Prompt to the Cheapest Model: Building a Multi-LLM Cost Optimizer with Pydantic AI

Comments
6 min read
'"An LLM and a harness": Nvidia''s simple thesis on what agents actually are'

'"An LLM and a harness": Nvidia''s simple thesis on what agents actually are'

Comments 1
2 min read
My Notes on LLMs

My Notes on LLMs

Comments
6 min read
GLM-5.2 vs Claude Opus: What the Numbers Actually Say for Developers

GLM-5.2 vs Claude Opus: What the Numbers Actually Say for Developers

Comments
7 min read
Catch LLM hallucinations with multi-model consensus

Catch LLM hallucinations with multi-model consensus

Comments
2 min read
You Wanted Me to Delete the DB, Right?

You Wanted Me to Delete the DB, Right?

Comments
3 min read
Three Rounds of Training Turn a Word-Predictor Into a Chatbot. None of Them Are Magic.

Three Rounds of Training Turn a Word-Predictor Into a Chatbot. None of Them Are Magic.

Comments
7 min read
Stop Sending the Raw User Prompt Straight to Your Retriever

Stop Sending the Raw User Prompt Straight to Your Retriever

Comments 3
2 min read
Why Multi-Head Attention Needs Position, Residuals, and Normalization

Why Multi-Head Attention Needs Position, Residuals, and Normalization

Comments
5 min read
How to Stop One Customer From Blowing Up Your Entire LLM Budget

How to Stop One Customer From Blowing Up Your Entire LLM Budget

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