DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
From SLM Fundamentals to webSLM: A Practical Path to Domain-Specific Browser AI

From SLM Fundamentals to webSLM: A Practical Path to Domain-Specific Browser AI

1
Comments
13 min read
Google Fills the Sora Gap, Recursive Bets $650M on Self-Improving AI, and the 35-Hour Agent That Changes Everything — May 24, 2026

Google Fills the Sora Gap, Recursive Bets $650M on Self-Improving AI, and the 35-Hour Agent That Changes Everything — May 24, 2026

Comments
6 min read
How a Missing Config Line Cost Me 38x More for the Same Model

How a Missing Config Line Cost Me 38x More for the Same Model

Comments
2 min read
Day 1: I'm Done Writing Prompts by Hand — Meet DSPy

Day 1: I'm Done Writing Prompts by Hand — Meet DSPy

Comments
4 min read
We built the first slice of a cockpit that doesn't trust an agent's "done" — then our own tests lied to us

We built the first slice of a cockpit that doesn't trust an agent's "done" — then our own tests lied to us

1
Comments 2
2 min read
Confidence is enough to decide. It's not enough to do.

Confidence is enough to decide. It's not enough to do.

1
Comments 6
5 min read
Beyond Function Calling: Why MCP is the "USB-C" of AI Integrations

Beyond Function Calling: Why MCP is the "USB-C" of AI Integrations

3
Comments
3 min read
Long context is not AI memory: a builder playbook for reliable AI apps

Long context is not AI memory: a builder playbook for reliable AI apps

5
Comments 2
4 min read
The Messages Array, in 4 GIFs

Hidden token costs of chat history

The Messages Array, in 4 GIFs

16
Comments 18
6 min read
We prevented our agents going rogue at runtime.

We prevented our agents going rogue at runtime.

Comments
3 min read
An open source LLM eval tool with two independent quality signals

An open source LLM eval tool with two independent quality signals

Comments
4 min read
AI Agent Context Packet: Give Agents the Right Inputs Without Blowing the Budget

AI Agent Context Packet: Give Agents the Right Inputs Without Blowing the Budget

2
Comments 1
9 min read
I checked six LLM-as-judge tools against human labels. The scoreboard was the wrong thing to read.

I checked six LLM-as-judge tools against human labels. The scoreboard was the wrong thing to read.

Comments 1
4 min read
Can AI Scan the Internet? AI Search vs Real-Time Monitoring

Can AI Scan the Internet? AI Search vs Real-Time Monitoring

1
Comments
5 min read
Running Llama Models Locally with Docker

Running Llama Models Locally with Docker

6
Comments 1
2 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.