DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Memory is just re-sending: what building a CLI chat tool taught me about LLM cost

Memory is just re-sending: what building a CLI chat tool taught me about LLM cost

1
Comments 3
5 min read
A Simple Tool for Finding the Right Open-Source LLM for Your Hardware

A Simple Tool for Finding the Right Open-Source LLM for Your Hardware

Comments
1 min read
What If 1,000 Developers Bought Their AI Tokens Together?

What If 1,000 Developers Bought Their AI Tokens Together?

Comments 1
4 min read
ALTK-Evolve: On-the-Job Learning for AI Agents

ALTK-Evolve: On-the-Job Learning for AI Agents

Comments 4
5 min read
I built a small Python library to add retries, caching, fallbacks, budgets, and guardrails around native LLM SDK calls

I built a small Python library to add retries, caching, fallbacks, budgets, and guardrails around native LLM SDK calls

Comments 1
3 min read
Prompt Caching Strategies to Cut LLM Costs by 70%

Prompt Caching Strategies to Cut LLM Costs by 70%

Comments
5 min read
Is Claude Watermarking Code? What Developers Need to Know

Is Claude Watermarking Code? What Developers Need to Know

5
Comments
7 min read
Anthropic's Production Agent Guardrails: Lint Rules, Fuzzers, and Automated Reviews for Claude-Generated Code

Anthropic's Production Agent Guardrails: Lint Rules, Fuzzers, and Automated Reviews for Claude-Generated Code

2
Comments
7 min read
The AI Guessed 13/10. Seconds Later, I Said 5/10.

The AI Guessed 13/10. Seconds Later, I Said 5/10.

1
Comments
6 min read
How We Separate Persistent AI Identity from the Underlying LLM

How We Separate Persistent AI Identity from the Underlying LLM

Comments
4 min read
Two LLMs, One Key Pool, Zero Improvisation

Two LLMs, One Key Pool, Zero Improvisation

2
Comments 1
3 min read
Navigating the Hidden Traps of AI Provider Routing in Production

Navigating the Hidden Traps of AI Provider Routing in Production

Comments
6 min read
Small Models, Strong Guardrails

Small Models, Strong Guardrails

5
Comments
4 min read
An LLM Is Not Your Backend — Here's What I Learned

An LLM Is Not Your Backend — Here's What I Learned

1
Comments
4 min read
I traced the agentic calls. Here's where the token consumption comes from

I traced the agentic calls. Here's where the token consumption comes from

1
Comments 3
3 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.