DEV Community

# llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
How a model upgrade silently broke our extraction prompt (and how we caught it)

How a model upgrade silently broke our extraction prompt (and how we caught it)

Comments
3 min read
BeeLlama v0.2.0: 164 tok/s on a 27B model, one RTX 3090

BeeLlama v0.2.0: 164 tok/s on a 27B model, one RTX 3090

Comments
3 min read
Context window == RAM?

Context window == RAM?

Comments
1 min read
Anna's Archive llms.txt: a routing guide for LLM crawlers

Anna's Archive llms.txt: a routing guide for LLM crawlers

Comments
3 min read
Gemini 3.5 Flash beat 3.1 Pro on coding and agents

Gemini 3.5 Flash beat 3.1 Pro on coding and agents

Comments
3 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
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
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
The File Modification Boundary We Found After 12 ForgeFlow Projects

The File Modification Boundary We Found After 12 ForgeFlow Projects

Comments
8 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
Qwen3-Coder-Next: 80B total, 3B active, 70.6 on SWE-Bench

Qwen3-Coder-Next: 80B total, 3B active, 70.6 on SWE-Bench

Comments
4 min read
O fim do “modelo que faz tudo”? Conheça o Conductor, a IA que orquestra outras IAs

O fim do “modelo que faz tudo”? Conheça o Conductor, a IA que orquestra outras IAs

Comments
8 min read
Google just commoditized the agent stack with a single API call

Google just commoditized the agent stack with a single API call

Comments
3 min read
How I use an LLM as a translation judge

How I use an LLM as a translation judge

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