DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
How I use premortems with Claude and Codex

Bypassing AI politeness with failure framing

How I use premortems with Claude and Codex

54
Comments 6
5 min read
Most Generative AI Projects Don’t Fail Because of the Model

Most Generative AI Projects Don’t Fail Because of the Model

Comments
4 min read
The Core of a Coding Agent Is 128 Lines of Python. So I Built One From Scratch.

The Core of a Coding Agent Is 128 Lines of Python. So I Built One From Scratch.

2
Comments
4 min read
The LLMPositive Guy Manifesto

The LLMPositive Guy Manifesto

Comments
3 min read
AIChain!? Why Another LLM Library?

AIChain!? Why Another LLM Library?

1
Comments 5
4 min read
Agent evals should explain why they passed

Agent evals should explain why they passed

1
Comments
1 min read
Why production RAG fails — and the boring metrics that fix it

Why production RAG fails — and the boring metrics that fix it

Comments 1
6 min read
Compiled AI for GCP Landing Zones

Compiled AI for GCP Landing Zones

1
Comments
7 min read
Your AI Agent Will Fail in Production Without a Reliability Layer

Your AI Agent Will Fail in Production Without a Reliability Layer

Comments
4 min read
Chunking for RAG: stop tuning the wrong knob

Chunking for RAG: stop tuning the wrong knob

2
Comments
5 min read
We ported how brains manage the cost of thinking to LLM systems

We ported how brains manage the cost of thinking to LLM systems

Comments 2
9 min read
I thought Mnemara would save tokens for cloud based models, that was wrong.

I thought Mnemara would save tokens for cloud based models, that was wrong.

Comments
4 min read
Fable disappeared overnight. That's the best ad for open-weight AI anyone could have run.

Fable disappeared overnight. That's the best ad for open-weight AI anyone could have run.

1
Comments
3 min read
AI Agents write code that compiles, but they still lie to the user. Here is how to fix the pipeline

AI Agents write code that compiles, but they still lie to the user. Here is how to fix the pipeline

Comments
1 min read
I Benchmarked 47 LLM Providers Against Real Queries - Here's What I Found 📊

I Benchmarked 47 LLM Providers Against Real Queries - Here's What I Found 📊

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