DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Tinkuy 0.1.0 — Donde los ríos se encuentran

Tinkuy 0.1.0 — Donde los ríos se encuentran

7
Comments 1
2 min read
Your eval's confidence interval assumes independent examples. Yours are clustered.

Your eval's confidence interval assumes independent examples. Yours are clustered.

2
Comments
4 min read
How I Let a Cloud AI Operate My Home Without Handing Over My Home

How I Let a Cloud AI Operate My Home Without Handing Over My Home

3
Comments
3 min read
The AI Wasn't Hallucinating. Our Architecture Was.

The AI Wasn't Hallucinating. Our Architecture Was.

Comments
2 min read
How to run Hermes, a self-improving personal AI agent, fully local with QVAC

How to run Hermes, a self-improving personal AI agent, fully local with QVAC

Comments
7 min read
What GLM-5.3-Flash Changes for AI Engineering Teams

What GLM-5.3-Flash Changes for AI Engineering Teams

6
Comments 2
4 min read
Your local LLM app needs guardrails before it needs prompts

Your local LLM app needs guardrails before it needs prompts

Comments
2 min read
I don't want to build another AI memory database

I don't want to build another AI memory database

2
Comments 2
7 min read
Key-space C3: the Bloom filter that closes referent gameability — tested

Key-space C3: the Bloom filter that closes referent gameability — tested

5
Comments
8 min read
We measured a week of inference. Routing by task difficulty cuts our cost per call roughly 48x — and flips which users are profitable.

We measured a week of inference. Routing by task difficulty cuts our cost per call roughly 48x — and flips which users are profitable.

3
Comments 3
5 min read
RAG Chunking Explained: How to Choose the Right Chunk Size and Strategy

RAG Chunking Explained: How to Choose the Right Chunk Size and Strategy

1
Comments
13 min read
I Scraped 20,000 YouTube Comments. The Videos and the Comments Were Having Two Different Conversations.

Divergence between tutorials and user pain

I Scraped 20,000 YouTube Comments. The Videos and the Comments Were Having Two Different Conversations.

9
Comments 9
3 min read
Your LLM Returns JSON That Isn't JSON: A Robust Structured-Output Pipeline for Local Models

Your LLM Returns JSON That Isn't JSON: A Robust Structured-Output Pipeline for Local Models

2
Comments 1
7 min read
Dead-Letter Queues for LLM Extraction Failures: Capture, Triage, and Replay Without Losing Trust

Dead-Letter Queues for LLM Extraction Failures: Capture, Triage, and Replay Without Losing Trust

1
Comments
6 min read
Building a Multi-Agent System in TypeScript

Building a Multi-Agent System in TypeScript

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