DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
I Spent $8,857 Using Claude Code to Build 6 Projects. Here's What I Learned.

I Spent $8,857 Using Claude Code to Build 6 Projects. Here's What I Learned.

1
Comments 1
10 min read
portage-cli

portage-cli

Comments
3 min read
Tracking token usage across OpenAI, Anthropic, and Gemini: every streaming gotcha I hit

Tracking token usage across OpenAI, Anthropic, and Gemini: every streaming gotcha I hit

Comments
5 min read
The Hidden Cost of Production AI: How to Build Fallback Chains That Don't Fail Silently

The Hidden Cost of Production AI: How to Build Fallback Chains That Don't Fail Silently

Comments
5 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
9 Practical Ways Senior ML Engineers Reduce Inference Latency

9 Practical Ways Senior ML Engineers Reduce Inference Latency

Comments
3 min read
🚀 I Ran Claude Code on Every New Claude Model. Here's What Actually Ships.

🚀 I Ran Claude Code on Every New Claude Model. Here's What Actually Ships.

Comments
14 min read
The AI Cost Paradox: 280x Cheaper, Bills Still Rising

The AI Cost Paradox: 280x Cheaper, Bills Still Rising

Comments
8 min read
20 Claude agents for M&A diligence, built on one rule: cite the source or cut the claim

20 Claude agents for M&A diligence, built on one rule: cite the source or cut the claim

Comments
6 min read
Building a Memory System for My AI Code Generator

Building a Memory System for My AI Code Generator

Comments
2 min read
60–95% fewer tokens in your agent loops, same answers. Meet Headroom.

60–95% fewer tokens in your agent loops, same answers. Meet Headroom.

Comments
2 min read
The hardest LLM bugs are contract failures, not hallucinations

The hardest LLM bugs are contract failures, not hallucinations

Comments
2 min read
Load late, load little: just-in-time context for conversation history

Load late, load little: just-in-time context for conversation history

Comments
10 min read
Temperature and Sampling: the LLM Creativity Dial

Temperature and Sampling: the LLM Creativity Dial

Comments
1 min read
Self-RAG: Let the Model Decide When to Retrieve, Then Grade Itself

Self-RAG: Let the Model Decide When to Retrieve, Then Grade Itself

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