DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
I Built a Memory API That Beats Mem0 on LongMemEval Without Using a Single LLM Token

I Built a Memory API That Beats Mem0 on LongMemEval Without Using a Single LLM Token

1
Comments 3
4 min read
I built a local Vault to take back my AI chats. V1.1 is out: Local AI Librarian, ChatGPT/Claude support, and a 1-Click Installer! 🚀

I built a local Vault to take back my AI chats. V1.1 is out: Local AI Librarian, ChatGPT/Claude support, and a 1-Click Installer! 🚀

Comments 1
2 min read
Your Scraper Returned a Clean Row. It Was Wrong.

Your Scraper Returned a Clean Row. It Was Wrong.

Comments
10 min read
Platforms Cross Below Neoclouds in 2026 First as Cached Pricing Diverges 59 Points Between Frontier and Platform Channels YTD

Platforms Cross Below Neoclouds in 2026 First as Cached Pricing Diverges 59 Points Between Frontier and Platform Channels YTD

1
Comments
6 min read
Point an OpenAI-compatible SDK at a ChatGPT API relay

Point an OpenAI-compatible SDK at a ChatGPT API relay

1
Comments
2 min read
Train LLMs from Scratch, Hermes Agent WebUI, & Efficient OlmoEarth v1.1 for Local AI

Train LLMs from Scratch, Hermes Agent WebUI, & Efficient OlmoEarth v1.1 for Local AI

Comments
3 min read
You can't debug a RAG you didn't instrument

You can't debug a RAG you didn't instrument

3
Comments 28
3 min read
I found this Massive 10M Context Window AI Model

I found this Massive 10M Context Window AI Model

1
Comments
6 min read
How LLMs Actually Work: The Explanation Nobody Else Gives You

How LLMs Actually Work: The Explanation Nobody Else Gives You

Comments
4 min read
The state of LLMs — June 2026

The state of LLMs — June 2026

Comments
5 min read
I shipped the wrong abstraction, then deleted it

I shipped the wrong abstraction, then deleted it

Comments
9 min read
Stop writing prompts to classify text: make evaluation declarative

Stop writing prompts to classify text: make evaluation declarative

Comments
4 min read
Una capa de prompts que se califica a sĂ­ misma por resultados, hace A/B testing de sus propias reescrituras, e intercambia al ganador casi sin despliegue

Una capa de prompts que se califica a sĂ­ misma por resultados, hace A/B testing de sus propias reescrituras, e intercambia al ganador casi sin despliegue

Comments
9 min read
91% pass rate. Gate green. Shipped. Worst regression we had all quarter.

91% pass rate. Gate green. Shipped. Worst regression we had all quarter.

1
Comments 1
2 min read
Why My Portfolio Website Still Doesn't Exist

Why My Portfolio Website Still Doesn't Exist

2
Comments
7 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.