DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Search Didn't Make Your LLM Dumber. Unweighted Context Did.

Search Didn't Make Your LLM Dumber. Unweighted Context Did.

1
Comments 15
3 min read
Evaluating Agents With an LLM-as-Judge Harness (Without Kidding Yourself About It)

Evaluating Agents With an LLM-as-Judge Harness (Without Kidding Yourself About It)

Comments 2
5 min read
Stop letting Claude guess your SaaS API auth flow

Stop letting Claude guess your SaaS API auth flow

7
Comments 1
5 min read
llms.txt and GEO in 2026: How to Get Your Site Cited by AI Search

llms.txt and GEO in 2026: How to Get Your Site Cited by AI Search

Comments 1
9 min read
I built 3 free APIs for LLM developers — here's what I shipped and why

I built 3 free APIs for LLM developers — here's what I shipped and why

Comments
2 min read
Generative AI: What Happens When You Type a Prompt?

Generative AI: What Happens When You Type a Prompt?

2
Comments
6 min read
We Measured LLM Prompt Caching in Production — Same Prompt, 0% to 91% Hit Rates

We Measured LLM Prompt Caching in Production — Same Prompt, 0% to 91% Hit Rates

Comments
5 min read
What Is Lua AI? A Developer's Guide to Building AI Agents

What Is Lua AI? A Developer's Guide to Building AI Agents

2
Comments
3 min read
Stop hand-parsing LLM JSON: structured outputs with pydantic-ai

Stop hand-parsing LLM JSON: structured outputs with pydantic-ai

2
Comments 1
2 min read
I stopped prompting my agent. Now I design the loop that prompts it.

I stopped prompting my agent. Now I design the loop that prompts it.

8
Comments 3
5 min read
The End of AI "Slop"? How Google is Using LoRA and LLMs to Fight Coordinated Synthetic Spam

The End of AI "Slop"? How Google is Using LoRA and LLMs to Fight Coordinated Synthetic Spam

1
Comments
5 min read
OWASP LLM Top 10 in Production: How I Audited My TypeScript Agent Pipeline Against All 10 Risks — and What I Found

OWASP LLM Top 10 in Production: How I Audited My TypeScript Agent Pipeline Against All 10 Risks — and What I Found

1
Comments
9 min read
/align v0.8 — personal evals for Claude Code, maintained by an LLM agent

/align v0.8 — personal evals for Claude Code, maintained by an LLM agent

Comments 1
4 min read
Notes: Memory, Context, and Large Language Models (LLMs)

Notes: Memory, Context, and Large Language Models (LLMs)

4
Comments 1
9 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 1
5 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.