DEV Community

#reasoning

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
André Dias Moreira Prol: Claude 4 Extended Reasoning for Power Users

André Dias Moreira Prol: Claude 4 Extended Reasoning for Power Users

Comments
3 min read
André Dias Moreira Prol: raciocínio estendido do Claude 4 na prática

André Dias Moreira Prol: raciocínio estendido do Claude 4 na prática

Comments
3 min read
Twelve LLMs Played Werewolf. The Real Wolf Was the Thinking Knob.

Twelve LLMs Played Werewolf. The Real Wolf Was the Thinking Knob.

1
Comments
8 min read
OpenCoF Introduces Chain-of-Frame Reasoning for Enhanced Video Generation

OpenCoF Introduces Chain-of-Frame Reasoning for Enhanced Video Generation

Comments
3 min read
The Soul Question: Can a Language Model Have Psyche?

The Soul Question: Can a Language Model Have Psyche?

Comments
8 min read
The Syllogism Gap: Why Formal Logic Is Not Reasoning — And What It Means for AI

The Syllogism Gap: Why Formal Logic Is Not Reasoning — And What It Means for AI

Comments
9 min read
When AI Connects the Dots Doctors Couldn't: Lessons for Every Knowledge Worker

When AI Connects the Dots Doctors Couldn't: Lessons for Every Knowledge Worker

Comments
4 min read
A11: A Structured Way to Not Lie to Yourself During Reasoning

A11: A Structured Way to Not Lie to Yourself During Reasoning

Comments
3 min read
MCTS-Reasoning: Tree Search for LLM Reasoning

MCTS-Reasoning: Tree Search for LLM Reasoning

Comments
3 min read
An OpenAI Model Just Cracked an 80-Year-Old Math Problem

An OpenAI Model Just Cracked an 80-Year-Old Math Problem

Comments
3 min read
ARES: Cut LLM Agent Reasoning Costs 52% Per Step

ARES: Cut LLM Agent Reasoning Costs 52% Per Step

Comments
7 min read
The Memory Was Authorized. The Agent Should Have Refused. *AI Memory Judgment — CLAIM-28*

The Memory Was Authorized. The Agent Should Have Refused. *AI Memory Judgment — CLAIM-28*

3
Comments 2
8 min read
Más allá de la fuerza bruta: El razonamiento de la IA como un punto de equilibrio

Más allá de la fuerza bruta: El razonamiento de la IA como un punto de equilibrio

Comments 1
8 min read
Why your LLM agent drifts off-task by step 4 (and why prompts can't fix it)

Why your LLM agent drifts off-task by step 4 (and why prompts can't fix it)

2
Comments 2
3 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.