DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Don’t “Execute” the LLM: Typed Actions + Verifiers for Safe Business Agents

Don’t “Execute” the LLM: Typed Actions + Verifiers for Safe Business Agents

1
Comments
8 min read
I audited CrewAI's default patterns for token efficiency. Score: 43/100.

I audited CrewAI's default patterns for token efficiency. Score: 43/100.

Comments
4 min read
A Spreadsheet Library Where You Can Build =LLM("question") — GridSheet v3 Release Notes

A Spreadsheet Library Where You Can Build =LLM("question") — GridSheet v3 Release Notes

Comments
10 min read
The LiteLLM Supply Chain Attack Changed How We Think About AI Cost Monitoring

The LiteLLM Supply Chain Attack Changed How We Think About AI Cost Monitoring

Comments
2 min read
How I added LLM fallback to my OpenAI app in 10 minutes

How I added LLM fallback to my OpenAI app in 10 minutes

Comments 1
3 min read
The Compound Interest of AI Context: Why Your Knowledge Layer Will Be Your Most Valuable Business Asset

The Compound Interest of AI Context: Why Your Knowledge Layer Will Be Your Most Valuable Business Asset

Comments
4 min read
Using GPT-4o-mini for Simple Tasks and GPT-4o for Complex Ones - Automatically

Using GPT-4o-mini for Simple Tasks and GPT-4o for Complex Ones - Automatically

Comments
5 min read
Building an LLM-as-a-Judge Evaluation Pipeline for Translation Quality

Building an LLM-as-a-Judge Evaluation Pipeline for Translation Quality

1
Comments
4 min read
CAG-EDU: Extending Context-Anchored Generation into Educational Intelligence

CAG-EDU: Extending Context-Anchored Generation into Educational Intelligence

1
Comments
5 min read
Mistral Medium 3.5 Review: A 128B Open-Weight Model With a Coding Agent That Opens PRs For You

Mistral Medium 3.5 Review: A 128B Open-Weight Model With a Coding Agent That Opens PRs For You

Comments
9 min read
How I built a Go proxy that keeps your LLM conversation alive when cloud quota runs out

How I built a Go proxy that keeps your LLM conversation alive when cloud quota runs out

1
Comments 1
2 min read
I Tested GPT-5.4 vs Claude Opus 4.6 vs Gemini 3.1 Pro on 5 Real Coding Tasks

I Tested GPT-5.4 vs Claude Opus 4.6 vs Gemini 3.1 Pro on 5 Real Coding Tasks

Comments
2 min read
Prompt Injection in Agentic Apps: 4 Layers of Defense

Prompt Injection in Agentic Apps: 4 Layers of Defense

Comments 2
9 min read
How to Build a Local Agentic Search Pipeline That Actually Gets Facts Right

How to Build a Local Agentic Search Pipeline That Actually Gets Facts Right

2
Comments
6 min read
CTX: I built a LLM-free code context loader that uses 5.2% of tokens

CTX: I built a LLM-free code context loader that uses 5.2% of tokens

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